Academic Journal of Engineering and Technology Science, 2024, 7(4); doi: 10.25236/AJETS.2024.070413.
Zhichao Zhou1,2, Chaofan Hu1,2
1School of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, 541004, Guilin, China
2Guangxi Key Laboratory of Manufacturing System & Advanced Manufacturing Technology, Guilin University of Electronic Technology, 541004, Guilin, China
Our study introduces an innovative intelligent fault diagnosis approach employing the Rationale Invariance-Domain Adversarial Network (RIDAN). This approach leverages domain generalization principles to enhance classification accuracy for data from unknown target domains. The process begins by transforming one-dimensional bearing vibration signals, captured through acceleration sensors, into two-dimensional gray pixel images. Subsequently, a domain discriminator is developed to learn domain-specific features and align domain distributions. Concurrently, a label classifier is established, incorporating rationale matrices for different categories. Our research rigorously validates this methodology using datasets from Guilin University of Electronic Technology and Case Western Reserve University. When compared with contemporary domain generalization methods, our approach shows excellent efficacy in bearing fault diagnosis across different operating domains.
rolling bearings; intelligent fault diagnosis; domain adversarial neural networks; rationale invariance; domain generalization
Zhichao Zhou, Chaofan Hu. Cross-Condition Intelligent Fault Diagnosis of Rolling Bearing Based on Rationle-Invariant Domain Adversarial Networks. Academic Journal of Engineering and Technology Science (2024) Vol. 7, Issue 4: 84-92. https://doi.org/10.25236/AJETS.2024.070413.
[1] X. Wang, H. Jiang, Z. Wu, Q. Yang, Adaptive variational autoencoding generative adversarial networks for rolling bearing fault diagnosis, Adv Eng Inform, 56 (2023) 102027.
[2] Z. Wang, J. Yang, Y. Guo, Unknown fault feature extraction of rolling bearings under variable speed conditions based on statistical complexity measures, Mech Syst Signal Pr, 172 (2022) 108964.
[3] Shuilong He, Qianwen Cui, Jinglong Chen, Tongyang Pan, Chaofan Hu. Contrastive feature-based learning-guided elevated deep reinforcement learning: Developing an imbalanced fault quantitative diagnosis under variable working conditions[J]. Mechanical Systems and Signal Processing, 2024, 211: 111192.
[4] D. Zhao, S. Liu, H. Du, L. Wang, Z. Miao, Deep branch attention network and extreme multi-scale entropy based single vibration signal-driven variable speed fault diagnosis scheme for rolling bearing, Adv Eng Inform, 55 (2023) 101844.
[5] P. Lyu, K. Zhang, W. Yu, B. Wang, C. Liu, A novel RSG-based intelligent bearing fault diagnosis method for motors in high-noise industrial environment, Adv Eng Inform, 52 (2022) 101564.
[6] X. Li, Y. Yang, N. Hu, Z. Cheng, H. Shao, J. Cheng, Maximum margin Riemannian manifold-based hyperdisk for fault diagnosis of roller bearing with multi-channel fusion covariance matrix, Adv Eng Inform, 51 (2022) 101513.
[7] A. Rai, S.H. Upadhyay, A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings, Tribol Int, 96 (2016) 289-306.
[8] J. Lu, B. Jia, S. Li, S. Gong, A noise reduction method of rolling bearing based on empirical wavelet transform and adaptive time frequency peak filtering, Meas Sci Technol, 34 (2023) 125146.
[9] J. Zheng, S. Huang, H. Pan, J. Tong, C. Wang, Q. Liu, Adaptive power spectrum Fourier decomposition method with application in fault diagnosis for rolling bearing, Measurement, 183 (2021) 109837.
[10] S. Aziz, M.U. Khan, M. Faraz, G.A. Montes, Intelligent bearing faults diagnosis featuring Automated Relative Energy based Empirical Mode Decomposition and novel Cepstral Autoregressive features, Measurement, 216 (2023) 112871.
[11] Z. Liu, D. Peng, M.J. Zuo, J. Xia, Y. Qin, Improved Hilbert–Huang transform with soft sifting stopping criterion and its application to fault diagnosis of wheelset bearings, Isa T, 125 (2022) 426-444.
[12] J. Wang, C. Lan, C. Liu, Y. Ouyang, T. Qin, W. Lu, Y. Chen, W. Zeng, P. Yu, Generalizing to Unseen Domains: A Survey on Domain Generalization, IEEE Transactions on Knowledge and Data Engineering, (2022) 1-1.