The DOI matches its Crossref record; 460 of the 473 references it cites were found in a registry or an index; 3 of the 65 sources its claims cite were checked for support.
Applications of machine learning to machine fault diagnosis: A review and roadmap
Open accessAbstract
This paper presents a review and roadmap to systematically cover the development of intelligent fault diagnosis following the progress of machine learning theories and offer a future perspective.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
This review traces intelligent fault diagnosis through three eras—traditional machine learning, deep learning, and transfer learning—and proposes a roadmap toward machine health management. It argues that transfer learning is the key future direction for applying diagnosis models in engineering settings where labeled fault data are scarce.
Key findings
- The authors divide intelligent fault diagnosis into three periods: traditional machine learning before the 2010s, which relied on handcrafted features; deep learning since the 2010s, which enables end-to-end feature learning; and transfer learning as the future direction for cross-task and cross-domain diagnosis.
- Publication counts from Web of Science show rapid growth since the 2010s, with output from 2017 to 2019 nearly matching the total from before 2017.
- Among the transfer-learning studies reviewed, most address transfer within the same machine (TIM), while only four publications target transfer across different machines (TDM).
- The roadmap highlights future challenges including data quality and cleaning, imbalanced health states, streaming data analytics, negative transfer and source-domain selection, and interpretability of deep diagnosis models.
Methods
- Narrative literature review and roadmap, not an experimental study. It organizes intelligent fault diagnosis by three periods and by method families: expert systems, ANN, SVM, kNN, PGM, and decision trees; stacked AE, DBN, CNN, and ResNet; and transfer-learning categories.
- Uses Web of Science search results to count publications and motivate the periodization, then reviews representative applications across bearings, gears, motors, engines, and other machines.
- For transfer learning, it defines domains and tasks, distinguishes TIM from TDM scenarios, and categorizes approaches as feature-based, GAN-based, instance-based, and parameter-based.
Limitations
- The paper states no limitations of its own review; the following are evident from the text.
- Evident: no formal systematic-review protocol, search strings, inclusion/exclusion criteria, or quality appraisal are reported, and the publication-counting procedure is described only briefly.
- Evident: the roadmap and future directions are conceptual and perspective-based rather than empirically tested in the paper.
- Evident: coverage is selective and organized around the authors’ three-period framework, so it may not exhaustively capture all intelligent fault diagnosis literature.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
43 Own interpretation · 43 No basis given · 26 No full text of the sources · 7 Not checked yet · 4 Own result · 3 Sources not found · 1 Supported so far
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“First, the signal processing methods, such as the wavelet packet [369][370][371], the continue wavelet transform [372,373], the dual-tree complex wavelet transform [374,375], and the synchrosqueezing transform [376], are employed to preprocess the input 1D data, which are expected to convert the signals from the time domain to the time-frequency domain.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (2) Applications of CNN to machine fault diagnosis
What the sources say
- Not matchedcites [369][370][371]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [372] 372. S. Guo, T. Yang, W. Gao, C. Zhang, A novel fault diagnosis method for rotating machinery based on a convolutional neural network, Sensors 18 (2018) 1429. source
The Introduction describes transforming vibration signals with a continuous wavelet transform into a two-dimensional time-frequency scalogram and using its coefficients as CNN input. Section 3.2 confirms that the scalograms are processed as pixel images. This supports the claim as applied to the continuous wavelet transform, the method for which this source is cited; the supplied passages have no page numbers. (LLM, conf=0.93)
- Supportedcites [373] 373. S. Guo, T. Yang, W. Gao, C. Zhang, Y. Zhang, An intelligent fault diagnosis method for bearings with variable rotating speed based on pythagorean spatial pyramid pooling CNN, Sensors 18 (2018) 3857. source
The Introduction says the method uses continuous wavelet transform to turn vibration signals into two-dimensional scalograms that retain time-frequency information, which the CNN then processes. This supports the claim for the continuous-wavelet-transform citation; the paper need not establish the other listed methods. (LLM, conf=0.92)
- Supportedcites [374] 374. W. Sun, B. Yao, N. Zeng, B. Chen, Y. He, X. Cao, W. He, An intelligent gear fault diagnosis methodology using a complex wavelet enhanced convolutional neural network, Materials 10 (2017) 790. source
The citation supports the dual-tree complex wavelet transform example in the citing sentence, not the other listed methods. Section 6.2 describes applying DTCWT to a 1D time-domain signal and arranging frequency sub-bands over time as 2D data; Section 3.1 describes those sub-bands as input to the CNN’s convolutional layer. No page numbers are available in our copy. (LLM, conf=0.91)
- Not checked — no full text of the sourcecites [375] 375. X. Cao, B. Chen, B. Yao, W. He, Combining translation-invariant wavelet frames and convolutional neural network for intelligent tool wear state identification, Comput. Ind. 106 (2019) 71-84. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As shown in Fig. 1, the number of publications from 2017 to 2019 almost approaches to the total of that before 2017.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Furthermore, majority of studies focus on TIM scenarios, and only four 8 publications aim at TDM scenarios.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Among them, the studies about feature-based approaches account for the 7 largest proportion.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Furthermore, majority of studies focus on TIM scenarios, and only four 8 publications aim at TDM scenarios.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“The previous reviews just concerned IFD in a certain period like using traditional machine learning or using deep learning.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These reviews have not reported a roadmap on IFD to predict future trends yet.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“They just cover the publications of IFD before 2017.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In the past, traditional machine learning theories were popularly conducted in IFD from the debut to the 2010s.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“As a result, a review to systematically cover the development of IFD from the past to the future is still left blank.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- The quote only partly states this claim. 1
- It may state two separate claims as one. 47
- Probably not a substantial claim. 52
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“According to the results on the topic of machine fault diagnosis by using machine learning, the number of publications has rapidly increased since the 2010s.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“With regard to fault diagnosis, Tong et al. [420,421] employed JDA to complete the diagnosis tasks of bearings respectively used in the motor and the belt conveyor idler, and achieve better diagnosis accuracy than TCA-based diagnosis models.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 9
What the sources say
- Not checked — no full text of the sourcecites [420] 420. Z. Tong, W. Li, B. Zhang, F. Jiang, G. Zhou, Bearing fault diagnosis under variable working conditions based on domain adaptation using feature transfer learning, IEEE Access 6 (2018) 76187-76197. source
- Not checked — no full text of the sourcecites [421] 421. Z. Tong, W. Li, B. Zhang, M. Zhang, Bearing fault diagnosis based on domain adaptation using transferable features under different working conditions, Shock Vibrat. (2018) Doi: 10.1155/2018/6714520. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“The results showed that the trained diagnosis model could correctly recognize the unlabeled samples in the target domain although there were a small number of labeled samples in the target domain.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.3.3. Instance-based approaches
What the sources say
- Not checked — no full text of the sourcecites [36] 36. F. Shen, C. Chen, R. Yan, R.X. Gao, Bearing fault diagnosis based on svd feature extraction and transfer learning classification, in: Prognostics and System Health Management Conference, Beijing, China, 2015, pp. 1-6. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Compared with the diagnosis model just trained with a small number of target-domain samples, the fine-tuned diagnosis model presented the faster convergence rate and higher diagnosis accuracy.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
What the sources say
- Not checked — no full text of the sourcecites [438] 438. R. Zhang, H. Tao, L. Wu, Y. Guan, Transfer learning with neural networks for bearing fault diagnosis in changing working conditions, IEEE Access 5 (2017) 14347-14357. source
- Not checked — no full text of the sourcecites [37] 37. M.J. Hasan, J.M. Kim, Bearing fault diagnosis under variable rotational speeds using stockwell transform- based vibration imaging and transfer learning, Appl. Sci.-Basel 8 (2018) 2357. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Over the recent years, the advent of deep learning theories has reformed IFD in further releasing the artificial assistance since the 2010s, which encourages to construct an end-to-end diagnosis process.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, it needs a new review to summary the current research progress of IFD.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“With the help of traditional machine learning, the diagnosis models began to establish the relationship between the selected features and the health states of machines, which weakened the contribution of human labor in machine fault diagnosis and pushed it into the era of artificial intelligence.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the future, transfer learning theories will promote the research of IFD in engineering scenarios.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In order to improve the diagnosis accuracy of SVM-based models, researchers mainly focused on two branches, i.e., the modified SVM and the algorithm optimization.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of SVM to machine fault diagnosis
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Third, the SVM algorithm is originally used to solve binary classification tasks.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of SVM to machine fault diagnosis
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It is easy for PGM-based diagnosis models to achieve fault diagnosis with multiple health states of machines.They can be used to analyze the among-class discrepancy in convenience.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Furthermore, if the probabilistic relationship among the variables is not clear, it would be difficult to construct the diagnosis models.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, transfer-learning theories are expected to overcome the problems of lacking labeled samples and finally enlarge the applications of IFD in engineering scenarios.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The kNN-based diagnosis models are easily-implemented.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Furthermore, the expert system lacks the self-learning capability so that the diagnosis knowledge base is difficult to be expanded and corrected.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (2) Applications of expert system to machine fault diagnosis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Second, the performance of SVM-based diagnosis models is sensitive to the kernel parameters.The inappropriate kernel parameter even cannot induce the reliable diagnosis result.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of SVM to machine fault diagnosis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“Among the proposed methods, the algorithm of C4.5 is widely used to induce a decision tree for classification and obtain satisfactory accuracy and easily-understood classification rules [300].”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3) Decision tree
What the sources say
- Not checked — no full text of the sourcecites [300] 300. J.R. Quinlan, C4.5: Programs for machine learning, Morgan Kaufmann Publishers Inc., San Francisco, 1993.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, it takes much computation cost to handle the large-volume dataset.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The optimization objective solution of SVM refers to the convex quadratic optimization so that the diagnosis models could easily obtain the global optimal solution and further get the high diagnosis accuracy.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of SVM to machine fault diagnosis
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the performance of the diagnosis models greatly relies on the expert knowledge, which is difficult to be acquired and expressed.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (2) Applications of expert system to machine fault diagnosis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Fortunately, transfer learning is concerned to overcome such weaknesses by applying the knowledge learned from one or multiple tasks to other related but novel ones [27].”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > Abstract
What the sources say
- Not checked — no full text of the sourcecites [27] 27. S.J. Pan, Q. Yang, A survey on transfer learning, IEEE Trans. Knowl. Data Eng. 22 (2010) 1345-1359. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“The non-naive Bayesian classifier [288] is further developed to release the assumption, and it has also been used for fault diagnosis of bearings [289] and gears [290].”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
What the sources say
- Not checked — no full text of the sourcecites [288] 288. Y. He, R. Wang, S. Kwong, X. Wang, Bayesian classifiers based on probability density estimation and their applications to simultaneous fault diagnosis, Inf. Sci. 259 (2014) 252-268. source
- Not checked — no full text of the sourcecites [289] 289. J. Yu, B. Ding, Y. He, Rolling bearing fault diagnosis based on mean multigranulation decision-theoretic rough set and non-naive Bayesian classifier, J. Mech. Sci. Technol. 32 (2018) 5201-5211. source
- Not checked — no full text of the sourcecites [290] 290. M.Y. Asr, M.M. Ettefagh, R. Hassannejad, S.N. Razavi, Diagnosis of combined faults in rotary machinery by non-naive Bayesian approach, Mech. Syst. Signal Process. 85 (2017) 56-70. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In terms of multi-class classification tasks in IFD, it always needs to use complicated 2 architectures, such as OAA and OAO, to integrate results from multiple SVM-based models.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 1
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For these diagnosis objects, SVM-based diagnosis models are expected to recognize multiple states but not just the binary states of health and faults.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of SVM to machine fault diagnosis
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It is noted that the applications of naive Bayesian classifier are subject to an assumption of independence among features.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Different from the ANN, SVM-based diagnosis models are trained by minimizing the structural risk, which is beneficial to improving the interpretability of the models due to the rigorous theories.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of SVM to machine fault diagnosis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“In order to improve the generalization performance of decision tree, the random forest [306] is further investigated by integrating decisions from multiply tree-based classifiers.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3) Decision tree
What the sources say
- Not checked — no full text of the sourcecites [306] 306. L. Breiman, Random forests, Mach. Learn. 45 (2001) 5-32. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Thus, the one-against-all strategy (OAA) and one-against-one strategy (OAO) are mainly concerned [17].”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of SVM to machine fault diagnosis
What the sources say
- Not checked — no full text of the sourcecites [17] 17. A. Widodo, B.S. Yang, Support vector machine in machine condition monitoring and fault diagnosis, Mech. Syst. Signal Process. 21 (2007) 2560-2574. source
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Furthermore, the parameter 𝑘𝑘 is difficult to be determined, which greatly affects the performance of the diagnosis models.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“The kNN is a commonly-used supervised learning model to complete the classification tasks [13].”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
What the sources say
- Not checked — no full text of the sourcecites [13] 13. T.M. Cover, P.E. Hart, Nearest neighbor pattern classification, IEEE Trans. Inf. Theory 13 (1967) 21-27. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, the performance of kNN is subject to some problems, such as the indistinguishable neighborhood boundary and the difficulty in selecting the optimal neighborhood parameter.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
In the paper
“The diagnosis process includes three steps [1], i.e., data collection, artificial feature extraction, and health state recognition, as shown in Fig. 2.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2.1. Overview
What the sources say
- Not matchedcites [1] 1. Y. Lei, Intelligent fault diagnosis and remaining useful life prediction of rotating machinery, Butterworth- Heinemann Elsevier Ltd, Oxford, 2016.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In particular, the imbalanced distribution of the collected data would reduce the diagnosis accuracy of this kind of diagnosis models.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (1) kNN
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“4) The prosperous development of sensor technologies and data transmission, especially with the advent of IoT and high-speed internet, promotes to collect a large number of data that contain the real-time information.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.2. Step 1: Big data collection
What the sources say
- Not matchedcites [314] 314. G.I. Platforms, The rise of industrial big data, 2012, Available: http://www.geautomation.com/download/rise-industrial-big-data.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [315] 315. S. Yin, X. Li, H. Gao, O. Kaynak, Data-based techniques focused on modern industry: An overview, IEEE Trans. Ind. Electron. 62 (2015) 657-667. source
- Not matchedcites [316] 316. J. Lee, Industrial big data: The revolutionary transformation and value creation in industry 4.0 era, Mechanical Industry Press, Beijing, China, 2015.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Multiple AE can be stacked to represent the information contained in the input data deeply, and further obtain the features in deep layers, as shown in Fig. 11.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.3.1. Stacked AE-based approaches (1) A brief introduction to AE and Stacked AE
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In contrast, monitoring big data of machines holds these characteristics, and further extends to the much-specialized ones.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.2. Step 1: Big data collection
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Stacked AE-based diagnosis models are able to automatically represent the health information from the input monitoring data, which does not rely on much expert knowledge in feature extraction.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of AE to machine fault diagnosis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“First, the step of artificial feature extraction depends on the human labor, in which the engineers need to design powerful algorithms to extract sensitive features to health states of machines.However, it is still unrealistic for engineers to extract specialized features from the large-volume monitoring data by expert experience because of the huge labor cost.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2.5. Epilog
What the sources say
- Not checked — no full text of the sourcecites [310] 310. F. Jia, Y. Lei, J. Lin, X. Zhou, N. Lu, Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data, Mech. Syst. Signal Process. 72-73 (2016) 303-315. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Generally, big data includes four characteristics, i.e., volume, velocity, variety, and veracity [312].”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.2. Step 1: Big data collection
What the sources say
- Not matchedcites [312] 312. V. Mayer-Schnberger, K. Cukier, Big data: A revolution that will transform how we live, work, and think, Hodder & Stoughton Press, Carmelite House, London, 2013.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
None of the sources cited for this claim have been checked yet.
In the paper
“First, the healthy condition accounts for the majority of the longterm operation for machines, while faults seldom happen.Consequently, it is more easily to collect healthy data than faulty data.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.2. Step 1: Big data collection
What the sources say
- Not matchedcites [314] 314. G.I. Platforms, The rise of industrial big data, 2012, Available: http://www.geautomation.com/download/rise-industrial-big-data.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [315] 315. S. Yin, X. Li, H. Gao, O. Kaynak, Data-based techniques focused on modern industry: An overview, IEEE Trans. Ind. Electron. 62 (2015) 657-667. source
- Not matchedcites [316] 316. J. Lee, Industrial big data: The revolutionary transformation and value creation in industry 4.0 era, Mechanical Industry Press, Beijing, China, 2015.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Similar to other deep learning-based models, the diagnosis performance of CNN-based diagnosis models is subject to training with sufficient labeled samples.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (2) Applications of CNN to machine fault diagnosis
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The decision tree-based diagnosis models are naturally interpreted, which may not relay on the explanation of experts and can be easily converted into diagnosis rules.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3) Decision tree
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“As an unsupervised learning method, the stacked AE cannot be directly used to recognize the health states of machines.Therefore, a classification layer is usually added at the top of the architecture of the model, and the constructed diagnosis models need to be trained with sufficient labeled samples.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Applications of AE to machine fault diagnosis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, the ResNet-based diagnosis models inherit the advantages of the CNN-based diagnosis models, and possibly obtain high diagnosis accuracy, especially for the complicated operation conditions such as varying-speed or varying-load conditions.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.3.4. ResNet-based approaches
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Furthermore, they could achieve the diagnosis tasks with missing data.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3) Decision tree
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Furthermore, the number of training parameters in diagnosis models is reduced by sharing weights, which could accelerate the convergence and restrain the over fitting.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > (2) Applications of CNN to machine fault diagnosis
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Furthermore, the output layer is placed after the last extraction layer for health state recognition, generally with an ANN-based classifier because of the high capability in multi-class classification.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.3. Step 2: Deep learning-based diagnosis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Different from the stacked AE, DBN-based diagnosis models could automatically learn features from the input data by pre-training a set of stacked RBMs, which solves the problem of vanishing gradient in using BP algorithm to fine-tune the deep-layer networks.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.3.2. DBN-based approaches (1) A brief introduction to RBM and DBN
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It is necessary to use sufficient labeled data to train the constructed diagnosis models so as to obtain the convinced diagnosis results.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.3.2. DBN-based approaches (1) A brief introduction to RBM and DBN
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Deep learning-based diagnosis models automatically learn features from the input monitoring data and simultaneously recognize the health states of machines according to the learned features.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.3. Step 2: Deep learning-based diagnosis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“3) In order to collect sufficient health information of machines, there are many monitoring points on machines.Furthermore, multisource sensors are used to collect different kinds of data.The collected data are stored with various data structures.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.2. Step 1: Big data collection
What the sources say
- Not matchedcites [314] 314. G.I. Platforms, The rise of industrial big data, 2012, Available: http://www.geautomation.com/download/rise-industrial-big-data.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [315] 315. S. Yin, X. Li, H. Gao, O. Kaynak, Data-based techniques focused on modern industry: An overview, IEEE Trans. Ind. Electron. 62 (2015) 657-667. source
- Not matchedcites [316] 316. J. Lee, Industrial big data: The revolutionary transformation and value creation in industry 4.0 era, Mechanical Industry Press, Beijing, China, 2015.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, this kind of diagnosis models is easily caught by the over fitting and the low generalization performance, which would reduce the diagnosis performance of the models on the diagnosis tasks.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3) Decision tree
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Furthermore, the advent of state-of-art technologies, such as the edge computing and the applications of GPU, helps cope with monitoring data stream effectively.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.2. Step 1: Big data collection
What the sources say
- Not matchedcites [314] 314. G.I. Platforms, The rise of industrial big data, 2012, Available: http://www.geautomation.com/download/rise-industrial-big-data.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [315] 315. S. Yin, X. Li, H. Gao, O. Kaynak, Data-based techniques focused on modern industry: An overview, IEEE Trans. Ind. Electron. 62 (2015) 657-667. source
- Not matchedcites [316] 316. J. Lee, Industrial big data: The revolutionary transformation and value creation in industry 4.0 era, Mechanical Industry Press, Beijing, China, 2015.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In addition, the tree-type models are mostly constructed according to the expert knowledge.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3) Decision tree
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The deep learning theories construct end-to-end diagnosis models to automatically learn features from the collected data, and subsequently recognize the health states of machines.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“GAN-based approaches are able to generate fake labeled data that are similar to the actual data in the target domain.These fake data are able to help train reliable diagnosis models for the target domain.Therefore, such approaches are not affected by the condition whether labeled samples in the target domain are available, and they are expected to work for both the TIM scenarios and the TDM”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.3.2. GAN-based approaches
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Among them, feature-based approaches and GAN-based approaches are widely concerned because they can accomplish TDM scenarios subject to serious cross-domain discrepancy.In contrast, the instance-based approaches and parameter-based approaches are easily-implemented, and mostly focus on TIM scenarios subject to slight cross-domain discrepancy.Furthermore, the transfer performance of these”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.4. Epilog
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Instance-based approaches are easily-implemented for transfer scenarios.However, the transfer performance of them relates to the number of target-domain samples.Furthermore, they just are able to correct discrepancy in TIM scenarios, but incapable to implement transfer scenarios with serious discrepancy, such as TDM scenarios, because these approaches may lack the powerful capability of data”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.3.3. Instance-based approaches
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although there are state-of-the-art achievements of deep learning-based diagnosis models, an open issue of black box for deep hierarchical networks still confuses the academic researchers.It is difficult to acquire how these models learn the diagnosis knowledge from the monitoring data.As a result, the diagnosis models are constructed by experimental trials once and once again rather than the”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Deep learning-based diagnosis models are beneficial to reducing the cross-domain discrepancy by extracting deep-layer features [33].However, they are unable to adapt serious cross-domain discrepancy in some diagnosis scenarios, such as TDM.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 2) Deep learning and AdaBN
What the sources say
- Not checked — no full text of the sourcecites [33] 33. M. Long, J. Wang, Y. Cao, J. Sun, P.S. Yu, Deep learning of transferable representation for scalable domain adaptation, IEEE Trans. Knowl. Data Eng. 28 (2016) 2027-2040. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“To select the optimal one and guarantee the transfer success, it must take much time by experimental trials.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Second, the ANN-based diagnosis models are black-boxed due to the lack of rigorous 10 theoretical supports.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Imbalanced distribution in health states of machines is a common phenomenon in engineering scenarios.For example, the data collected from the healthy state are far more sufficient than those from the faults.If the imbalanced data are used to train the deep learning-based diagnosis models, the decision boundary of the models might be enforced to shift towards the health states with minority of”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Transfer learning is promising to expand IFD from academic research to engineering scenarios.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.4. Epilog
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
In the paper
“The fact is that machines mostly work under the healthy state, while the faults seldom happen.Thus, it is easier to collect healthy data than faulty data.As a result, the collected data are seriously imbalanced.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.4. Epilog
What the sources say
- Not checked — no full text of the sourcecites [26] 26. B. Yang, Y. Lei, F. Jia, S. Xing, An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings, Mech. Syst. Signal Process. 122 (2019) 692-706. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“The majority of the collected data are unlabeled.It is unrealistic to frequently stop the machines and inspect the health states due to the huge loss of wealth.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3.4. Epilog
What the sources say
- Not checked — no full text of the sourcecites [26] 26. B. Yang, Y. Lei, F. Jia, S. Xing, An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings, Mech. Syst. Signal Process. 122 (2019) 692-706. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“To bridge the gap, transfer learning theories are promising to construct diagnosis models, in which the diagnosis knowledge can be transferred across multiple diagnosis tasks.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The deep learning-based diagnosis models are trained by minimizing empirical risk, which really lacks rigorous theory.As a result, the physical meanings of them are difficult to be interpretable.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“It is possible to collect data from multiple source domains to match a common target domain, but the health information contained in these source domains is not all related to the that in the target domain in engineering scenarios.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“Transfer learning is able to get the above purpose, in which the knowledge from one or more diagnosis tasks can be reused to other related but different ones [27].”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.1. Motivation of applying transfer learning to IFD in engineering scenarios
What the sources say
- Not checked — no full text of the sourcecites [27] 27. S.J. Pan, Q. Yang, A survey on transfer learning, IEEE Trans. Knowl. Data Eng. 22 (2010) 1345-1359. source
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The process of learning features through deep learning is similar to the filtering process.Therefore, the adaptive filter theory is beneficial to analyzing the physical meanings of deep learning-based diagnosis models.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The constructed transfer learning-based diagnosis models are incapable to extract the related health information.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“According to Section 4.3, several approaches can be used in IFD, but the transfer performance of them is different for a given transfer scenario due to diverse performance ceilings.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In the past, IFD is implemented by the steps of data collection, artificial feature extraction, and health state recognition.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“With the revolution of big data, two special issues come to bring negative effects on the IFD using deep learning theories, i.e., imbalanced health states and analytics for data stream.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Diagnosis models based on TCA and JDA use the simple nonlinear mapping to extract features, which is difficult to fit the complicated distribution of data.As a result, the diagnosis models may get poor transfer results on the target domain because of the under-corrected discrepancy of the source and target domains.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 9
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Such issue has been concerned by the researchers for years, but the unreliable data transmission and the bandwidth limitations prevent the monitoring data stream from arriving the destination in an unbroken sequence.Furthermore, the inefficient computation capability impedes the success of data stream analytics.As a result, the IFD using deep learning is just implemented based on the off-line”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Parameter-based approaches fine-tune the pre-trained diagnosis models for fault diagnosis tasks in the target domain, which consumes less computation resources in handling massive data.However, the transfer performance of these approaches mostly depends on the number of labeled samples in the target domain.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.3.4. Parameter-based approaches
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By using traditional machine learning theories, the diagnosis models are able to automatically recognize the health states of machines.However, the literature review presents that the artificial feature extraction still relies on the expert knowledge.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 6. Conclusions
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“TCA just adapts the marginal probability distribution of the input cross-domain data, but 8 ignores the conditional probability distribution from the feature space to the target classes.Thus,”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 7
What the sources say
- Not checked — no full text of the sourcecites [30] 30. M. Long, J. Wang, G. Ding, J. Sun, P.S. Yu, Transfer feature learning with joint distribution adaptation, in: IEEE International Conference on Computer Vision, Sydney, Australia, 2013, pp. 2200-2207. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The statistical learning theories, such as SVM and PGM, have rigorous theory grounds, which promote to constructed diagnosis models with easily-understood model parameters, features, and diagnosis results.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 5. Discussions: Future challenges and a roadmap in IFD
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, it takes much cost to recollect sufficient data and further label them, which is unpractical for machines in engineering scenarios.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.1. Motivation of applying transfer learning to IFD in engineering scenarios
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper relies on this without support.
In engineering scenarios, machine users would like an automatic method to shorten the maintenance cycle and improve the diagnosis accuracy.
“In engineering scenarios, however, the machine users would like an automatic method to shorten the maintenance cycle and improve the diagnosis accuracy.”
The paper relies on this without support.
Traditionally, the process of fault diagnosis is mostly developed by manually inspecting the health states of machines, which increases the labor intensity and reduces the diagnosis accuracy.
“Traditionally, the process of fault diagnosis is mostly developed by manually inspecting the health states of machines, which increases the labor intensity and reduces the diagnosis accuracy.”
The paper relies on this without support.
Advanced signal processing methods greatly rely on specialized knowledge that maintainers mostly lack in engineering scenarios.
“However, these methods greatly rely on the specialized knowledge that maintainers mostly lack in engineering scenarios.”
The paper relies on this without support.
The diagnosis results by signal processing methods are too specialized to be understood by the machine users.
“Furthermore, the diagnosis results by signal processing methods are too specialized to be understood by the machine users.”
The paper relies on this without support.
The volume of collected data is dramatically increasing due to rapid development of internet technologies and IoT.
“With the rapid development of internet technologies and internet of things (IoT), the volume of collected data is dramatically gathered than ever before.”
The paper relies on this without support.
Increasingly-grown data bring more sufficient information to machine fault diagnosis, making it more possible to provide accurate diagnosis results.
“The increasingly-grown data bring more sufficient information to machine fault diagnosis so that it is more possible to provide accurate diagnosis results.”
The authors state this as an assumption.
Labeled data are sufficient and contain complete information about the health states of machines.
“the labeled data are sufficient and contain completed information about the health states of machines [35]”
The authors state this as an assumption.
The source-domain data are labeled, while there are minority of labeled data or even none of labeled data in the target domain.
“These two categories are both subject to the common assumption, in which the source-domain data are labeled, while there are minority of labeled data or even none of labeled data in the target domain.”
The authors state this as an assumption.
In instance-based approaches, minority of labeled samples are labeled in the target domain, which is insufficient to train reliable diagnosis models.
“In instance-based approaches, it is assumed that minority of labeled samples are labeled in the target domain, which is insufficient to train reliable diagnosis models.”
The authors state this as an assumption.
In parameter-based approaches, there are minority of labeled samples in the target domain.
“Similar to the instance-based approaches, parameter-based approaches also assume that there are minority of labeled samples in the target domain [27].”
The authors state this as an assumption.
The successes of transfer learning are subject to the assumption of related health information across multiple diagnosis tasks.
“The successes of transfer learning are subject to the assumption of related health information across multiple diagnosis tasks.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 3
“Yang et al [443] further proposed the polynomial kernel induced MMD to improve the transfer performance of the deep transfer learning-based diagnosis models”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > References
“443. I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets, in: Conference on Neural Information Processing Systems, Montreal, Canada, 2014, pp. 2672-2680.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.2.2. Transfer scenarios in IFD
“In TDM scenarios, the source and target domain data are collected from different but related machines like motors and generators.”
§ Applications of machine learning to machine fault diagnosis: A review and roadmap > 4.2.1. Transfer problems in IFD
“Such constraint can be explained by the example that it is unrealistic to use the diagnosis knowledge from motors for fault diagnosis of generators.”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Cortes, C., & Vapnik, V. N. (1995) · Machine Learning · doi:10.1023/a:1022627411411 · Cited by 34,565
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
(1992) · Cited by 23,431
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Cited by
Sorted by citations
Items 1,301–1,400 of 2,939
Yin, X., He, Q., Zhang, H., et al. (2022) · Electronics · doi:10.3390/electronics11152422 · Cited by 10
Xie, T., Huang, X., Park, H. W., Kim, H. S., & Choi, S.-K. (2023) · Journal of Engineering Design · doi:10.1080/09544828.2023.2177937 · Cited by 11
“…multisensory systems in modern industrial manufacturing, the following three technical challenges need to be overcome for MIF of different sensors (Lei et al. 2020; Yang and Ge 2022; Wang et al.2022): (1) High-frequency data explosion : To analyse health conditions from the high-frequency data…”
BackgroundLi, X., Yu, T., Li, D., Wang, X., Shi, C., Xie, Z., & Kong, X. (2023) · Sustainability · doi:10.3390/su15108034 · Cited by 10
Du, K., Wu, D., Ke, B., Li, M., & Zhu, B. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.112797 · Cited by 9
Cai, S., Wang, Y., Cai, W., Mo, Y., & Wei, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-12533-2 · Cited by 11
Harmonising convolutional networks and Transformer for transfer learning in bearing fault diagnosis
Su, K., Ran, G., Li, X., Wang, T., Yang, Y., CHU, F., & Kong, X. (2026) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2606949 · Cited by 9
Determining Dynamic Thresholds for Gas Turbine Engine Condition Monitoring
Li, Z., Miao, D., & Feng, K. (2022) · IEEE Access · doi:10.1109/access.2022.3198983 · Cited by 9
“While most of the thresholds are fixed [5], varying only to the parameter type or fault related feature (researches that consider fault diagnosis as a classification task [1] all have fixed thresholds – because the decision boundaries are fixed), or are dynamic regarding some discrete working conditions in previous re…”
BackgroundDynamics of a High-Power AMB–Multirotor Drivetrain
Jastrzębski, R. P., Putkonen, A., Zhuravlev, A., et al. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3317865 · Cited by 9
“Currently, this is also being exploited and has further potential with the physics-based digital twins, where a virtual counterpart is used throughout the lifetime of the product and supports its operation [11].”
BackgroundFault causes identification of rotating machinery based on multiphase zoom permutation entropy
Ma, C., Wang, X., Li, Y., & Cai, Z. (2023) · Measurement · doi:10.1016/j.measurement.2023.114028 · Cited by 9
Structured Data Ontology for AI in Industrial Asset Condition Monitoring
Hendriks, J., Azarm, M., & Dumond, P. (2024) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan13020023 · Cited by 9
“Machine learning (ML) approaches are increasingly popular for condition monitoring applications [5,6], and these can benefit from TSDBs that are specifically designed for this use.”
Yu, K., Wang, X., Cheng, Y., Feng, K., Zhang, Y., & Xing, B. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3396831 · Cited by 10
Frequency-focused sound data generator for fault diagnosis in industrial robots
Ahn, S., Ahn, S., Yoo, J., et al. (2024) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwae061 · Cited by 9
Zhang, X., Pan, X., Zeng, H., & Zhou, H. (2024) · Chinese Journal of Mechanical Engineering · doi:10.1186/s10033-024-01046-0 · Cited by 10
“At the same time, the application of deep learning in rotating machinery is also increasing [4–7].”
BackgroundEraliev, O., Lee, K., & Lee, C.-H. (2024) · Sensors · doi:10.3390/s24144661 · Cited by 9
Liu, H., Sun, Y., Wang, X., Wu, H., & Wang, H. (2024) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2024.111878 · Cited by 9
Wang, X., Jiao, J., Zhou, X., & Xia, Y. (2024) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2024.112052 · Cited by 10
Mo, C., Huang, K., Li, W., & Xu, K. (2024) · Sensors · doi:10.3390/s24227139 · Cited by 9
Zhou, H., Huang, Q., Zhou, C., et al. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3496776 · Cited by 9
A normal-fault sample translator for fault diagnosis with insufficient fault samples
Cheng, Y., Gu, H., & Suo, M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126109 · Cited by 9
Fang, Y., Nie, Y., Du, Y., et al. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3513643 · Cited by 9
Liu, B., Li, G., He, J., et al. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.103061 · Cited by 9
Xiang, Y., Zhou, K.-Q., Sarkheyli-Hägele, A., et al. (2024) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2400184 · Cited by 9
“These include the application of Petri nets (PNs) (Liu et al., 2017), deep learning techniques (Lei et al., 2020; Chen XH et al., 2021), and swarm intelligence algo‐ rithms (Ziani et al., 2017; Chen RH et al., 2020; Ye et al., 2023).”
Data-Driven Digital Twins for Real-Time Machine Monitoring: A Case Study on a Rotating Machine
Cheruku, S., Balaji, S., Delgado, A., et al. (2025) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4067600 · Cited by 9
Enhancing Smart Grid Efficiency
Sharma, B. B., Kumar, R., & Sharma, R. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-7352-1.ch011 · Cited by 9
Ren, J., Hu, C., Shang, Z., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3544700 · Cited by 9
“Meanwhile, with the rapid development of sensing and computing technologies, as well as the improvement of device intelligence, the demand for intelligent fault diagnosis is becoming increasingly urgent [2].”
Wang, H., Zhao, Y., Luo, Z., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adc1f8 · Cited by 9
Research on Open-Set Recognition Methods for Rolling Bearing Fault Diagnosis
Xu, J., Wang, Y., Xu, R., et al. (2025) · Sensors · doi:10.3390/s25103019 · Cited by 9
“In the past decade, data-driven fault diagnosis methods have rapidly advanced, with machine learning and deep learning being widely applied in intelligent fault diagnosis [3–11].”
Weng, W., Gong, W., Wan, A., et al. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.121620 · Cited by 9
Wan, A., Li, P., AL-Bukhaiti, K., Cheng, X., Ji, X., Wang, J., & Shan, T. (2025) · Next Energy · doi:10.1016/j.nxener.2025.100424 · Cited by 15
Machinery Fault Diagnosis Using Recurrent Neural Network: A Review
Xu, T., Wang, H., Liu, Z., et al. (2020) · Global Reliability and Prognostics and Health Management (PHM) · doi:10.1109/phm-shanghai49105.2020.9280936 · Cited by 9
“Nevertheless, although traditional IFD systems can recognize healthy states of machinery automatically, the diagnosis accuracy is less than satisfactory due to poor generalization performance of traditional machine learning theories which are not suitable for the infinitely growing data [8].”
BackgroundZhang, Y., Cheng, G., & He, L. X. (2022) · Measurement · doi:10.1016/j.measurement.2022.110905 · Cited by 9
Iterative Error Self-Correction for Robust Fault Diagnosis of Mechanical Equipment With Noisy Label
Wang, H., & Li, Y. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3189730 · Cited by 9
A Rolling Bearing Fault Diagnosis Method Using Multi-Sensor Data and Periodic Sampling
Zheng, J., Yang, C., Zheng, F., & Jiang, B. (2022) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme52920.2022.9859658 · Cited by 9
“Based on acceleration data, current approaches for fault diagnosis can be divided into three categories: signal processing (SP) methods, traditional machine learning (TML) methods, and deep learning (DL) methods [2], [3].”
MethodSmart Grid Stability Prediction with Machine Learning
Vera, V. D. G. (2022) · WSEAS TRANSACTIONS ON POWER SYSTEMS · doi:10.37394/232016.2022.17.30 · Cited by 9
Fault identification with limited labeled data
Berenji, A., Taghiyarrenani, Z., & Bastami, A. R. (2023) · Journal of Vibration and Control · doi:10.1177/10775463231164445 · Cited by 9
“Accordingly, IFD is de fi ned as taking advantage of intelligent methods to diagnose machine health states Lei et al. (2020).”
BackgroundMethodSilva, L. C. B., & Segatto, M. E. V. (2023) · Journal of the Optical Society of America B · doi:10.1364/josab.482200 · Cited by 9
Liu, Y., Wang, X., Dai, D., et al. (2023) · Agriculture · doi:10.3390/agriculture13071299 · Cited by 9
Generative Adversarial Network for State of Health Estimation of Lithium-ion Batteries
Ye, Z., Yu, J., Yang, P., Shang, Y., Zhou, R., & Ma, M. (2023) · IEEE Conference on Prognostics and Health Management · doi:10.1109/icphm57936.2023.10194162 · Cited by 9
“Recently, the deep learning methods have been widely employed for health prognostics of equipment [8], because of their powerful feature learning capacity and satisfactory performance.”
MethodBearing Fault Diagnosis Based on Deep Discriminative Adversarial Domain Adaptation Neural Networks
Guo, J., Chen, K., Liu, J., Ma, Y., Wu, J., Wu, Y., Xue, X., & Li, J. (2023) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2023.031360 · Cited by 12
Yang, F., Liu, J., Hua, C., Liu, W., & Dong, D. (2023) · Vehicle System Dynamics · doi:10.1080/00423114.2023.2295935 · Cited by 9
“Many studies have been conducted on model-based methods [3–13], data-driven methods [2, 14–20], and neural network methods [21–34], which accurately diagnosed medium and serious faults (50–80% performance degradation) of primary and secondary suspensions; however, they still have some limitations.”
Jiao, Z., Zhang, Z., Li, Y., Wu, Y., Liu, L., & Shao, S. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad30bc · Cited by 9
Huang, Y., Wen, B., Liao, W., et al. (2024) · Symmetry · doi:10.3390/sym16050512 · Cited by 9
“In recent years, machine learning, especially deep learning, has been extensively utilized in monitoring bearing conditions and diagnosing faults in rotating machinery [6–8].”
BackgroundA new multiple mixed augmentation-based transfer learning method for machinery fault diagnosis
Ge, H., Shen, C., Lin, X., et al. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad4d15 · Cited by 9
“Traditional fault diagnosis methods require manual intervention; that is, they rely on the expertise and prior knowledge of experts for fault diagnosis [4].”
Hardware implementation of bearing fault diagnosis using empirical mode decomposition
Ninawe, S., & Deshmukh, R. B. (2024) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2024.2380462 · Cited by 9
“In fact, these methods effectively extract features through the compression of relevant information [11,12].”
Adamou, A. A., & Alaoui, C. (2024) · Machines · doi:10.3390/machines12090604 · Cited by 10
Zheng, D., Han, B., Liu, G., Li, Y., & Yu, H. (2021) · IEEE Access · doi:10.1109/access.2021.3063743 · Cited by 9
“The prognostic health management (PHM) ensures that the machinery can run normally, which has great significance to reduce economic losses and guarantee operation safety [1].”
BackgroundMethodInfluentialHendriks, J., & Dumond, P. (2021) · Vibration · doi:10.3390/vibration4020019 · Cited by 9
“Classical applications of machine learning using hand-crafted features such as k-nearest neighbors (kNN) and support vector machines (SVM) have been widely explored and perform well in many fault diagnosis problems [3].”
BackgroundWen, T., Chen, R., & Tang, L. (2021) · IEEE Access · doi:10.1109/access.2021.3069884 · Cited by 9
“However, the representations can hardly be extracted for the data under all working conditions in the multi-source unsupervised domain adaptation (MUDA) [25].”
BackgroundOrder-Based Identification of Bearing Defects under Variable Speed Condition
Farhat, M. H., Chiementin, X., Chaari, F., et al. (2021) · Applied Sciences · doi:10.3390/app11093962 · Cited by 9
“Machine learning algorithms (MLA) are increasingly being used as an effective solution for processing vibration signals [7].”
MethodBearing Fault Diagnosis Based on RF-PCA-LSTM Model
Zhou, H., Cheng, L., Teng, L., & Sun, H. (2021) · Information Communication Technologies Conference (ICTC) · doi:10.1109/ictc51749.2021.9441578 · Cited by 9
“Many classification techniques have been applied to fault diagnosis, which can be summarized as follows: model-driven methods, knowledge-driven methods, statistics-driven methods, probabilistic reasoning methods, machine learning methods, and deep learning methods [11].”
MethodHuang, X., Li, Y., & Chai, Y. (2021) · Frontiers in Energy Research · doi:10.3389/fenrg.2021.747622 · Cited by 9
“At present, most of the fault diagnosis research on the gears of planetary gearboxes are based on vibration signals (Lei et al., 2020).”
BackgroundShi, Y., Deng, A., Deng, M., et al. (2022) · Measurement · doi:10.1016/j.measurement.2022.111797 · Cited by 9
Parallel network using intrinsic component filtering for rotating machinery fault diagnosis
Han, B., Liu, Z., Zhang, Z., Wang, J., Bao, H., Yang, Z., Xing, S., Jiang, X., & Li, B. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/aca705 · Cited by 9
Self-citationZhang, X., Li, Y., Liu, Y., Li, D., & Chen, X. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3217839 · Cited by 9
“Although the above diagnosis algorithms have achieved good results in the field of roller bearing diagnosis, some challenging problems limit the application of intelligent diagnosis methods in engineering practice: 1) the existing fault diagnosis models perform poorly in generalization and have been questioned due to…”
BackgroundXiong, J., Cui, S., & Tang, H. (2023) · Scientific Reports · doi:10.1038/s41598-023-31648-y · Cited by 10
A Semisupervised Method With Swarm Intelligence Optimization for Intelligent Fault Diagnosis
Xu, Z., Feng, Z., Wu, Q., & Yang, S. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3268131 · Cited by 10
“Intelligent fault diagnosis could be viewed as a pattern classification problem, which maps collected data to healthy or fault state patterns of machines from the perspective of machine learning [2], thus there is no need to obtain sufficient prior knowledge of relevant disciplines.”
BackgroundHwang, T., Ha, J. M., & Youn, B. D. (2023) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwad056 · Cited by 9
Fault Diagnosis of Rolling Bearings Based on Spectral Kurtosis Graph and LFMB Network
Huang, X., Qu, H., Lv, M., & Yang, J. (2023) · Russian Journal of Nondestructive Testing · doi:10.1134/s1061830923600363 · Cited by 8
“Compared with traditional fault diagnosis methods based on signal processing, these algorithms have achieved adaptability and generalization [14–16].”
Advancing Damage Assessment of CFRP-Composite through BILSTM and Hilbert Upper Envelope Analysis
Frik, M., Benkedjouh, T., Essaidi, A. B., & Boumédiene, F. (2023) · Russian Journal of Nondestructive Testing · doi:10.1134/s106183092360082x · Cited by 8
“Similarly, Lei et al. [29] summarized various machine learning and deep learning techniques and their applications specific to machine health monitoring, highlighting the effectiveness of deep learning methods, which are not restricted to specific machine types and involve minimal human…”
Hua, J., Wang, Z., Han, H., Gao, H., & Nie, L. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad5199 · Cited by 8
Early warning model based on support vector machine ensemble algorithm
He, S.-S., Hou, W., Chen, Z., Liu, H., Wang, J., & Cheng, P. (2024) · Journal of the Operational Research Society · doi:10.1080/01605682.2024.2360111 · Cited by 8
“The data-driven approach is to find out the hidden rules from a large number of historical data by machine learning or statistical analysis (Kolokas et al., 2020; Lei et al., 2020).”
Zhu, Z., Fang, X., Zhu, C., et al. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3415642 · Cited by 8
“Consequently, fault diagnosis has emerged as a crucial technology, attracting increasing attention in industries, such as manufacturing, energy, transportation, and healthcare [1], [2].”
BackgroundSreekumar, K. T., Kumar, C. S., & Ramachandran, K. I. (2024) · IEEE Access · doi:10.1109/access.2024.3438099 · Cited by 8
“Recently, with the advancements in machine learning and deep learning techniques, researchers have explored the use of these techniques in machine fault diagnosis and prognostics [11], [12], [13].”
BackgroundXu, Q., Li, Y., & Xie, M. (2024) · Water Air & Soil Pollution · doi:10.1007/s11270-024-07457-y · Cited by 9
“The problem of insufficient sample data also trou-bled the data mining in other fields including the synthetic aperture radar (SAR) (Song et al., 2018), the autonomous mobile robot (Wu et al., 2020), the automatic speech recognition (Golik et al., 2015), the fault diagnosis (Lei et al., 2020), etc.”
A hybrid transformer masked time-domain denoising network for vibration signals
Huang, X., Qian, W., Zhang, P., et al. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad99f2 · Cited by 8
Shahbaz, N., Chen, Y., Liang, F., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3529585 · Cited by 8
“Moreover, a comprehensive review revealed that SVM, KNN, and ensemble ML classifiers are widely favored and extensively used for predicting faults in induction motors due to their high accuracy [1], [2], [8], [9], [10], [11], [12], [13], [14], [15].”
A machine-learning-based approach for active monitoring of blade pitch misalignment in wind turbines
Milani, S., Leoni, J., Cacciola, S., et al. (2025) · Wind energy science · doi:10.5194/wes-10-497-2025 · Cited by 8
Xia, Y., Gao, J., Shao, X., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adbf34 · Cited by 8
Tang, R., Li, Y., & Zhang, S. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06390-9 · Cited by 8
“Although differences exist between the pretrained images and the target classification images, convolutional neural networks can still transfer during training on similar tasks [33], which increases the efficiency of the recognition and detection of guided wave defect images in ship pipelines.”
Liu, Z., Ma, H., Mao, S., et al. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.112594 · Cited by 8
Li, L., Ma, Z., Yu, Z., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adc4fd · Cited by 8
“Existing studies mainly focus on steady speed fault transfer diagnosis cases [19], but there are a large number of variable speed conditions in industrial scenarios for production tasks such as starting and braking.”
Motor Bearing Fault Diagnosis Based on LMSWT With Improved Multiscale Convolutional Neural Network
Fan, Y., Fu, Z., Li, H., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3565707 · Cited by 8
“The deep learning-based fault diagnosis methods proposed in recent years have effectively solved the problems of high personnel requirements and low accuracy in handling large amounts of data [2].”
Enhanced dual-channel feature fusion approach for rolling bearing fault diagnosis
Wen, J., Zheng, Y., Zhang, Y., & Yu, W. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2507761 · Cited by 9
“Next, adaptive average pooling is applied to reduce the spatial dimensions of the concatenated features, compressing the feature map to [32, 200, 1, 1], dynamically adjusting the pooling window to generate a high-dimensional feature vector.”
Gong, X., Zhang, S., Du, W., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3573359 · Cited by 8
A Dual-Attentive Multimodal Fusion Method for Fault Diagnosis Under Varying Working Conditions
Chu, Y., Zhu, L., & Lu, M. (2025) · Mathematics · doi:10.3390/math13111868 · Cited by 11
Jia, N., Huang, W., Ding, C., Wang, J., & Zhu, Z. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.111411 · Cited by 8
Hai, T., Yuan, J. P., Jiang, H., & Zhao, Q. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111614 · Cited by 11
Hu, W., Li, Q., Wang, T., & Chu, F. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.113122 · Cited by 11
Deng, S., Lei, Z., Wen, G., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111954 · Cited by 8
MB-ViT: MBConv vision transformer with time–frequency feature fusion for bearing fault diagnosis
Xiao, G., Yao, J., Zhong, L., et al. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11509-7 · Cited by 8
Literature Review on Fault Mechanism Analysis and Diagnosis Methods for Main Pump Systems
Ma, W., Ma, S., Zou, Z., Fu, B., Ma, J., Liu, J., & Zhang, Q. (2025) · Machines · doi:10.3390/machines13111000 · Cited by 10
PHM–GPT: A Large Language Model for Prognostics and Health Management
Ren, J., Liu, X., Wang, T., Zhao, Z., Chen, X., Li, W., & Yan, R. (2025) · Engineering · doi:10.1016/j.eng.2025.11.001 · Cited by 9
Multi-view feature consistency learning for cross-domain open-set mechanical fault diagnosis
Chen, G., Xiang, D., Liu, T., et al. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.113667 · Cited by 8
Yu, Y., Karimi, H. R., & Pawełczyk, M. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.113674 · Cited by 9
Zhang, Z., Miao, R., Wang, C., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112683 · Cited by 8
A novel complex network community clustering method for fault diagnosis
Chen, H., Lei, Z., Tian, F., et al. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac97b2 · Cited by 8
Tayyab, S. M., Chatterton, S., & Pennacchi, P. (2022) · Machines · doi:10.3390/machines10100908 · Cited by 8
Wang, Z., Zhang, L., Zhang, B., Zhao, J., & Wu, S. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3211708 · Cited by 8
“Due to its strong data fitting ability and generalization ability, various deep-learning models have been successfully applied in the fields of machine fault diagnosis [28], speech recognition [29], and computer vision [30].”
BackgroundLocal parameter identification with neural ordinary differential equations
Yin, Q., Cai, J., Gong, X., et al. (2022) · Applied Mathematics and Mechanics · doi:10.1007/s10483-022-2926-9 · Cited by 8
Kim, S.-H., Jung, W., Lim, D., & Park, Y. (2022) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon49645.2022.9969003 · Cited by 8
“Convolutional neural network (CNN) was proposed for image-related tasks, but recently CNN has been applied to fault diagnosis and completed superior achievements [13], [14].”
Fault Detection and Diagnosis for Thrust Drop of Launch Vehicles Against Disturbances
Zhang, R., Du, H., Wu, Y., et al. (2023) · Journal of Spacecraft and Rockets · doi:10.2514/1.a35592 · Cited by 8
Ye, Q., & Liu, C. (2023) · Applied Sciences · doi:10.3390/app13042376 · Cited by 8
Zhang, C., Sun, Q., Sun, W. P., et al. (2023) · Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture · doi:10.1177/09544054221147713 · Cited by 8
Zou, X., Tao, L., Sun, L., et al. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109372 · Cited by 8
A Survey of Few-shot Learning-based Compound Fault Diagnosis Methods for Industrial Processes
Ma, L., Shi, F., Wu, Z., et al. (2023) · IEEE International Conference on Industrial Cyber-Physical Systems (ICPS) · doi:10.1109/icps58381.2023.10128105 · Cited by 8
Li, X., Cheng, C., Zhang, G., et al. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3300435 · Cited by 8
Han, S., & Feng, Z. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3309363 · Cited by 8
“the health identification of rotating equipment [6].”
Two-dimensional explainability method for fault diagnosis of fluid machine
Liu, J., Hou, L., He, S., et al. (2023) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2023.08.080 · Cited by 8
Bottrighi, A., & Pennisi, M. A. (2023) · Information · doi:10.3390/info14090513 · Cited by 10
“…methodologies to a set of very heterogeneous domains including, to cite some, environment and energy applications [3–5], materials science [6,7], agriculture [8,9], natural language processing and computer vision [10,11], industrial applications and IoT [12–15], and public health policies [16,17].”
BackgroundZhang, K., Ding, K., Zheng, Q. S., Zou, Y., & Ding, G. (2023) · Journal of Vibration and Control · doi:10.1177/10775463231202550 · Cited by 9
“Numerous data-driven diagnostic methods have emerged, and the prognostics health management (PHM) of bearings has entered the era of AI (Lei et al., 2020).”
Metadata
- Authors
- Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. K.
- Affiliations
- Xi'an Jiaotong University (CN)
- Brunel University of London (GB)
- Corresponding author
- Lei, Yaguo
- Venue
- Mechanical Systems and Signal Processing
- Publisher
- Elsevier BV
- Published
- 2020-04
- Volume
- 138
- Pages
- 106587
- ISSN
- 0888-3270 (ISSN-L)
- OpenAlex
- W2998506103
- Cited by
- 2,997
- References
- 473
- Citations by year
- 2026: 553 · 2025: 549 · 2024: 497 · 2023: 515 · 2022: 439 · 2021: 327 · 2020: 115
- FWCI
- 172.43
- Type
- journal article
- Language
- en
- Open access
- green
- bura.brunel.ac.uk
- Locations
- Mechanical Systems and Signal Processing (publishedVersion)
- Brunel University Research Archive (BURA) (Brunel University London) (submittedVersion)
- Funders
- National Natural Science Foundation of China
- Ministry of Science and Technology of the People's Republic of China
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Reliability and Maintenance Optimization
- Keywords
- mechanical fault diagnosis, intelligent fault diagnosis, deep learning, transfer learning, condition monitoring, research trends
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
