Enhancing Data-driven Vibration-based Machinery Fault Diagnosis Generalization Under Varied Conditions by Removing Domain-Specific Information Utilizing Sparse Representation
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
This paper introduces a novel approach to machinery fault diagnosis, addressing the challenge of domain generalization in diverse industrial environments. Traditional methods often struggle with domain shift and the scarcity of balanced, la- beled datasets, limiting their effectiveness across varied oper- ational conditions. The proposed method leverages the abun- dance of healthy machinery signals as a reference for extract- ing domain-specific information. By doing so, it removes the domain-related variances from the observation signals, focus- ing on the intrinsic characteristics of faults. The methodol- ogy is validated with a case study, demonstrating enhanced diagnosis accuracy and generalization capabilities in unseen domains. This research contributes to the field of vibration- based intelligent fault diagnosis by providing a robust solu- tion to a long-standing problem in machine condition moni- toring.
How to Cite
##plugins.themes.bootstrap3.article.details##
rotating machines, intelligent fault diagnosis, vibration analysis, domain generalization
Antoni, J., Bonnardot, F., Raad, A., & El Badaoui, M. (2004, November). Cyclostationary modelling of ro- tating machine vibration signals. Mechanical Sys- tems and Signal Processing, 18(6), 1285–1314. doi: 10.1016/S0888-3270(03)00088-8
Azari, M. S., Flammini, F., Santini, S., & Caporuscio, M. (2023). A Systematic Literature Review on Transfer Learning for Predictive Maintenance in Industry 4.0. IEEE Access, 11, 12887–12910. doi: 10.1109/AC- CESS.2023.3239784
Borghesani, P., Herwig, N., Antoni, J., & Wang, W. (2023, December). A Fourier-based explanation of 1D-CNNs for machine condition monitoring applications. Me- chanical Systems and Signal Processing, 205, 110865. doi: 10.1016/j.ymssp.2023.110865
Cai, G., Selesnick, I. W., Wang, S., Dai, W., & Zhu, Z. (2018, October). Sparsity-enhanced signal decomposition via generalized minimax-concave penalty for gearbox fault diagnosis. Journal of Sound and Vibration, 432, 213– 234. doi: 10.1016/j.jsv.2018.06.037
Chen, S. S., Donoho, D. L., & Saunders, M. A. (1998, January). Atomic Decomposition by Basis Pur- suit. SIAM J. Sci. Comput., 20(1), 33–61. doi: 10.1137/S1064827596304010
Feng, Z., Zhou, Y., Zuo, M. J., Chu, F., & Chen, X. (2017, June). Atomic decomposition and sparse representa- tion for complex signal analysis in machinery fault di- agnosis: A review with examples. Measurement, 103, 106–132. doi: 10.1016/j.measurement.2017.02.031
Iatsenko, D., McClintock, P., & Stefanovska, A. (2016, August). Extraction of instantaneous frequencies from ridges in time–frequency representations of sig- nals. Signal Processing, 125, 290–303. doi: 10.1016/j.sigpro.2016.01.024
Jia, S., Li, Y., Wang, X., Sun, D., & Deng, Z. (2023, June). Deep causal factorization network: A novel domain generalization method for cross-machine bearing fault diagnosis. Mechanical Systems and Signal Processing, 192, 110228. doi: 10.1016/j.ymssp.2023.110228
Kim, I., Wook Kim, S., Kim, J., Huh, H., Jeong, I., Choi, T., . . . Lee, S. (2024, May). Single do- main generalizable and physically interpretable bear- ing fault diagnosis for unseen working conditions. Ex- pert Systems with Applications, 241, 122455. doi: 10.1016/j.eswa.2023.122455
Liu, R., Yang, B., Zio, E., & Chen, X. (2018, Au- gust). Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Sys- tems and Signal Processing, 108, 33–47. doi:
10.1016/j.ymssp.2018.02.016
Mallat, S., & Zhang, Z. (1993, December). Match-
ing pursuits with time-frequency dictionaries. IEEE Transactions on Signal Processing, 41(12). doi: 10.1109/78.258082
Qin, Y. (2018, March). A New Family of Model-Based Impulsive Wavelets and Their Sparse Representation for Rolling Bearing Fault Diagnosis. IEEE Transac- tions on Industrial Electronics, 65(3), 2716–2726. doi: 10.1109/TIE.2017.2736510
Randall, R. (2010, 12). Vibration-based condition moni- toring: Industrial, aerospace and automotive applica- tions. Vibration-based Condition Monitoring: Indus- trial, Aerospace and Automotive Applications. doi: 10.1002/9780470977668
Selesnick, I. (2017, September).
ization via Convex Analysis.
on Signal Processing, 65(17), 4481–4494. doi: 10.1109/TSP.2017.2711501
Shi, Y., Deng, A., Deng, M., Li, J., Xu, M., Zhang, S., . . . Xu, S. (2023, June). Domain Transferability- Based Deep Domain Generalization Method Towards Actual Fault Diagnosis Scenarios. IEEE Transactions on Industrial Informatics, 19(6), 7355–7366. doi: 10.1109/TII.2022.3210555
Wang, R., Huang, W., Lu, Y., Zhang, X., Wang, J., Ding, C., & Shen, C. (2023, October). A novel domain gener- alization network with multidomain specific auxiliary classifiers for machinery fault diagnosis under unseen working conditions. Reliability Engineering & System Safety, 238, 109463. doi: 10.1016/j.ress.2023.109463
Zhang, D., & Feng, Z. (2022, January). Enhance- ment of time-frequency post-processing readability for nonstationary signal analysis of rotating machin- ery: Principle and validation. Mechanical Sys- tems and Signal Processing, 163, 108145. doi: 10.1016/j.ymssp.2021.108145
Zhao, C., & Shen, W. (2023, April). Mutual-assistance semisupervised domain generalization network for in- telligent fault diagnosis under unseen working condi- tions. Mechanical Systems and Signal Processing, 189, 110074. doi: 10.1016/j.ymssp.2022.110074
Zheng, H., Yang, Y., Yin, J., Li, Y., Wang, R., & Xu, M. (2021). Deep Domain Generalization Combining A Priori Diagnosis Knowledge Toward Cross-Domain Fault Diagnosis of Rolling Bearing. IEEE Transactions on Instrumentation and Measurement, 70, 1–11. doi: 10.1109/TIM.2020.3016068
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.