Fault Diagnosis of Variable Working Conditions Based on Transfer Learning and Multi-channel CNN-LSTM Network

被引:1
作者
Che, Kang [1 ]
Jin, Yongze [1 ]
Mu, Lingxia [1 ]
Li, Yankai [1 ]
Zhang, Jian [1 ]
Xie, Guo [1 ]
机构
[1] Xian Univ Technol, Sch Automat & Informat Engn, Xian, Peoples R China
来源
2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC | 2023年
基金
美国国家科学基金会;
关键词
Rolling hearings; variable working conditions; DANN Network; multi-channel feature fusion;
D O I
10.1109/CCDC58219.2023.10327445
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
As an indispensable component in the operation of machines, rolling bearings play an important role in modern industrial systems. In order to accurately diagnose the target domain fault data in this context, in this paper, the variable working condition dataset is firstly constructed. Further, the discrete Fourier transform (DFT) is applied to the original vibration signals, which can obtain the frequency domain signals. Then, on the basis of the domain adversarial neural networks(DANN) network, the multi-channel convolutional long short-term memory neural network(CNN-LSTM) network is utilized to perform feature fusion, the feature extraction module is reconstructed, and a cross-domain fault diagnosis model is established. Finally, the experimental results show that the proposed network model can extract the temporal characteristics of vibration signals more fully, improve the diagnostic performance of target domain datasets under different variable working conditions, and have good generalization performance under different working conditions.
引用
收藏
页码:658 / 663
页数:6
相关论文
共 15 条
[1]  
[Anonymous], 2019, 2019 PROGN SYST HLTH, DOI DOI 10.1109/GLOBECOM38437.2019.9014261
[2]   A Comparative Study of Various Methods of Bearing Faults Diagnosis Using the Case Western Reserve University Data [J].
Boudiaf A. ;
Moussaoui A. ;
Dahane A. ;
Atoui I. .
Journal of Failure Analysis and Prevention, 2016, 16 (02) :271-284
[3]   Long-Term Recurrent Convolutional Networks for Visual Recognition and Description [J].
Donahue, Jeff ;
Hendricks, Lisa Anne ;
Rohrbach, Marcus ;
Venugopalan, Subhashini ;
Guadarrama, Sergio ;
Saenko, Kate ;
Darrell, Trevor .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (04) :677-691
[4]  
Ganin Y, 2016, J MACH LEARN RES, V17
[5]   Bearing Fault Diagnosis Using Fully-Connected Winner-Take-All Autoencoder [J].
Li, Chuanhao ;
Zhang, Wei ;
Peng, Gaoliang ;
Liu, Shaohui .
IEEE ACCESS, 2018, 6 :6103-6115
[6]   Cross-domain intelligent bearing fault diagnosis under class imbalanced samples via transfer residual network augmented with explicit weight self-assignment strategy based on meta data [J].
Liu, Xuan ;
Chen, Jinglong ;
Zhang, Kaiyu ;
Liu, Shen ;
He, Shuilong ;
Zhou, Zitong .
KNOWLEDGE-BASED SYSTEMS, 2022, 251
[7]   Transfer learning using computational intelligence: A survey [J].
Lu, Jie ;
Behbood, Vahid ;
Hao, Peng ;
Zuo, Hua ;
Xue, Shan ;
Zhang, Guangquan .
KNOWLEDGE-BASED SYSTEMS, 2015, 80 :14-23
[8]   Deep Model Based Domain Adaptation for Fault Diagnosis [J].
Lu, Weining ;
Liang, Bin ;
Cheng, Yu ;
Meng, Deshan ;
Yang, Jun ;
Zhang, Tao .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2017, 64 (03) :2296-2305
[9]  
Radford A., 2016, INT C LEARN REPR
[10]  
[唐波 Tang Bo], 2020, [电子测量与仪器学报, Journal of Electronic Measurement and Instrument], V34, P88