Bearing Fault Diagnosis Based on Domain Adaptation Using Transferable Features under Different Working Conditions
Open accessThe DOI matches its Crossref record; 30 of the 31 references it cites were found in a registry or an index.
Abstract
Bearing failure is the most common failure mode in rotating machinery and can result in large financial losses or even casualties. However, complex structures around bearing and actual variable working conditions can lead to large distribution difference of vibration signal between a training set and a test set, which causes the accuracy‐dropping problem of fault diagnosis. Thus, how to improve efficiently the performance of bearing fault diagnosis under different working conditions is always a primary challenge. In this paper, a novel bearing fault diagnosis under different working conditions method is proposed based on domain adaptation using transferable features(DATF). The datasets of normal bearing and faulty bearings are obtained through the fast Fourier transformation (FFT) of raw vibration signals under different motor speeds and load conditions. Then we reduce marginal and conditional distributions simultaneously across domains based on maximum mean discrepancy (MMD) in feature space by refining pseudo test labels, which can be obtained by the nearest‐neighbor (NN) classifier built on training data, and then a robust transferable feature representation for training and test domains is achieved after several iterations. With the help of the NN classifier trained on transferable features, bearing fault categories are identified accurately in final. Extensive experiment results show that the proposed method under different working conditions can identify the bearing faults accurately and outperforms obviously competitive approaches.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing 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.”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [421]
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 2×
“DA can be considered as particular setting of transfer learning [17,18] which aims to leverage the knowledge learnt from a training domain to use in a different but related test domain by reducing distribution differences [18,19].”
BackgroundNonlinear Dimensionality Reduction by Locally Linear Embedding
Roweis, S. T., & Saul, L. K. (2000) · Science · doi:10.1126/science.290.5500.2323 · Cited by 14,965 · cited 1×
“Then reducing the dimensions is conducted for the sake of computational efficiency, such as principal component analysis(PCA) [11], locally linear embedding(LLE) [12] and linear discriminant analysis(LDA) [13].”
MethodDomain Adaptation via Transfer Component Analysis
Pan, S. J., Tsang, I. W., Kwok, J. T., & Yang, Q. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2091281 · Cited by 4,753 · cited 1×
“DA can be considered as particular setting of transfer learning [17,18] which aims to leverage the knowledge learnt from a training domain to use in a different but related test domain by reducing distribution differences [18,19].”
BackgroundText classification from labeled and unlabeled documents using EM
Nigam, K., Mccallum, A. K., Thrun, S., & Mitchell, T. (2000) · Machine Learning · doi:10.1023/a:1007692713085 · Cited by 2,736
Transfer Feature Learning with Joint Distribution Adaptation
Long, M., Wang, J., Ding, G., Sun, J., & Yu, P. S. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.274 · Cited by 2,071 · cited 4×
“test domains, respectively. Similarly let P(Y trjX tr) and Q(Y tejX te) be the conditional distributions of X tr = fx tr i gand X te = fx te i gfrom the training domain and test domain, respectively [20,25,26]. In this literature, we focus on the following settings: 1)one training domain and one test domain share the…”
BackgroundInfluentialZhang, W., Peng, G., Li, C., Chen, Y., & Zhang, Z. (2017) · Sensors · doi:10.3390/s17020425 · Cited by 1,925
Improving predictive inference under covariate shift by weighting the log-likelihood function
Shimodaira, H. (2000) · Journal of Statistical Planning and Inference · doi:10.1016/s0378-3758(00)00115-4 · Cited by 1,678
Unsupervised Visual Domain Adaptation Using Subspace Alignment
Fernando, B., Habrard, A., Sebban, M., & Tuytelaars, T. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.368 · Cited by 1,314 · cited 1×
“ation extracted from original input by PCA without domain adaptation. c. NN SA: NN classier with projection and domain adaptation using subspace alignment that only reduces the marginal distribution [28]. a is a baseline method without projection and domain adaptation techniques, which is widely used in the eld of fau…”
MethodDomain adaptation for object recognition: An unsupervised approach
Gopalan, R., Li, R., & Chellappa, R. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126344 · Cited by 1,053 · cited 1×
“.1 Domain adaptation DA as one research of transfer learning aims at making full use of information coming from both training domain and test domain during the learning process to adapt automatically [18,19,23]. Generally domain is considered as consisting of a feature space of inputs Xand a probability distribution o…”
BackgroundVisual Domain Adaptation: A survey of recent advances
Patel, V. M., Gopalan, R., Li, R., & Chellappa, R. (2015) · IEEE Signal Processing Magazine · doi:10.1109/msp.2014.2347059 · Cited by 899 · cited 3×
“test domains, respectively. Similarly let P(Y trjX tr) and Q(Y tejX te) be the conditional distributions of X tr = fx tr i gand X te = fx te i gfrom the training domain and test domain, respectively [20,25,26]. In this literature, we focus on the following settings: 1)one training domain and one test domain share the…”
BackgroundDeep Model Based Domain Adaptation for Fault Diagnosis
Lu, W., Liang, B., Cheng, Y., Meng, D., Yang, J., & Zhang, T. (2017) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2016.2627020 · Cited by 761
Domain adaptation for the classification of remote sensing data: An overview of recent advances
Tuia, D., Persello, C., & Bruzzone, L. (2016) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2016.2548504 · Cited by 675 · cited 1×
“This is caused by distribution differences between two domains, since features extracted from [15,16].”
BackgroundAdaptation Regularization: A General Framework for Transfer Learning
Long, M., Wang, J., Ding, G., Pan, S. J., & Yu, P. S. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.111 · Cited by 606 · cited 2×
“.1 Domain adaptation DA as one research of transfer learning aims at making full use of information coming from both training domain and test domain during the learning process to adapt automatically [18,19,23]. Generally domain is considered as consisting of a feature space of inputs Xand a probability distribution o…”
BackgroundMotor Bearing Fault Diagnosis Using Trace Ratio Linear Discriminant Analysis
Jin, X., Zhao, M., Chow, T. W. S., & Pecht, M. (2014) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2013.2273471 · Cited by 423 · cited 1×
“Then reducing the dimensions is conducted for the sake of computational efficiency, such as principal component analysis(PCA) [11], locally linear embedding(LLE) [12] and linear discriminant analysis(LDA) [13].”
MethodTransfer learning with neural networks for bearing fault diagnosis in changing working conditions
Zhang, R., Tao, H., Wu, L., & Guan, Y. (2017) · IEEE Access · doi:10.1109/access.2017.2720965 · Cited by 378 · cited 3×
“As a direct result, the classifier can achieve high accuracy on training domain while performing poorly on test domain [14].”
BackgroundMethodInfluentialMultivariate process monitoring and fault diagnosis by multi-scale PCA
Misra, M., Yue, H. H., Qin, S. J., & Ling, C. (2002) · Computers & Chemical Engineering · doi:10.1016/s0098-1354(02)00093-5 · Cited by 325 · cited 1×
“s, frequency-domain analysis [10] and time-frequency 2 domain analysis [2]. Then reducing the dimensions is conducted for the sake of computational eciency, such as principal component analysis(PCA) [11], locally linear embedding(LLE) [12] and linear discriminant analysis(LDA) [13]. Finally, with the help of a suitabl…”
MethodSaravanan, N., & Ramachandran, K. I. (2010) · Expert Systems with Applications · doi:10.1016/j.eswa.2009.11.006 · Cited by 324 · cited 2×
“Saravanan et al [8] proposed fault diagnosis method based on DWT and ANN, and it has been proved such approach had the potential to diagnose various faults of the gear box.”
MethodLi, Y., Xu, M., Wei, Y., & Huang, W. (2016) · Measurement · doi:10.1016/j.measurement.2015.08.034 · Cited by 275 · cited 1×
“With the vibration signals under different conditions are collected by sensors [6], many intelligent fault diagnosis methods have already achieved significant success in the field of fault diagnosis.”
MethodJalan, A. K., & Mohanty, A. R. (2009) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2009.07.014 · Cited by 269 · cited 1×
“…components and widely used in rotating machinery, whose health conditions, for example, the fault degree in different places under different motor speeds and loads, may have huge effect on the performance, reliability and residual life of the equipment [1] or even can lead to heavy casualties [2–4].”
BackgroundHuang, J., Hu, X., & Yang, F. (2011) · Measurement · doi:10.1016/j.measurement.2011.02.017 · Cited by 158 · cited 1×
“In [7], a genetic algorithm-based SVM(GA-SVM) model was presented, and it had high accuracy and generalization ability by optimizing parameters of SVM. N. Saravanan et al [8] proposed fault diagnosis method based on DWT and ANN, and it has been proved such approach had the potential to diagnose…”
MethodVisual domain adaptation via transfer feature learning
Tahmoresnezhad, J., & Hashemi, S. (2016) · Knowledge and Information Systems · doi:10.1007/s10115-016-0944-x · Cited by 153 · cited 5×
“…we resort MMD as the distance measures between x and x to compare different distributions: where is the MMD matrix and is computed as follows [24,26] The marginal distributions between training domain and test domain are brought closer under the new representation V = A T X D by minimizing…”
BackgroundMethodInfluentialImpact-force sparse reconstruction from highly incomplete and inaccurate measurements
Qiao, B., Zhang, X., Gao, J., & Chen, X. (2016) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2016.04.040 · Cited by 110 · cited 1×
“Cracks or spalls on the surfaces of the roller, outer race or inner race are commonly failure modes in bearings [5].”
BackgroundFault detection and diagnosis of rotating machinery
Loparo, K. A., Adams, M. L., Lin, W., Abdel-Magied, M. F., & Afshari, N. (2000) · IEEE Transactions on Industrial Electronics · doi:10.1109/41.873208 · Cited by 104
Al-Bugharbee, H., & Trendafilova, I. N. (2016) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2015.12.052 · Cited by 101 · cited 1×
“The test-bed illustrated in figure 3 consists of a driving motor, a 2 hp motor for loading, a torque sensor/encoder, a power meter, accelerometers and electronic control unit [27, 29].”
HIGHER-ORDER TIME–FREQUENCY ANALYSIS AND ITS APPLICATION TO FAULT DETECTION IN ROTATING MACHINERY
Lee, S. K., & White, P. R. (1997) · Mechanical Systems and Signal Processing · doi:10.1006/mssp.1997.0098 · Cited by 91 · cited 1×
“To further illustrate the influence of extracted transferable features on the results, receiver operating characteristics (ROC) is applied to evaluation [31].”
MethodJoannin, C., Chouvion, B., Thouverez, F., Ousty, J.-P., & Mbaye, M. (2016) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2016.05.044 · Cited by 88 · cited 1×
“Such as, timedomain statistical analysis, frequency-domain analysis [10] and time-frequency”
MethodBearing fault diagnosis based on spectrum images of vibration signals
Li, W., Qiu, M., Zhu, Z., Wu, B., & Zhou, G. (2016) · Measurement Science and Technology · doi:10.1088/0957-0233/27/3/035005 · Cited by 66 · cited 2×
“Subjected to electrosparking, inner-race faults (IF), outer-race faults (OF) and ball fault (BF) of different sizes (0.007in, 0.014in, and 0.021in) are introduced into the drive-end bearing of motor [30].”
BackgroundMethodSelf-citationJacobs, W., Hooreweder, B. V., Boonen, R., Sas, P., & Moens, D. (2015) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2015.04.033 · Cited by 33 · cited 1×
“…components and widely used in rotating machinery, whose health conditions, for example, the fault degree in different places under different motor speeds and loads, may have huge effect on the performance, reliability and residual life of the equipment [1] or even can lead to heavy casualties [2–4].”
BackgroundSinusoidal synthesis based adaptive tracking for rotating machinery fault detection
Li, G., McDonald, G. L., & Zhao, Q. Z. (2016) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2016.06.019 · Cited by 10 · cited 2×
“Such as, time-domain statistical analysis, frequency-domain analysis [10] and time-frequency domain analysis [2].”
Background
Research works printed but not linked: 1
- CsurkaG. Domain adaptation for visual applications: a comprehensive survey CoRR abs/1702.05374 2017. · arXiv
Cited by
Applications of machine learning to machine fault diagnosis: A review and roadmap
Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. K. (2020) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2019.106587 · Cited by 2,997
Li, W., Huang, R., Li, J., Liao, Y., Chen, Z., He, G., Yan, R., & Gryllias, K. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108487 · Cited by 816
Self-citationZhao, Z., Zhang, Q., Yu, X., Sun, C., Wang, S., Yan, R., & Chen, X. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3116309 · Cited by 526
“Tong et al. [86], [87] reduced marginal and conditional distributions simultaneously across domains based on MMD in the feature space by refining pseudo test labels for bearing fault diagnosis.”
BackgroundKnowledge Transfer for Rotary Machine Fault Diagnosis
Yan, R., Shen, F., Sun, C., & Chen, X. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2949057 · Cited by 245
“Tong et al. [162] proposed a domain adaptation using trans-ferable features (DATF), where difference of marginal and conditional distributions was reduced simultaneously across domains based on maximum mean discrepancy (MMD) in feature space by refining pseudo test labels.”
BackgroundMethodFault diagnosis in rotating machines based on transfer learning: Literature review
Misbah, I., LEE, C. K. M., & KEUNG, K. L. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111158 · Cited by 215
Metadata
- Authors
- Tong, Z., Li, W., Zhang, B., & Zhang, M.
- Affiliations
- China University of Mining and Technology (CN)
- Corresponding author
- Zhang, Bo
- Venue
- Shock and Vibration
- Publisher
- Wiley
- Published
- 2018-01
- Volume
- 2018
- Issue
- 1
- ISSN
- 1070-9622 (ISSN-L)
- 1875-9203
- OpenAlex
- W2963532361
- Cited by
- 64
- References
- 31
- Citations by year
- 2026: 6 · 2025: 5 · 2024: 5 · 2023: 6 · 2022: 6 · 2021: 17 · 2020: 12 · 2019: 6
- FWCI
- 5.42
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Shock and Vibration (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (51475455)
- Natural Science Foundation of Jiangsu Province (BK20160276)
- 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 › Mechanical Engineering › Gear and Bearing Dynamics Analysis
- Keywords
- bearing fault diagnosis, domain adaptation, transferable features, variable operating conditions, vibration signals, maximum mean discrepancy, pseudo-label refinement, nearest neighbor classification, rotating machinery
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.