Physics Informed Self Supervised Learning For Fault Diagnostics and Prognostics in the Context of Sparse and Noisy Data



Published Jun 29, 2022
Weikun Deng Khanh T. P. Nguyen Kamal Medjaher


Sparse & noisy monitoring data leads to numerous challenges in prognostic and health management (PHM). Big data volume but poor quality with scarce healthy states information limits the performance of training machine learning (ML) and physics-based failure modeling. To address these challenges, this thesis aims to develop a new hybrid PHM framework with the ability to autonomously discover and exploit incomplete implicit physics knowledge in sparse & noisy monitoring data, providing a solution for deep physics knowledge-ML fusion by physics-informed machine learning algorithms. In addition, the developed hybrid framework also applies the self-supervised learning paradigm to significantly improve the learning performance under uncertain, sparse, and noisy data with lower requirements for specialist area knowledge. The performance of the developed algorithms will be investigated on the sparse and noise data generated by simulation data sets, public benchmark data sets, and the PHM platform to demonstrate its applicability.

How to Cite

Deng, W., Nguyen, K. T. P., & Medjaher, K. (2022). Physics Informed Self Supervised Learning For Fault Diagnostics and Prognostics in the Context of Sparse and Noisy Data. PHM Society European Conference, 7(1), 574–576.
Abstract 529 | PDF Downloads 438



Prognostic and Health Management, Sparse & noisy data, Hybrid framework, Physics informed machine learning, Self-supervised learning

1. Chao, M. A., Kulkarni, C., Goebel, K., & Fink, O. (2019). Hybrid deep fault detection and isolation: Combining deep neural networks and system performance models. arXiv preprint arXiv:1908.01529.
2. Cury, A., Ribeiro, D., Ubertini, F., & Todd, M. D. (n.d.). Structural health monitoring based on data science techniques. Springer.
3. Ding, Y., Zhuang, J., Ding, P., & Jia, M. (2022). Self- supervised pretraining via contrast learning for intelligent incipient fault detection of bearings. Reliability Engineering & System Safety, 218, 108126.
4. Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3(6), 422–440.
5. Kim, N., An, D., & Choi, J.-H. (2017, 01). Prognostics and health management of engineering systems.
6. Kim, S. W., Kim, I., Lee, J., & Lee, S. (2021). Knowledge integration into deep learning in dynamical systems: an overview and taxonomy. Journal of Mechanical Science and Technology, 1–12.
7. Mart ́ın-Gonz ́alez, E., Alskaf, E., Chiribiri, A., Casaseca-de-la Higuera, P., Alberola-L ́opez, C., Nunes, R. G., & Correia, T. (2021). Physics-informed self-supervised deep learning reconstruction for accelerated first-pass perfusion cardiac mri. In International workshop on machine learning for medical image reconstruction (pp.
8. Viana, F. A., & Subramaniyan, A. K. (2021). A survey of bayesian calibration and physics-informed neural networks in scientific modeling. Archives of Computational Methods in Engineering, 28(5), 3801–3830.
9. Wang, T., Qiao, M., Zhang, M., Yang, Y., & Snoussi, H. (2020). Data-driven prognostic method based on self-supervised learning approaches for fault de-
tection. Journal of Intelligent Manufacturing, 31(7), 1611–1619.
10. Yaman, B., Hosseini, S. A. H., Moeller, S., Ellermann, J., U ̆gurbil, K., & Akc ̧akaya, M. (2020). Self-supervised learning of physics-guided reconstruction neural networks without fully sampled reference data. Magnetic resonance in medicine, 84(6), 3172–3191.
11. Zhang, T., Chen, J., He, S., & Zhou, Z. (2022). Prior knowledge-augmented self-supervised feature learning
for few-shot intelligent fault diagnosis of machines. IEEE Transactions on Industrial Ele
Doctoral Symposium