Fault Diagnosis for Rolling Bearings of a Freight Train under Limited Fault Data: Few-Shot Learning Method
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 147, Issue 8
Abstract
In recent years, many machine learning-based methods have emerged to detect faulty bearings. However, most of these methods may not be practical due to the need to collect a large number of fault samples for training. This paper developed a novel few-shot learning framework for the fault diagnosis of freight train rolling bearings. The proposed method has the capability to transfer the learning outcome from one bearing fault diagnosis model to another different but related task for which very limited training data are available. The authors established a single-wheelset platform to collect acceleration signals of different types of bearing faults. The authors preprocessed the data through data segmentation and frequency domain transformation, and divided the data into training and test sets according to a certain ratio. A one-dimensional convolutional neural network (1D-CNN) was established to automatically extract the features of the bearing vibration signals and classify the fault types. The authors implemented two few-shot learning methods through parameter fine-tuning and a conditional Wasserstein generative adversarial network (C-WGAN). A case study demonstrated the classification performance of the proposed models. The results showed that the diagnosis capability of the 1D-CNN in the frequency domain is significantly superior to that in the time domain. However, when the amount of data is small, the 1D-CNN model does not work. In contrast, the few-shot learning of bearing faults works well for both the fine-tuned CNN and C-WGAN models. Furthermore, the classification performance of the C-WGAN is better than that of the fine-tuned CNN when the training data are extremely limited.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are proprietary or confidential in nature and may be provided only with restrictions. The rolling-bearing data are owned by the China Railway Rolling Stock Corporation Academy. They are proprietary and require permission for distribution. The models and code developed in this paper are available from the corresponding author upon reasonable request.
Acknowledgments
This study was funded by the National Natural Science Foundation of China (NSFC) under Grant Nos. 51878576 and U1934214, and Sichuan Science and Technology Project No. 2020YFG0049. The authors express their sincere thanks for the support from the NSFC.
References
Ali, J. B., B. Chebel-Morello, L. Saidi, S. Malinowski, and F. Fnaiech. 2015. “Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network.” Mech. Syst. Signal Process. 56–57 (May): 150–172. https://doi.org/10.1016/j.ymssp.2014.10.014.
Amar, M., I. Gondal, and C. Wilson. 2015. “Vibration spectrum imaging: A novel bearing fault classification approach.” IEEE Trans. Ind. Electron. 62 (1): 494–502. https://doi.org/10.1109/TIE.2014.2327555.
Arjovsky, M., S. Chintala, and L. Bottou. 2017. “Wasserstein GAN.” Preprint, submitted January 26, 2017. http://arxiv.org/abs/1701.07875.
Cabrera, D., F. Sancho, J. Long, R.-V. Sánchez, S. Zhang, M. Cerrada, and C. Li. 2019. “Generative adversarial networks selection approach for extremely imbalanced fault diagnosis of reciprocating machinery.” IEEE Access 7 (May): 70643–70653. https://doi.org/10.1109/ACCESS.2019.2917604.
Cuanang, J., C. Tarawneh, M. Amaro Jr., J. Lima, and H. Foltz. 2020. “Optimization of railroad bearing health monitoring system for wireless utilization.” In Proc., ASME/IEEE Joint Rail Conf. New York: ASME.
De Los Santos, N., R. Jones, C. M. Tarawneh, A. Fuentes, and A. Villarreal. 2017. “Development of prognostic techniques for surface defect growth in railroad bearing rolling elements.” In Proc., 2017 Joint Rail Conf. New York: ASME.
Feng, Z., M. Liang, and F. Chu. 2013. “Recent advances in time–frequency analysis methods for machinery fault diagnosis: A review with application examples.” Mech. Syst. Signal Process. 38 (1): 165–205. https://doi.org/10.1016/j.ymssp.2013.01.017.
Frid-Adar, M., I. Diamant, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan. 2018. “GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification.” Neurocomputing 321 (Dec): 321–331. https://doi.org/10.1016/j.neucom.2018.09.013.
Gao, Z., C. Cecati, and S. X. Ding. 2015. “A survey of fault diagnosis and fault-tolerant techniques—Part I: Fault diagnosis with model-based and signal-based approaches.” IEEE Trans. Ind. Electron. 62 (6): 3757–3767. https://doi.org/10.1109/TIE.2015.2417501.
Goodfellow, I., J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. 2014. “Generative adversarial nets.” In Advances in neural information processing systems, 2672–2680. Cambridge, MA: MIT Press.
Gulrajani, I., F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville. 2017. “Improved training of Wasserstein GANs.” In Advances in neural information processing systems, 5767–5777. Cambridge, MA: MIT Press.
Hoang, D.-T., and H.-J. Kang. 2019. “A survey on Deep Learning based bearing fault diagnosis.” Neurocomputing 335 (Mar): 327–335. https://doi.org/10.1016/j.neucom.2018.06.078.
Kalogeiton, V., V. Ferrari, and C. Schmid. 2016. “Analysing domain shift factors between videos and images for object detection.” IEEE Trans. Pattern Anal. Mach. Intell. 38 (11): 2327–2334. https://doi.org/10.1109/TPAMI.2016.2551239.
Kankar, P. K., S. C. Sharma, and S. P. Harsha. 2011. “Fault diagnosis of ball bearings using machine learning methods.” Expert Syst. Appl. 38 (3): 1876–1886. https://doi.org/10.1016/j.eswa.2010.07.119.
Koch, G., R. Zemel, and R. Salakhutdinov. 2015. “Siamese neural networks for one-shot image recognition.” In Vol. 2 of Proc., ICML Deep Learning Workshop. Berlin: Federal Ministry of Education and Research.
LeCun, Y., Y. Bengio, and G. Hinton. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Li, C., R.-V. Sanchez, G. Zurita, M. Cerrada, D. Cabrera, and R. E. Vásquez. 2016. “Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals.” Mech. Syst. Signal Process. 76–77 (Aug): 283–293. https://doi.org/10.1016/j.ymssp.2016.02.007.
Li, W., Z. Zhu, F. Jiang, G. Zhou, and G. Chen. 2015. “Fault diagnosis of rotating machinery with a novel statistical feature extraction and evaluation method.” Mech. Syst. Signal Process. 50–51 (Jan): 414–426. https://doi.org/10.1016/j.ymssp.2014.05.034.
Liu, H., L. Li, and J. Ma. 2016a. “Rolling bearing fault diagnosis based on STFT-deep learning and sound signals.” Shock Vib. 2016: 12. https://doi.org/10.1155/2016/6127479.
Liu, R., G. Meng, B. Yang, C. Sun, and X. Chen. 2016b. “Dislocated time series convolutional neural architecture: An intelligent fault diagnosis approach for electric machine.” IEEE Trans. Ind. Inf. 13 (3): 1310–1320. https://doi.org/10.1109/TII.2016.2645238.
Liu, X., M. R. Saat, and C. P. L. Barkan. 2012. “Analysis of causes of major train derailment and their effect on accident rates.” Transp. Res. Rec. 2289 (1): 154–163. https://doi.org/10.3141/2289-20.
Lu, W., B. Liang, Y. Cheng, D. Meng, J. Yang, and T. Zhang. 2016. “Deep model based domain adaptation for fault diagnosis.” IEEE Trans. Ind. Electron. 64 (3): 2296–2305. https://doi.org/10.1109/TIE.2016.2627020.
Ming, A. B., W. Zhang, Z. Y. Qin, and F. L. Chu. 2015. “Envelope calculation of the multi-component signal and its application to the deterministic component cancellation in bearing fault diagnosis.” Mech. Syst. Signal Process. 50–51 (Jan): 70–100. https://doi.org/10.1016/j.ymssp.2014.05.033.
Montalvo, J., C. Tarawneh, and A. A. Fuentes. 2018. “Vibration-based defect detection for freight railcar tapered-roller bearings.” In Proc., 2018 Joint Rail Conf. New York: ASME.
Pan, H., X. He, S. Tang, and F. Meng. 2018. “An improved bearing fault diagnosis method using one-dimensional CNN and LSTM.” J. Mech. Eng 64 (7–8): 443–452. https://doi.org/10.5545/sv-jme.2018.5249.
Peng, D., Z. Liu, H. Wang, Y. Qin, and L. Jia. 2018. “A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains.” IEEE Access 7 (Dec): 10278–10293. https://doi.org/10.1109/ACCESS.2018.2888842.
Qiao, S., C. Liu, W. Shen, and A. L. Yuille. 2018. “Few-shot image recognition by predicting parameters from activations.” In Proc., of the IEEE Conf. on Computer Vision and Pattern Recognition, 7229–7238. New York: IEEE.
Ren, Z., Y. Zhu, K. Yan, K. Chen, W. Kang, Y. Yue, and D. Gao. 2020. “A novel model with the ability of few-shot learning and quick updating for intelligent fault diagnosis.” Mech. Syst. Signal Process. 138 (Apr): 106608. https://doi.org/10.1016/j.ymssp.2019.106608.
Shao, H., H. Jiang, Y. Lin, and X. Li. 2018. “A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders.” Mech. Syst. Signal Process. 102 (Mar): 278–297. https://doi.org/10.1016/j.ymssp.2017.09.026.
Shen, C., D. Wang, F. Kong, and P. W. Tse. 2013. “Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classifier.” Measurement 46 (4): 1551–1564. https://doi.org/10.1016/j.measurement.2012.12.011.
Tarawneh, C., J. Ley, D. Blackwell, S. Crown, and B. M. Wilson. 2017. “Onboard load sensor for use in freight railcar applications.” Int. J. Railway Technol. 6 (1): 41–67. https://doi.org/10.4203/ijrt.6.1.3.
Tarawneh, C., J. D. Lima, N. De Los Santos, and R. E. Jones. 2019. “Prognostics models for railroad tapered roller bearings with spall defects on inner or outer rings.” Tribol. Trans. 62 (5): 897–906. https://doi.org/10.1080/10402004.2019.1634228.
Tian, J., C. Morillo, M. H. Azarian, and M. Pecht. 2016. “Motor bearing fault detection using spectral kurtosis-based feature extraction coupled with K-nearest neighbor distance analysis.” IEEE Trans. Ind. Electron. 63 (3): 1793–1803. https://doi.org/10.1109/TIE.2015.2509913.
Vakharia, V., V. K. Gupta, and P. K. Kankar. 2015. “Ball bearing fault diagnosis using supervised and unsupervised machine learning methods.” Int. J. Acoust. Vibr. 20 (4): 244–250.
Weiss, K., T. M. Khoshgoftaar, and D. Wang. 2016. “A survey of transfer learning.” J. Big Data 3 (1): 1–40. https://doi.org/10.1186/s40537-016-0043-6.
Wen, L., L. Gao, and X. Li. 2017. “A new deep transfer learning based on sparse auto-encoder for fault diagnosis.” IEEE Trans. Syst. Man Cybern.: Syst. 49 (1): 136–144. https://doi.org/10.1109/TSMC.2017.2754287.
Xian, Y., T. Lorenz, B. Schiele, and Z. Akata. 2018. “Feature generating networks for zero-shot learning.” In Proc., of the IEEE Conf. on Computer Vision and Pattern Recognition, 5542–5551. New York: IEEE.
Yang, Y., D. Yu, and J. Cheng. 2007. “A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM.” Measurement 40 (9–10): 943–950. https://doi.org/10.1016/j.measurement.2006.10.010.
Yin, J., W. Wang, Z. Man, and S. Khoo. 2014. “Statistical modeling of gear vibration signals and its application to detecting and diagnosing gear faults.” Inf. Sci. 259 (Feb): 295–303. https://doi.org/10.1016/j.ins.2013.03.029.
Yu, Y., Y. Dejie, and C. Junsheng. 2006. “A roller bearing fault diagnosis method based on EMD energy entropy and ANN.” J. Sound Vib. 294 (1–2): 269–277. https://doi.org/10.1016/j.jsv.2005.11.002.
Zhang, A., S. Li, Y. Cui, W. Yang, R. Dong, and J. Hu. 2019. “Limited data rolling bearing fault diagnosis with few-shot learning.” IEEE Access 7 (Aug): 110895–110904. https://doi.org/10.1109/ACCESS.2019.2934233.
Zhang, R., T. Che, Z. Ghahramani, Y. Bengio, and Y. Song. 2018a. “MetaGAN: An adversarial approach to few-shot learning.” In Advances in neural information processing systems, 2365–2374. Cambridge, MA: MIT Press.
Zhang, W., C. Li, G. Peng, Y. Chen, and Z. Zhang. 2018b. “A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load.” Mech. Syst. Signal Process. 100 (Feb): 439–453. https://doi.org/10.1016/j.ymssp.2017.06.022.
Zhang, W., F. Zhang, W. Chen, Y. Jiang, and D. Song. 2018c. “Fault state recognition of rolling bearing based fully convolutional network.” Comput. Sci. Eng. 21 (5): 55–63. https://doi.org/10.1109/MCSE.2018.110113254.
Zhao, R., D. Wang, R. Yan, K. Mao, F. Shen, and J. Wang. 2017. “Machine health monitoring using local feature-based gated recurrent unit networks.” IEEE Trans. Ind. Electron. 65 (2): 1539–1548. https://doi.org/10.1109/TIE.2017.2733438.
Information & Authors
Information
Published In
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Oct 21, 2020
Accepted: Mar 18, 2021
Published online: Jun 2, 2021
Published in print: Aug 1, 2021
Discussion open until: Nov 2, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.