Dynamic Distribution Adaptation Based Transfer Network for Cross Domain Bearing Fault Diagnosis

Yixiao Liao; Ruyi Huang; Jipu Li; Zhuyun Chen; Weihua Li

doi:10.1186/s10033-021-00566-3

摘要

In machinery fault diagnosis, labeled data are always difficult or even impossible to obtain. Transfer learning can leverage related fault diagnosis knowledge from fully labeled source domain to enhance the fault diagnosis performance in sparsely labeled or unlabeled target domain, which has been widely used for cross domain fault diagnosis. However, existing methods focus on either marginal distribution adaptation (MDA) or conditional distribution adaptation (CDA). In practice, marginal and conditional distributions discrepancies both have significant but different influences on the domain divergence. In this paper, a dynamic distribution adaptation based transfer network (DDATN) is proposed for cross domain bearing fault diagnosis. DDATN utilizes the proposed instance-weighted dynamic maximum mean discrepancy (IDMMD) for dynamic distribution adaptation (DDA), which can dynamically estimate the influences of marginal and conditional distribution and adapt target domain with source domain. The experimental evaluation on cross domain bearing fault diagnosis demonstrates that DDATN can outperformance the state-of-the-art cross domain fault diagnosis methods.

关键词： Cross domain fault diagnosis; Dynamic distribution adaptation; Instance-weighted dynamic MMD; Transfer learning

本文引用格式

Yixiao Liao , Ruyi Huang , Jipu Li , Zhuyun Chen , Weihua Li . Dynamic Distribution Adaptation Based Transfer Network for Cross Domain Bearing Fault Diagnosis[J]. Chinese Journal of Mechanical Engineering, 2021 , 34(3) : 52 -52 . DOI: 10.1186/s10033-021-00566-3

Abstract

In machinery fault diagnosis, labeled data are always difficult or even impossible to obtain. Transfer learning can leverage related fault diagnosis knowledge from fully labeled source domain to enhance the fault diagnosis performance in sparsely labeled or unlabeled target domain, which has been widely used for cross domain fault diagnosis. However, existing methods focus on either marginal distribution adaptation (MDA) or conditional distribution adaptation (CDA). In practice, marginal and conditional distributions discrepancies both have significant but different influences on the domain divergence. In this paper, a dynamic distribution adaptation based transfer network (DDATN) is proposed for cross domain bearing fault diagnosis. DDATN utilizes the proposed instance-weighted dynamic maximum mean discrepancy (IDMMD) for dynamic distribution adaptation (DDA), which can dynamically estimate the influences of marginal and conditional distribution and adapt target domain with source domain. The experimental evaluation on cross domain bearing fault diagnosis demonstrates that DDATN can outperformance the state-of-the-art cross domain fault diagnosis methods.

Key words： Cross domain fault diagnosis; Dynamic distribution adaptation; Instance-weighted dynamic MMD; Transfer learning

参考文献

[1] R N Liu, B Y Yang, E Zio, et al. Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 2018, 108: 33-47.
[2] Z Z Pan, Z Meng, Z J Chen, et al. A two-stage method based on extreme learning machine for predicting the remaining useful life of rolling-element bearings. Mechanical Systems and Signal Processing, 2020, 144: 106899.
[3] L L Cui, X Wang, H Q Wang, et al. Remaining useful life prediction of rolling element bearings based on simulated performance degradation dictionary. Mechanism and Machine Theory, 2020, 153: 103967.
[4] D Z Zhao, J Y Li, W D Cheng, et al. Generalized demodulation transform for bearing fault diagnosis under nonstationary conditions and gear noise interferences. Chinese Journal of Mechanical Engineering, 2019, 32: 7.
[5] Y T Hu, S Q Zhang, A Q Jiang, et al. A new method of wind turbine bearing fault diagnosis based on multi-masking empirical mode decomposition and fuzzy c-means clustering. Chinese Journal of Mechanical Engineering, 2019, 32: 46.
[6] G Q Jiang, P Xie, X Wang, et al. Intelligent fault diagnosis of rotary machinery based on unsupervised multiscale representation learning. Chinese Journal of Mechanical Engineering, 2017, 30(6): 1314-1324.
[7] F B Zhang, J F Huang, F L Chu, et al. Mechanism and method for the full-scale quantitative diagnosis of ball bearings with an inner race fault. Journal of Sound and Vibration, 2020, 488: 115641.
[8] J P Li, R Y Huang, G L He, et al. A deep adversarial transfer learning network for machinery emerging fault detection. IEEE Sensors Journal, 2020, 20(15): 8413-8422.
[9] S Y Shao, W J Sun, R Q Yan, et al. A deep learning approach for fault diagnosis of induction motors in manufacturing. Chinese Journal of Mechanical Engineering, 2017, 30(6): 1347-1356.
[10] H Q Wang, S Li, L Y Song, et al. An enhanced intelligent diagnosis method based on multi-sensor image fusion via improved deep learning network. IEEE Transactions on Instrumentation and Measurement, 2019, 69(6): 2648-2657.
[11] R Y Huang, J P Li, S H Wang, et al. A robust weight-shared capsule network for intelligent machinery fault diagnosis. IEEE Transactions on Industrial Informatics, 2020, 16(10): 6466-6475.
[12] Z Y Chen, K Gryllias, W H Li. Mechanical fault diagnosis using convolutional neural networks and extreme learning machine. Mechanical Systems and Signal Processing, 2019, 133: 106272.
[13] J P Li, R Y Huang, G L He, et al. A two-stage transfer adversarial network for intelligent fault diagnosis of rotating machinery with multiple new faults. IEEE/ASME Transactions on Mechatronics, 2020, doi: https://doi.org/10.1109/TMECH.2020.3025615.
[14] S J Pan, Q Yang. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2009, 22(10): 1345-1359.
[15] R Zhao, R Q Yan, Z H Chen, et al. Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 2019, 115: 213-237.
[16] R Q Yan, F Shen, C Sun, et al. Knowledge transfer for rotary machine fault diagnosis. IEEE Sensors Journal, 2019, 20(15): 8374-8393.
[17] T Han, C Liu, W G Yang, et al. A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults. Knowledge-Based Systems, 2019, 165: 474-487.
[18] L Guo, Y G Lei, S B Xing, et al. Deep convolutional transfer learning network: A new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Transactions on Industrial Electronics, 2018, 66(9): 7316-7325.
[19] B Yang, Y G Lei, F Jia, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mechanical Systems and Signal Processing, 2019, 122: 692-706.
[20] X Wang, C Q Shen, M Xia, et al. Multi-scale deep intra-class transfer learning for bearing fault diagnosis. Reliability Engineering & System Safety, 2020, 202: 107050.
[21] X Li, X D Jia, W Zhang, et al. Intelligent cross-machine fault diagnosis approach with deep auto-encoder and domain adaptation. Neurocomputing, 2020, 383: 235-247.
[22] J D Wang, Y Q Chen, W J Feng, et al. Transfer learning with dynamic distribution adaptation. ACM Transactions on Intelligent Systems and Technology, 2020, 11(1): 1-25.
[23] T Han, C Liu, W G Yang, et al. Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application. ISA Transactions, 2020, 97: 269-281.
[24] M Li, Z H Sun, W H He, et al. Rolling bearing fault diagnosis under variable working conditions based on joint distribution adaptation and SVM. 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, Jul. 19-24, 2020: 1-8.
[25] A Gretton, K M Borgwardt, M J Rasch, et al. A kernel two-sample test. The Journal of Machine Learning Research, 2012, 13(1): 723-773.
[26] X S Lou, K A Loparo. Bearing fault diagnosis based on wavelet transform and fuzzy inference. Mechanical Systems and Signal Processing, 2004, 18(5): 1077-1095.
[27] E Tzeng, J Hoffman, N Zhang, et al. Deep domain confusion: Maximizing for domain invariance. arXiv preprint, http://arxiv.org/abs/1412.3474;2014.
[28] L Maaten, G E Hinton. Visualizing data using t-SNE. Journal of Machine Learning Research, 2008, 9: 2579-2605.

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献