Towards Physics-Informed PHM for Multi-component degradation (MCD) in complex systems

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

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

Published Jun 27, 2024
Atuahene Barimah Octavian Niculita Don McGlinchey Andrew Cowell Billy Milligan

Abstract

This study seeks to address the challenge of limited degradation data in developing Fault Detection and Isolation (FDI) models for multi-component degradation (MCD) scenarios. Utilizing a small fraction (0.05%) of a previously utilized water distribution testbed dataset in a previous publication, a weighted ensemble hybrid approach is proposed and evaluated against more established modelling approaches used in the previous publication. The proposed approach combines heuristic approximation and Physics-Informed Neural Network (PINN) methods with a recurrent neural network (RNN) model to enhance diagnostic performance for predicting MCD scenarios. The hybrid model generally outperformed other algorithms when tested on an MCD dataset, demonstrating improved diagnostic accuracy in such scenarios. Future research aims to optimize ensemble weights based on model uncertainty, further enhancing diagnostic capabilities.

How to Cite

Barimah, A., Niculita , O. ., McGlinchey, D. ., Cowell, A. ., & Milligan, B. (2024). Towards Physics-Informed PHM for Multi-component degradation (MCD) in complex systems . PHM Society European Conference, 8(1), 14. https://doi.org/10.36001/phme.2024.v8i1.4099
Abstract 241 | PDF Downloads 148

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

Keywords

Physics Informed Neural Network (PINN), Multi Component Degradation, Fault Detection and Isolation, Digital Twin, PHM

References
Bararnia, H., & Esmaeilpour, H. (2022). On the application of physics informed neural networks (PINN) to solve boundary layer thermal-fluid problems. International Communications in Heat and Mass Transfer.
Barimah, A., Niculita, I.-O., McGlinchey, D., & Cowell, A. (2023). Data-quality assessment for digital twins targeting multi-component degradation in industrial internet of things (IIoT)-enabled smart infrastructure systems. Applied Science, 13(24).
Barimah, A., Niculita, O., McGlinchey, D., & Alkali., B. (2021). Optimal Service Points (OSP) for PHM enabled condition based maintenance for oil and gas applications. 6th European Conference of the Prognostics and Health Management Society.
Bera, S. and Shrivastava, V.K., 2020. Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification. International Journal of Remote Sensing, 41(7), pp.2664-2683.
Cai, S., Mao, Z., Wang, Z., Yin, M., & Karniadakis, G. (2021). Physics-informed neural networks (PINNs) for fluid mechanics. A review. Acta Mechanica Sinica, 1727-1738.
Duriez, T., Brunton, S., & Noack, B. (2017). Machine learning control-taming nonlinear dynamics and turbulence. Cham: Springer.
Higdon, D., Kennedy, M., Cavendish, J., Cafeo, J., & Ryne, R. (2004). Combining field data and computer simulations for calibration and prediction. SIAM Journal on Scientific Computing, 26(2), 448-466.
Hu, Y., Miao, X., Si, Y., Pan, E., & Zio, E. (2022). Prognostics and health management: A review from the perspectives of design, development and decision. Reliability Engineering & System Safety, 217, 108063.
Huang, B., & Wang, J. (2022). Applications of physics-informed neural networks in power systems-a review. IEEE Transactions on Power Systems, 38(1), 572-588.
Knight, E., Russell, M., Sawalka, D. and Yendell, S., 2013. ValveModeling. Control Valve Wiki.
Lu, Q., Xie, X., Parlikad, A., & Schooling, J. (2020). Digital twin-enabled anomaly detection for built asset monitoring in operation and maintenance. Automation in Construction, 118, 103277.
Maass, W., Parsons, J., Purao, S., Storey, V., & Woo, C. (2018). Data-driven meets theory-driven research in the era of big data: Opportunities and challenges for information systems research. ournal of the Association for Information Systems,, 19(2), 1.
Rizi, S., & Abbas, M. (2023). From data to insight, enhancing structural health monitoring using physics-informed machine learning and advanced data collection methods. Engineering Research Express, 5(3), 32003.
Section
Technical Papers