An exponent adjustment strategy based adversarial network learning method for bearing fault diagnosis

被引：0

作者：

Tian J. ^{[1
,2
]}

Shen C.-Q. ^{[1
,2
]}

Chen Z.-G. ^{[1
]}

Shi J.-J. ^{[2
]}

Jiang X.-X. ^{[2
]}

Zhu Z.-K. ^{[2
]}

机构：

[1] State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University, Chengdu

[2] Department of Vehicle Engineering, School of Rail Transportation, Soochow University, Suzhou

来源：

Zhendong Gongcheng Xuebao/Journal of Vibration Engineering | 2024年 / 37卷 / 03期

关键词：

adversarial learning; bearing; domain adaptation; fault diagnosis;

D O I：

10.16385/j.cnki.issn.1004-4523.2024.03.012

中图分类号：

学科分类号：

摘要：

The fault diagnosis method based on deep learning is widely used in the fault diagnosis of key mechanical components represented by bearings. The premise of achieving ideal results is that there are enough fault samples and the training set and test set meet the same distribution requirements. However，the data distribution will change under the actual working conditions，which makes it difficult to apply the diagnostic model under the original working conditions to the new working conditions. For this reason，the domain adaptation transfer learning method is used to solve the problem of different distribution of training sets and test sets，and its key point is to achieve data distribution adaptation，that is，to measure data distribution differences and use the mea⁃ surement results to guide model training，which can effectively improve learning efficiency and diagnostic accuracy. On this basis，this paper proposes a new domain adaptation method based on adversarial learning. The core of this method is to combine the pro⁃ posed exponential adjustment strategy with adversarial network to make the network adapt to different data distribution in source domain and target domain more specifically in the process of fault diagnosis. The network consists of a feature extractor，a classifi⁃ er，a global domain discriminator，and multiple local domain discriminators，and the model is optimized by using the adversarial strategy and adaptive moment estimation algorithm，and adjusted the importance of marginal distribution and conditional distribu⁃ tion by using the exponential adaptive factor set based on the exponential adjustment strategy，so that the model could diagnose faults stably and efficiently. The proposed method is verified in bearing diagnosis cases of cross-speed，cross-load and simultaneous cross-speed load. The results show that the method in this paper is better than other domain adaptation methods in diagnosis effect and has better stability. © 2024 Nanjing University of Aeronautics an Astronautics. All rights reserved.

引用

页码：476 / 484

页数：8

共 25 条

[1] Liu Wenpeng, Yang Shaopu, Li Qiang, Et al., An enhanced spectral amplitude modulation method and its application to rolling element bearings fault diagnosis under complex interference［J］, Journal of Vibration En⁃ gineering, 34, 5, (2021)
[2] Dong Zhen, Tian Shaoning, Junchao Guo, Et al., An improved decomposition method using EEMD and MSB and its application in rolling bearing fault feature extraction［J］, Journal of Vibration Engineering, 36, 5, (2023)
[3] Li Ke, Yan Han, Gu Jiefei, Et al., Research on multi⁃source transfer learning bearing fault diagnosis based on Shapelets time series［J］, China Mechanical Engineering, 33, 24, pp. 2990-2996, (2022)
[4] Li Y, Liu C., Research on bearing fault diagno⁃ sis based on spectrum characteristics under strong noise interference［J］, Measurement, 169, (2021)
[5] Chen Renxiang, Jun Zhou, Hu Xiaolin, Et al., Fault diagnosis method of rotating machinery based on deep Q⁃learning and continuous wavelet transform［J］, Jour⁃ nal of Vibration Engineering, 34, 5, (2021)
[6] Jun Xia, Minping Jia, Rolling bearing fault diagnosis with a resonance⁃based sparse decomposition and squir⁃ rel optimization algorithm［J］, Journal of Vibration and Shock, 40, 4, (2021)
[7] Zhang K, Xu Y G，, Liao Z Q，, Et al., A novel Fast Entro⁃ gram and its applications in rolling bearing fault diagno⁃ sis［J］, Mechanical Systems and Signal Processing, 154, (2021)
[8] Gomez-Aguilar J F，, Et al., Online ANN⁃based fault diagnosis implementation using an FPGA：application in the EFI system of a vehicle［J］, ISA Transactions, 100, (2020)
[9] Shi Q, Zhang H., Fault diagnosis of an autonomous vehi⁃ cle with an improved SVM algorithm subject to unbal⁃ anced datasets［J］, IEEE Transactions on Industrial Electronics, 68, 7, pp. 6248-6256, (2021)
[10] Chen Z Y, Li W H., Multisensor feature fusion for bear⁃ ing fault diagnosis using sparse autoencoder and deep be⁃ lief network［J］, IEEE Transactions on Instrumentation and Measurement, 66, 7, (2017)

← 1 2 3 →