基于DCGAN和DANN网络的滚动轴承跨域故障诊断

PDF(1697 KB)

振动与冲击 ›› 2022, Vol. 41 ›› Issue (6) : 21-29.

论文

胡若晖1，张敏1,2，许文鑫1

作者信息 +

Cross-domain fault diagnosis of rolling element bearings using DCGAN and DANN

HU Ruohui1，ZHANG Min1,2，XU Wenxin1

Author information +

文章历史 +

摘要

实现滚动轴承智能故障诊断需要大量标签数据，但实际中机械设备因轴承故障无法提前收集充足振动信号，导致滚动轴承故障模式难以判断。为解决该问题，提出一种有效利用少量样本数据实现领域自适应的迁移学习模型。首先，通过深度生成式对抗网络（deep convolutional generative adversarial networks，DCGAN）实现少量振动信号的模拟式扩充，生成信号保留了真实信号完整的高频和低频特征；其次，通过对抗领域自适应网络（domain-adversarial neural networks，DANN）将源域与目标域特征投射到同一特征空间，实现多领域特征提取与适配；最后，通过智能诊断网络完成变工况下未知标签滚动轴承健康状态的识别。实验结果表明，所提方法在可用样本较少时能准确有效实现滚动轴承跨域故障诊断，准确率均优于其他迁移学习对比模型。

Abstract

A large amount of label data is needed to realize intelligent fault diagnosis of rolling element bearings. However, in practice, sufficient vibration signals cannot be collected in advance due to bearing faults, which makes it difficult to determine the bearing fault mode under variable conditions. To solve this problem, a domain adaptive transfer learning model using a small amount of sample data is proposed. Firstly, a small amount of vibration signals are extended by the Deep Convolutional Generative Adversarial Networks. The generated signals retain the complete high and low frequency characteristics of the real signals. Secondly, the features of source domain and target domain are projected into the same feature space through the Domain-Adversarial Neural Networks to achieve multi-domain feature extraction and adaptation. Finally, the health status of unknown label rolling bearing is identified by transfer learning network. The experimental results show that the proposed method can accurately and effectively realize the cross-domain fault diagnosis of rolling bearings when the available samples are relatively small. The accuracy is better than other transfer learning comparison models.

导出引用

胡若晖1，张敏1,2，许文鑫1. 基于DCGAN和DANN网络的滚动轴承跨域故障诊断[J]. 振动与冲击, 2022, 41(6): 21-29

HU Ruohui1，ZHANG Min1,2，XU Wenxin1. Cross-domain fault diagnosis of rolling element bearings using DCGAN and DANN[J]. Journal of Vibration and Shock, 2022, 41(6): 21-29

参考文献

[1] Lee J, Wu F J, Zhao W Y, et al. Prognostics and health management design for rotary machinery systems-Reviews, methodology and applications[J]. Mechanical Systems and Signal Processing, 2014, 42(1-2): 314-334.
[2] Hu Q, He Z J, Zhang Z S. Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble[J]. Mechanical Systems and Signal Processing, 2007, 21(2): 688-705.
[3] Wen L, Li X Y, Gao L. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998.
[4] Jia F, Lei Y G, Lin J, et al. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical Systems and Signal Processing, 2016, 72-73: 303-315.
[5] 李恒, 张氢, 秦仙蓉, 等. 基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J]. 振动与冲击, 2018, 37(19): 124-131.
Li H, Zhang Q, Qin X R, et al. Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network [J]. Journal of Vibration and Shock, 2018, 37(19): 124-131. (in Chinese)
[6] 张伟. 基于卷积神经网络的轴承故障诊断算法研究[D]. 哈尔滨:哈尔滨工业大学, 2017.
[7] Pan S J, Yang Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.
[8] Li C, Zhang S H, Qin Y, et al. A systematic review of deep transfer learning for machinery fault diagnosis[J]. Neurocomputing, 2020, 407: 121-135.
[9] Fawaz H I, Forestier G, Weber J, et al. Transfer learning for time series classification[C]// IEEE International Conference on Big Data 2018, IEEE, 2018.
[10] Lu W N, Liang B, Cheng Y, et al. Deep model based domain adaptation for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2017, 64(3): 2296-2305.
[11] Wu Z, Jiang H, Zhao K, et al. An adaptive deep transfer learning method for bearing fault diagnosis[J]. Measurement, 2019, 151:107227.
[12] Wang J R, Ji S S, Han B K, et al. Deep adaptive adversarial network-based method for mechanical fault diagnosis under different working conditions[J]. Complexity, 2020, 2020: 6946702.
[13] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[C]// Advances in Neural Information Processing Systems, Montreal, 2014: 2672-2680.
[14] Zhang Y C, Ren Z H, Zhou S H. An intelligent fault diagnosis for rolling bearing based on adversarial semi-supervised method[J]. IEEE Access, 2020, 8: 3016314.
[15] Jiao J Y, Zhao M, Lin J. Unsupervised adversarial adaptation network for intelligent fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2020, 67(11): 9904-9913.
[16] Shao S Y, Wang P, Yan R Q. Generative adversarial networks for data augmentation in machine fault diagnosis[J]. Computers in Industry, 2019, 106: 85-93.
[17] Liang P F, Deng C, Wu J, et al. Intelligent fault diagnosis via semisupervised generative adversarial nets and wavelet transform[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(7): 4659-4671.
[18] 刘建伟, 刘媛, 罗雄麟. 半监督学习方法[J]. 计算机学报, 2015, 38(8): 1592-1617.
Liu J W, Liu Y, Luo X L. Semi-Supervised Learning Methods[J]. Chinese Journal of Computers, 2015, 38(8): 1592-1617. (in Chinese)
[19] Li X, Zhang W, Ding Q. Cross-domain fault diagnosis of rolling element bearings using deep generative neural networks[J]. IEEE Transactions on Industrial Electronics, 2019, 66(7): 5525-5534.
[20] Jiao J Y, Zhao M, Lin J. Residual joint adaptation adversarial network for intelligent transfer fault diagnosis[J]. Mechanical Systems and Signal Processing, 2020, 145: 106962.
[21] Rozantsev A, Salzmann M, Fua P. Beyond sharing weights for deep domain adaptation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 41(4): 801-814.
[22] Alec R, Luke M. Unsupervised representation learning with deep convolution generative adversarial networks[J]. arXiv: 1511.06434, 2015.
[23] Ganin Y, Ustinova E, Ajakan H, et al. Domain-Adversarial Training of Neural Networks[J]. Journal of Machine Learning Research, 2017, 17(1):2096-2030.
[24] W.A. Smith, R.B. Randall. Rolling element bearing diagnostics using the case western reserve university data: a benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64–65: 100–131.
[25] Laurens V D M, Hinton G. Visualizing Data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(2605):2579-2605.