DiffPhysiNet: A Bearing Diagnostic Framework Based on Physics-Driven Diffusion Network for Unseen Working Conditions

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Zhinbin Guo Jingsong Xie Tongyang Pan Tiantian Wang

Abstract

Fault diagnosis is essential to ensure bearing safety in industrial applications. Many existing diagnostic methods require large scales of data from a full range of working conditions. However, the structure and working conditions differences between machines lead to significant variation in data distribution, making it difficult to diagnostic with unseen samples. To handle this situation, an unknown condition diagnosis Framework (UCDF) based on physics-driven diffusion network (DiffPhysiNet) is proposed, effectively integrating the generation capability of the diffusion model and learning from the working conditional encoding (WCE). Specifically, signals under limited working conditions are gradually convert to noise through a forward noising process. Then, DiffPhysiNet reconstructs signals from the noise by a reverse denoising process. In addition, a physics-driven UNet (Physi-UNet) structure is designed to extract WCE for noise level prediction during the reverse process. Moreover, an Unsupervised Clustering Filter (UCFilter) is constructed to select signals with high quality after generation. Signals under unknown working condition can be generated with certain WCE. Ultimately, extensive experiments on two bearing datasets (SDUST and PU) validate the effectiveness of our method compared with the state-of-the-art baselines and the ablution test confirms the significant role of Physi-UNet and UCFilter.

How to Cite

Guo, Z., Xie, J., Pan, T. ., & Wang, T. . (2024). DiffPhysiNet: A Bearing Diagnostic Framework Based on Physics-Driven Diffusion Network for Unseen Working Conditions. PHM Society European Conference, 8(1), 10. https://doi.org/10.36001/phme.2024.v8i1.4119
Abstract 206 | PDF Downloads 165

##plugins.themes.bootstrap3.article.details##

Keywords

Diffusion Model, Unseen Working Condition, Fault Diagnosis, Rotating Machinery

References
Ben-David, S., J. Blitzer, K. Crammer, A. Kulesza, F. Pereira, and J. W. Vaughan. 2010. 'A theory of learning from different domains', Machine Learning, 79: 151-75.
Benitez, Jose Antonio Lara, Takashi Furuya, Florian Faucher, Xavier Tricoche, and Maarten V. de Hoop. 2023. 'Fine-tuning Neural-Operator architectures for training and generalization', Arxiv.
Chen, L., Q. Li, C. Q. Shen, J. Zhu, D. Wang, and M. Xia. 2022. 'Adversarial Domain-Invariant Generalization: A Generic Domain-Regressive Framework for Bearing Fault Diagnosis Under Unseen Conditions', Ieee Transactions on Industrial Informatics, 18: 1790-800.
Chen, Z. Y., and W. H. Li. 2017. 'Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network', Ieee Transactions on Instrumentation and Measurement, 66: 1693-702.
Cui, W., J. Ding, G. Y. Meng, Z. Y. Lv, Y. H. Feng, A. M. Wang, and X. W. Wan. 2023. 'Fault Diagnosis of Rolling Bearings in Primary Mine Fans under Sample Imbalance Conditions', Entropy, 25.
Dang, Z. R., and M. Ishii. 2022. 'Towards stochastic modeling for two-phase flow interfacial area predictions: A physics-informed reinforcement learning approach', International Journal of Heat and Mass Transfer, 192.
Han, T., Y. F. Li, and M. Qian. 2021. 'A Hybrid Generalization Network for Intelligent Fault Diagnosis of Rotating Machinery Under Unseen Working Conditions', Ieee Transactions on Instrumentation and Measurement, 70.
Hu, C. F., Y. X. Wang, and J. W. Gu. 2020. 'Cross-domain intelligent fault classification of bearings based on tensor-aligned invariant subspace learning and two-dimensional convolutional neural networks', Knowledge-Based Systems, 209.
Huang, Z. L., Z. H. Lei, G. R. Wen, X. Huang, H. X. Zhou, R. Q. Yan, and X. F. Chen. 2022. 'A Multisource Dense Adaptation Adversarial Network for Fault Diagnosis of Machinery', Ieee Transactions on Industrial Electronics, 69: 6298-307.
Jia, S. X., J. R. Wang, B. K. Han, G. W. Zhang, X. Y. Wang, and J. T. He. 2020. 'A Novel Transfer Learning Method for Fault Diagnosis Using Maximum Classifier Discrepancy With Marginal Probability Distribution Adaptation', Ieee Access, 8: 71475-85.
Jiao, J. Y., M. Zhao, J. Lin, and K. X. Liang. 2020. 'Residual joint adaptation adversarial network for intelligent transfer fault diagnosis', Mechanical Systems and Signal Processing, 145.
Kordestani, M., M. Saif, M. E. Orchard, R. Razavi-Far, and K. Khorasani. 2021. 'Failure Prognosis and Applications-A Survey of Recent Literature', Ieee Transactions on Reliability, 70: 728-48.
Lehmann, F., F. Gatti, M. Bertin, and D. Clouteau. 2024. '3D elastic wave propagation with a Factorized Fourier Neural Operator (F-FNO)', Computer Methods in Applied Mechanics and Engineering, 420.
Li, R. R., S. M. Li, K. Xu, J. T. Lu, G. R. Teng, and J. Du. 2021. 'Deep domain adaptation with adversarial idea and coral alignment for transfer fault diagnosis of rolling bearing', Measurement Science and Technology, 32.
Li, W. H., R. Y. Huang, J. P. Li, Y. X. Liao, Z. Y. Chen, G. L. He, R. Q. Yan, and K. Gryllias. 2022. 'A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges', Mechanical Systems and Signal Processing, 167.
Li, X., W. Zhang, Q. Ding, and J. Q. Sun. 2020. 'Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation', Journal of Intelligent Manufacturing, 31: 433-52.
Michau, G., and O. Fink. 2019. 'Domain Adaptation for One-Class Classification: Monitoring the Health of Critical Systems Under Limited Information', International Journal of Prognostics and Health Management, 10.
Rafiq, M., G. Rafiq, and G. S. Choi. 2022. 'DSFA-PINN: Deep Spectral Feature Aggregation Physics Informed Neural Network', Ieee Access, 10: 22247-59.
Rombach, K., G. Michau, and O. Fink. 2023. 'Controlled generation of unseen faults for Partial and Open-Partial domain adaptation', Reliability Engineering & System Safety, 230.
Shu, D. L., Z. J. Li, and A. B. Farimani. 2023. 'A physics-informed diffusion model for high-fidelity flow field reconstruction', Journal of Computational Physics, 478.
Si, Y. N., J. X. Pu, S. F. Zang, and L. F. Sun. 2021. 'Extreme Learning Machine Based on Maximum Weighted Mean Discrepancy for Unsupervised Domain Adaptation', Ieee Access, 9: 2283-93.
van der Maaten, L., and G. Hinton. 2008. 'Visualizing Data using t-SNE', Journal of Machine Learning Research, 9: 2579-605.
Wang, K. W., X. Zhang, Q. S. Hao, Y. Wang, and Y. Shen. 2019. 'Application of improved least-square generative adversarial networks for rail crack detection by AE technique', Neurocomputing, 332: 236-48.
Wang, X., C. Q. Shen, M. Xia, D. Wang, J. Zhu, and Z. K. Zhu. 2020. 'Multi-scale deep intra-class transfer learning for bearing fault diagnosis', Reliability Engineering & System Safety, 202.
Zio, E. 2022. 'Prognostics and Health Management (PHM): Where are we and where do we (need to) go in theory and practice', Reliability Engineering & System Safety, 218.
Zuo, L., F. J. Xu, C. H. Zhang, T. F. Xiahou, and Y. Liu. 2022. 'A multi-layer spiking neural network-based approach to bearing fault diagnosis', Reliability Engineering & System Safety, 225.
Section
Technical Papers