Transfer Learning With Neural Networks for Bearing Fault Diagnosis in Changing Working Conditions
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Traditional machine learning algorithms have made great achievements in data-driven fault diagnosis. However, they assume that all the data must be in the same working condition and have the same distribution and feature space. They are not applicable for real-world working conditions, which often change with time, so the data are hard to obtain. In order to utilize data in different working conditions to improve the performance, this paper presents a transfer learning approach for fault diagnosis with neural networks. First, it learns characteristics from massive source data and adjusts the parameters of neural networks accordingly. Second, the structure of neural networks alters for the change of data distribution. In the same time, some parameters are transferred from source task to target task. Finally, the new model is trained by a small amount of target data in another working condition. The Case Western Reserve University bearing data set is used to validate the performance of the proposed transfer learning approach. Experimental results show that the proposed transfer learning approach can improve the classification accuracy and reduce the training time comparing with the conventional neural network method when there are only a small amount of target data.
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
“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.”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [438]
Citations
Cites
Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., Yen, N.-C., Tung, C. C., & Liu, H. H. (1998) · Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rspa.1998.0193 · Cited by 23,564 · cited 2×
“Lei et al. [28] proposed a mechanical fault diagnosis model based on WPD and EMD.”
MethodPan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 1×
“It has made great progresses in image, audio and text recognition [16]–[18].”
BackgroundWeiss, K., Khoshgoftaar, T. M., & Wang, D. (2016) · Journal of Big Data · doi:10.1186/s40537-016-0043-6 · Cited by 6,260
Robust Model-Based Fault Diagnosis for Dynamic Systems
Chen, J., & Patton, R. J. (1999) · The International Series on Asian Studies in Computer and Information Science · doi:10.1007/978-1-4615-5149-2 · Cited by 4,262 · cited 1×
“These fault diagnosis methods can be divided into model driven methods [1], [2] and data driven methods.”
MethodLearning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150 · cited 1×
“[20] combined convolutional neural networks with transfer learning to learn and transfer mid-level image representations.”
BackgroundGao, Z., Cecati, C., & Ding, S. X. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2015.2417501 · Cited by 3,135 · cited 1×
“These fault diagnosis methods can be divided into model driven methods [1], [2] and data driven methods.”
MethodBoosting for transfer learning
Dai, W., Yang, Q., Xue, G.-R., & Yu, Y. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273521 · Cited by 1,724 · cited 1×
“[22] proposed a transfer learning framework called TrAdaBoost to select most useful and different samples as additional training data to improve the performance.”
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×
“[9] used deep neural networks to recognize faults by training the model with frequency spectra extracted from vibration signals.”
Self-taught learning: transfer learning from unlabeled data
Raina, R., Battle, A., Lee, H., Packer, B., & Ng, A. Y. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273592 · Cited by 1,510 · cited 1×
“[21] designed selftaught learning to learn from unlabeled data and it improves classification accuracies of given image, audio and text classification tasks, respectively.”
BackgroundTransfer Learning for Reinforcement Learning Domains: A Survey
Taylor, M. E., & Stone, P. (2009) · doi:10.5555/1577069.1755839 · Cited by 1,488 · cited 1×
“The aim of transfer is to take advantage of experience learnt in one task and improve the performance in a similar but different task [24].”
BackgroundHierarchical 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 2×
“[11] proposed a model based on adaptive convolutional neural network on the bearing diagnosis.”
BackgroundMethodLu, C., Wang, Z.-Y., Qin, W.-L., & Ma, J. (2017) · Signal Processing · doi:10.1016/j.sigpro.2016.07.028 · Cited by 775 · cited 1×
“[10] investigated the application of stacked denoising autoencoder in health state indentification.”
BackgroundBearing fault detection of induction motor using wavelet and Support Vector Machines (SVMs)
Konar, P., & Chattopadhyay, P. (2011) · Applied Soft Computing · doi:10.1016/j.asoc.2011.03.014 · Cited by 499 · cited 1×
“Machine learning algorithms and classifiers with signal processing methods are commonly used in traditional data driven fault diagnosis models [4]–[6].”
MethodBoosting for transfer learning with multiple sources
Yao, Y., & Doretto, G. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539857 · Cited by 464 · cited 2×
“[23] Y. Yao and G. Doretto, ‘‘Boosting for transfer learning with multiple sources,’’ in Proc.”
BackgroundFault diagnosis in spur gears based on genetic algorithm and random forest
Cerrada, M., Zurita, G., Cabrera, D., Sánchez, R.-V., Artés, M., & Li, C. (2016) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2015.08.030 · Cited by 362 · cited 1×
“[8] proposed a fault diagnosis model based on genetic algorithm and random forest.”
MethodBearing Damage Detection via Wavelet Packet Decomposition of the Stator Current
Eren, L., & Devaney, M. J. (2004) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2004.823323 · Cited by 282 · cited 2×
“Lei et al. [28] proposed a mechanical fault diagnosis model based on WPD and EMD.”
MethodMulti-bearing remaining useful life collaborative prediction: A deep learning approach
Ren, L., Cui, J., Sun, Y., & Cheng, X. (2017) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2017.02.013 · Cited by 280 · cited 1×
“[12] used a deep neural network based model to predict remaining useful life of rolling bearings.”
MethodApplication of mother wavelet functions for automatic gear and bearing fault diagnosis
Rafiee, J., Reif, J., & Tse, P. W. (2010) · Expert Systems with Applications · doi:10.1016/j.eswa.2009.12.051 · Cited by 277
Application of an intelligent classification method to mechanical fault diagnosis
Lei, Y., He, Z., & Zi, Y. (2009) · Expert Systems with Applications · doi:10.1016/j.eswa.2009.01.065 · Cited by 263
Deep neural networks-based rolling bearing fault diagnosis
Chen, Z., Deng, S., Chen, X., Li, C., Sanchez, R.-V., & Qin, H. (2017) · Microelectronics Reliability · doi:10.1016/j.microrel.2017.03.006 · Cited by 254 · cited 1×
“[13] employed three different deep neural network, including Deep Boltzmann Machines, Deep Belief Networks and Stacked Auto-Encoders to identify faults of rolling bearings.”
MethodFault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning
Li, C., Sánchez, R.-V., Zurita, G., Cerrada, M., & Cabrera, D. (2016) · Sensors · doi:10.3390/s16060895 · Cited by 246 · cited 1×
“[14] set up a Gaussian-Bernoulli deep Boltzmann machine to learn statistical features from signals and make diagnosis.”
Vibration model of rolling element bearings in a rotor-bearing system for fault diagnosis
Cong, F., Chen, J., Dong, G., & Pecht, M. (2013) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2012.11.029 · Cited by 193 · cited 1×
“The feature selection of vibration signals is of great importance to the fault diagnosis [3].”
BackgroundTransfer learning for text classification
Shulman, J., & Ng, A. Y. (2005) · neural information processing systems · Cited by 185
Fault Diagnosis from Raw Sensor Data Using Deep Neural Networks Considering Temporal Coherence
Zhang, R., Peng, Z., Wu, L., Yao, B., & Guan, Y. (2017) · Sensors · doi:10.3390/s17030549 · Cited by 132 · cited 1×
“[15] proposed a fault diagnosis model based on deep neural networks to learn directly from time series data without signal preprocessing.”
BackgroundSelf-citationExtreme learning machine based transfer learning for data classification
Li, X., Mao, W., & Jiang, W. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.01.096 · Cited by 70 · cited 1×
“It has made great progresses in image, audio and text recognition [16]–[18].”
BackgroundFault Diagnosis of Roller Bearings Based on a Wavelet Neural Network and Manifold Learning
Wu, L., Yao, B., Peng, Z., & Guan, Y. (2017) · Applied Sciences · doi:10.3390/app7020158 · Cited by 40 · cited 1×
“[7] adopted manifold learning and wavelet neural networks to make diagnosis.”
MethodSelf-citationSignal Based Fault Detection and Diagnosis for Rotating Electrical Machines: Issues and Solutions
Giantomassi, A., Ferracuti, F., Iarlori, S., Ippoliti, G., & Longhi, S. (2014) · Studies in fuzziness and soft computing · doi:10.1007/978-3-319-12883-2_10 · Cited by 21
Research works printed but not linked: 1
- 0, Bearing Data Center Seeded Fault Test Data
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
Guo, L., Lei, Y., Xing, S., Yan, T., & Li, N. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2877090 · Cited by 1,234
“As a matter of fact, it is demonstrated in [8]–[10] that the success of intelligent fault diagnosis of machines relies on those two conditions.”
BackgroundDeep Learning Algorithms for Bearing Fault Diagnostics—A Comprehensive Review
Zhang, S., Zhang, S., Wang, B., & Habetler, T. G. (2020) · IEEE Access · doi:10.1109/access.2020.2972859 · Cited by 913
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
Zhao, 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
“2) Applications to IFD: Pre-trained deep neural networks using the source data were used in [26]–[37] via frozing their partial parameters, and then part of network parameters were transferred to the target network and other parameters were fine-tuned with a small amount of target data.”
Method
Metadata
- Authors
- Zhang, R., Tao, H., Wu, L., & Guan, Y.
- Affiliations
- Capital Normal University (CN)
- Venue
- IEEE Access
- Published
- 2017
- Volume
- 5
- Pages
- 14347-14357
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2731372149
- Cited by
- 378
- References
- 27
- Citations by year
- 2026: 23 · 2025: 29 · 2024: 37 · 2023: 48 · 2022: 62 · 2021: 62 · 2020: 58 · 2019: 44 · 2018: 14 · 2017: 1
- FWCI
- 20.10
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61202027)
- Beijing Natural Science Foundation of China (4122015)
- Project of Construction of Innovative Teams and Teacher Career Development for Universities and Colleges under Beijing Municipality (IDHT20150507)
- 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 › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- transfer learning, bearing fault diagnosis, artificial neural networks, changing working conditions, domain adaptation, distribution shift, vibration signal classification
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.