An End-to-End Model Based on Improved Adaptive Deep Belief Network and Its Application to Bearing Fault Diagnosis
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Effective machinery prognostics and health management play a crucial role in ensuring the safe and continuous operation of equipment, and satisfactory characteristics' expression of machine health status plays a key role in the ability to diagnose faults with high accuracy. At present, most methods based on signal processing and the shallow learning model rely on artificial feature extraction to identify the machine fault type. In practical applications, however, meaningful health management requires correct recognition of not only the health type but also the fault degree, if any occurs. Such recognition is useful for determining the priority level of mechanical maintenance and minimizing economic losses. Deep learning techniques, such as deep belief network (DBN), have demonstrated great potential in exploring characteristic information from machine status signals. In this paper, an end-to-end fault diagnosis model based on an adaptive DBN optimized by the Nesterov moment (NM) is proposed to extract deep representative features from rotating machinery and recognize bearing fault types and degrees simultaneously. Frequency-domain signals are inputted into the model for feature learning, and NM is introduced to the training process of the DBN model. Individual adaptive learning rate algorithms are then applied to optimize parameter updating. The performance of the proposed method is validated using a self-made bearing fault test platform, and the model is shown to achieve satisfactory convergence and a testing accuracy higher than those obtained from standard DBN and support vector machine.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 1×
“[24] proposed DBN, which is a stack of several RBMs.”
BackgroundDermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362 · cited 2×
“Some typical deep-learning networks include stacked auto-encoder [14], convolutional neural network (CNN) [15], and deep belief network (DBN) [16].”
BackgroundCaffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077 · cited 1×
“These methods have been successfully applied to speech recognition [17], natural language processing [18], and computer vision [19].”
MethodDeep learning and its applications to machine health monitoring
Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., & Gao, R. X. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.05.050 · Cited by 2,894 · cited 1×
“As a breakthrough in neural networks, deep learning [13] combines multiple nonlinear learning layers to simulate the multi-layer abstract learning mechanism of the human brain; this approach thus possesses the capacity to process raw data in different domains and avoids the complexity and uncertainty often observed in…”
BackgroundJia, F., Lei, Y., Lin, J., Zhou, X., & Lu, N. (2016) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2015.10.025 · Cited by 1,710 · cited 1×
“[23] utilized a DNN based on auto-encoders for bearing fault diagnosis.”
MethodAsk Me Anything: Dynamic Memory Networks for Natural Language Processing
Kumar, A., Irsoy, O., Ondruska, P., Iyyer, M., Bradbury, J., Gulrajani, I., Zhong, V., Paulus, R., & Socher, R. (2015) · arXiv · doi:10.48550/arxiv.1506.07285 · Cited by 1,020 · cited 1×
“These methods have been successfully applied to speech recognition [17], natural language processing [18], and computer vision [19].”
MethodHierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis
Guo, X., Chen, L., & Shen, C. (2016) · Measurement · doi:10.1016/j.measurement.2016.07.054 · Cited by 782 · cited 1×
“[21] proposed a two-layer hierarchical diagnosis network based on a CNN to classify bearing fault types and diagnose fault sizes.”
BackgroundSelf-citationYuan, X., Huang, B., Wang, Y., Yang, C., & Gui, W. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2809730 · Cited by 635 · cited 1×
“Some typical deep-learning networks include stacked auto-encoder [14], convolutional neural network (CNN) [15], and deep belief network (DBN) [16].”
BackgroundGan, M., Wang, C., & Zhu, C. (2016) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2015.11.014 · Cited by 550 · cited 1×
“[22] employed a two-layer hierarchical network based on DBN to diagnose bearing faults, and Jia et al.”
MethodPrognostics and Health Management: A Review of Vibration Based Bearing and Gear Health Indicators
Wang, D., Tsui, K.-L., & Miao, Q. (2018) · IEEE Access · doi:10.1109/access.2017.2774261 · Cited by 455 · cited 1×
“[6] proposed a new multi-speed fault diagnostic approach by using self-adaptive wavelet transform components generated from bearing vibration signals to identify four health states of rolling bearings.”
BackgroundTran, V. T., AlThobiani, F., & Ball, A. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.12.026 · Cited by 386 · cited 1×
“[20], for example, successfully used DBN to identify defects in the valves of a reciprocating compressor.”
MethodNgo, T. A., Lu, Z., & Carneiro, G. (2017) · Medical Image Analysis · doi:10.1016/j.media.2016.05.009 · Cited by 332 · cited 1×
“Some typical deep-learning networks include stacked auto-encoder [14], convolutional neural network (CNN) [15], and deep belief network (DBN) [16].”
BackgroundThe structure healthy condition monitoring and fault diagnosis methods in wind turbines: A review
Liu, W. Y., Tang, B. P., Han, J. G., Lu, X. N., Hu, N. N., & He, Z. Z. (2015) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2014.12.005 · Cited by 300 · cited 1×
“After pre-training of the Softmax classifier, the tagged data are used to begin input from the bottom layer, and BP [29] is used for global fine-tuning.”
MethodWang, Y., Xu, G., Liang, L., & Jiang, K. (2015) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2014.09.002 · Cited by 231 · cited 1×
“Numerous researchers have proposed various bearing fault diagnosis methods from the signal-processing aspect, such as empirical mode decomposition [3], wavelet packet transform [4], and morphological filter [5].”
BackgroundCui, L., Huang, J., & Zhang, F. (2017) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2698359 · Cited by 223 · cited 1×
“[8] used a search algorithm to extract the morphological characteristics of signals of different gear fault types to recognize the damage pattern of gear signals.”
MethodBearing Fault Model for Induction Motor With Externally Induced Vibration
Immovilli, F., Bianchini, C., Cocconcelli, M., Bellini, A., & Rubini, R. (2013) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2012.2213566 · Cited by 181 · cited 1×
“Depending on the type and size of the machine, bearing issues account for approximately 40% (large machines) to 90% (small machines) of all machine faults [1].”
BackgroundImaouchen, Y., Kedadouche, M., Alkama, R., & Thomas, M. (2016) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2016.05.009 · Cited by 145 · cited 1×
“Numerous researchers have proposed various bearing fault diagnosis methods from the signal-processing aspect, such as empirical mode decomposition [3], wavelet packet transform [4], and morphological filter [5].”
BackgroundZhao, Z., Xu, Q., & Jia, M. (2015) · Neural Computing and Applications · doi:10.1007/s00521-015-1850-y · Cited by 119 · cited 1×
“Fine-tuning is applied to improve the performance of the DBN model by utilizing the back-propagating (BP) algorithm [28].”
MethodLi, Y., Liang, X., & Zuo, M. J. (2016) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2016.08.019 · Cited by 95 · cited 1×
“Numerous researchers have proposed various bearing fault diagnosis methods from the signal-processing aspect, such as empirical mode decomposition [3], wavelet packet transform [4], and morphological filter [5].”
BackgroundCui, L., Gong, X., Zhang, J., & Wang, H. (2016) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2016.09.008 · Cited by 93 · cited 1×
“A novel doubledictionary matching pursuit for fault extent evaluation of rolling bearings based on the Lempel–Ziv complexity index has been proposed to achieve satisfactory quantitative rolling bearing fault diagnosis [10].”
BackgroundAn extension of the Blade Element Momentum method applied to Diffuser Augmented Wind Turbines
Vaz, D. A. T. D. D. R., Mesquita, A. L. A., Vaz, J. R. P., Blanco, C. J. C., & Pinho, J. T. (2014) · Energy Conversion and Management · doi:10.1016/j.enconman.2014.03.064 · Cited by 85 · cited 1×
“The momentum method [25] can effectively speed up the gradient descent of SGD through the gully and suppress oscillations.”
MethodCui, L., Huang, J., Zhai, H., & Zhang, F. (2016) · Mechanism and Machine Theory · doi:10.1016/j.mechmachtheory.2016.07.022 · Cited by 56 · cited 1×
“Therefore, to improve the reliability and ensure the safe operation of these machines, effectively diagnosing bearings is essential [2]; such diagnosis can also help reduce operating and maintenance costs.”
BackgroundIncoherent beam combining based on the momentum SPGD algorithm
Yang, G., Liu, L., Jiang, Z., Guo, J. B., & Wang, T. (2017) · Optics & Laser Technology · doi:10.1016/j.optlastec.2017.11.039 · Cited by 37 · cited 1×
“NM [26] can effectively solve this problem by calculating the gradient of J (θ − γ vt−1) to predict the position of the next drop of the parameter and decelerating before the parameter reaches the optimal point to avoid missing it.”
BackgroundKhoualdia, T., Aoul, E. H., Bouacha, K., & Abdeslam, D. O. (2016) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-016-9278-9 · Cited by 29 · cited 1×
“Several intelligent fault diagnosis methods, such as support vector machine (SVM) [11] and artificial neural network [12], have recently been proposed.”
MethodHarmonic W avelet Envelope Method Applied in Railway Bearing Fault Diagnosis
Yao, D., Jia, L., Li, M., Qin, Y. F., Peng, W. C., Liu, G., Guangzhou Metro . Guangzhou, 5., Pang, S., & Guangzhou Metro . Guangzhou, 5. (2013) · Journal of Engineering Science and Technology Review · doi:10.25103/jestr.062.06 · Cited by 5
Zhang, B., Xu, R., Yin, X., & Gao, Z. W. (2016) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2016.7531494 · Cited by 4 · cited 5×
“Verification using a self-made bearing fault testing platform indicated that the proposed method demonstrates excellent recognition performance on the defective bearing dataset and achieves higher accuracy than standard DBN and SVM. ACKNOWLEDGMENT This work was supported by the National Natural Science Foundation of C…”
MethodInfluentialFault Diagnosis in Printing Press Roller Bearing Based on Spectrum Kurtosis and Improved EEMD
Zhang, J., Wu, J., Wang, Y., Li, K., Ma, L., & Zhao, F. (2018) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-7629-9_67 · Cited by 1 · cited 1×
“[7] proposed a combination of the improved ensemble empirical mode decomposition (EEMD) and spectral kurtosis methods to address the problem of poor rolling bearing signals under the high background”
Background
Research works printed but not linked: 1
- tieleman, 2017, Rmsprop Divide the gradient by a running average of its recent magnitude
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
A review of the application of deep learning in intelligent fault diagnosis of rotating machinery
Zhu, Z., Lei, Y., Qi, G., Chai, Y., Mazur, N., An, Y., & Huang, X. (2023) · Measurement · doi:10.1016/j.measurement.2022.112346 · Cited by 731
Self-citationMulti-scale deep intra-class transfer learning for bearing fault diagnosis
Wang, X., Shen, C., Xia, M., Wang, D., Zhu, J., & Zhu, Z. (2020) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2020.107050 · Cited by 313
“An end-to-end fault diagnosis method embedded with an adaptive deep belief network (DBN) using the Nesterov moment optimization was designed by Xie et al. [18] to distinguish the states of signals collected from their self-made test platform e ff ectively.”
MethodSelf-citationHakim, M., Omran, A. A. B., Ahmed, A. N., Al-Waily, M., & Abdellatif, A. (2023) · Ain Shams Engineering Journal · doi:10.1016/j.asej.2022.101945 · Cited by 305
Saufi, S. R., Ahmad, Z. A. B., Leong, M. S., & Lim, M. H. (2019) · IEEE Access · doi:10.1109/access.2019.2938227 · Cited by 312
“between 98% and 100% for every bearing condition [153].”
Background
Metadata
- Authors
- Xie, J., Du, G., Shen, C., Chen, N., Chen, L., & Zhu, Z.
- Affiliations
- Soochow University (CN)
- National University of Singapore (SG)
- Venue
- IEEE Access
- Published
- 2018
- Volume
- 6
- Pages
- 63584-63596
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2898125729
- Cited by
- 78
- References
- 28
- Citations by year
- 2026: 3 · 2025: 7 · 2024: 6 · 2023: 15 · 2022: 10 · 2021: 12 · 2020: 10 · 2019: 15
- FWCI
- 5.73
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion)
- National University of Singapore (submittedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (51875375, 51505311)
- Suzhou Prospective Research Program (SYG201802)
- Natural Science Foundation of Jiangsu Province (BK 20150339)
- 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, deep belief network, adaptive learning rate, rotating machinery, frequency-domain signals, representation learning
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.