Generalizing Bearing Fault Diagnosis to Physically Unseen Bearings Adversarial Representation Learning and Bearing-Identity Analysis
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Reliable bearing fault diagnosis requires generalization to physical components unseen during model development. This study evaluates such generalization using strict 32-fold Leave-One-Bearing-Out (LOBO) testing on the Paderborn University Bearing Dataset. All four diagnostic classes are retained, and each physical bearing is treated as the unit of generalization. The input combines 53 dynamic vibration-derived features and 30 physics-informed features. A classical machine-learning baseline, a deep model without adversarial learning (No-GRL), and a class-conditional Gradient-Reversal Learning (GRL) model with four bearing-domain adversarial heads are compared under the same protocol. At the bearing level, the classical model achieves 81.25% Accuracy, 74.81% Balanced Accuracy, and 77.82% Macro-F1; No-GRL achieves 78.12%, 74.81%, and 77.75%; and GRL achieves 81.25%, 76.89%, and 79.85%, respectively. Relative to No-GRL, GRL yields numerical gains of 3.13, 2.08, and 2.10 percentage points. However, only one held-out bearing changed from an incorrect No-GRL prediction to a correct GRL prediction, with no observed regression; the exact two-sided McNemar test gives p=1.000. A post-hoc Bearing-Identity Representation Audit shows that mean linear Bearing-ID accuracy decreases from 99.22% for No-GRL to 86.27% for GRL across the folds. This remains well above the 31-class chance level, indicating reduced rather than eliminated bearing-specific information. Thus, GRL is associated with modest aggregate diagnostic gains and lower linear recoverability of bearing identity, but the paired results do not establish a statistically significant general improvement in fault classification.
##plugins.themes.bootstrap3.article.details##
Bearing Fault Diagnosis, Leave-One-Bearing-Out (LOBO), Domain Generalization, Domain-Adversarial Training, Bearing Identity
Cheng, L., Kong, X., Zhang, Y., Zhu, Y., Qi, H., & Zhang, J. (2024). A novel causal feature learning-based domain generalization framework for bearing fault diagnosis with a mixture of data from multiple working conditions and machines. Advanced Engineering Informatics, 62, Article 102622. https://doi.org/10.1016/j.aei.2024.102622
Ding, Y., Jia, M., Cao, Y., Ding, P., Zhao, X., & Lee, C.-G. (2023). Domain generalization via adversarial out-domain augmentation for remaining useful life prediction of bearings under unseen conditions. Knowledge-Based Systems, 261, Article 110199. https://doi.org/10.1016/j.knosys.2022.110199
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. S. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(59), 1-35.
Guo, Z., Xu, L., Zheng, Y., Xie, J., & Wang, T. (2025). Bearing fault diagnostic framework under unknown working conditions based on condition-guided diffusion model. Measurement, 242, Article 115951. https://doi.org/10.1016/j.measurement.2024.115951
Hoang, D.-T., & Kang, H.-J. (2019). A survey on deep learning based bearing fault diagnosis. Neurocomputing, 335, 327–335.
https://doi.org/10.1016/j.neucom.2018.06.078
Kim, I., Kim, S. W., Kim, J., Huh, H., Jeong, I., Choi, T., Kim, J., & Lee, S. (2024). Single domain generalizable and physically interpretable bearing fault diagnosis for unseen working conditions. Expert Systems with Applications, 241, Article 122455. https://doi.org/10.1016/j.eswa.2023.122455
Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. K. (2020). Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing, 138, Article 106587. https://doi.org/10.1016/j.ymssp.2019.106587
Lessmeier, C., Kimotho, J. K., Zimmer, D., & Sextro, W. (2016). Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: A benchmark data set for data-driven classification. PHM Society European Conference, 3(1). https://doi.org/10.36001/phme.2016.v3i1.157
Li, Q., Chen, L., Kong, L., Wang, D., Xia, M., & Shen, C. (2023). Cross-domain augmentation diagnosis: An adversarial domain-augmented generalization method for fault diagnosis under unseen working conditions. Reliability Engineering & System Safety, 234, Article 109171. https://doi.org/10.1016/j.ress.2023.109171
Muandet, K., Balduzzi, D., & Schölkopf, B. (2013). Domain generalization via invariant feature representation. In Proceedings of the 30th International Conference on Machine Learning (Vol. 28, No. 1, pp. 10–18). PMLR
Pang, B., Liu, Q., Xu, Z., Sun, Z., Hao, Z., & Song, Z. (2024). Fault vibration model driven fault-aware domain generalization framework for bearing fault diagnosis. Advanced Engineering Informatics, 62, Article 102620. https://doi.org/10.1016/j.aei.2024.102620
Shi, Y., Deng, A., Deng, M., Xu, M., Liu, Y., Ding, X., & Bian, W. (2023). Domain augmentation generalization network for real-time fault diagnosis under unseen working conditions. Reliability Engineering & System Safety, 235, Article 109188. https://doi.org/10.1016/j.ress.2023.109188
Vieira, J. P., Bauler, V. A., Rosa, R. K., & Silva, D. (2026). Towards a more realistic evaluation of machine learning models for bearing fault diagnosis. Mechanical Systems and Signal Processing, 258, Article 114640. https://doi.org/10.1016/j.ymssp.2026.114640
Zhang, Q., Zhao, Z., Zhang, X., Liu, Y., Sun, C., Li, M., Wang, S., & Chen, X. (2021). Conditional adversarial domain generalization with a single discriminator for bearing fault diagnosis. *IEEE Transactions on Instrumentation and Measurement, 70*, Article 3514515. https://doi.org/10.1109/TIM.2021.3071350
Zhao, Z., Li, T., Wu, J., Sun, C., Wang, S., Yan, R., & Chen, X. (2020). Deep learning algorithms for rotating machinery intelligent diagnosis: An open source benchmark study. ISA Transactions, 107, 224–255. https://doi.org/10.1016/j.isatra.2020.08.010
Zhu, Y., Zi, Y., Li, J., & Xu, J. (2024). PhysiCausalNet: A causal- and physics-driven domain generalization network for cross-machine fault diagnosis of unseen domain. IEEE Transactions on Industrial Informatics, 20(6), 8488–8498. https://doi.org/10.1109/TII.2024.3369240