A Graph Neural Network Approach to System-Level Health Index and Remaining Useful Life Estimation

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

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

Published Nov 11, 2024
Ark Ifeanyi

Abstract

Current methods for predicting health index and remaining useful life (RUL) in complex systems struggle to account for performance dependencies between components, leading to inaccurate system-level estimates. This research proposes a novel approach utilizing graph neural networks (GNNs) to improve system-level health index and RUL estimation. GNNs excel at capturing complex interdependencies within a system, making them ideal for this task. The proposed methodology is designed for systems with synchronously sampled process data. To illustrate the application of the proposed approach, we will use the Condensate Extraction Subsystem (CES) of a nuclear power plant (NPP) as a case study. Sensor data like temperature, pressure, and flow rates will be used to train GNNs to predict the overall health and RUL of the CES over time. To evaluate the effectiveness of GNNs, a custom NPP simulator will be used to model the CES under various realistic fault modes across a variety of components. The GNN's performance will be verified and its robustness will be tested under diverse scenarios. This research aims to demonstrate the effectiveness and resilience of GNNs for system-level prognostics.
By providing valuable insights for maintenance decision-making, this approach can enhance operational reliability and safety in complex engineering systems.
The proposed framework has the potential to be applied across various industries, leading to advancements in predictive maintenance practices.

How to Cite

Ifeanyi, A. (2024). A Graph Neural Network Approach to System-Level Health Index and Remaining Useful Life Estimation. Annual Conference of the PHM Society, 16(1). https://doi.org/10.36001/phmconf.2024.v16i1.4159
Abstract 34 | PDF Downloads 23

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

Keywords

Condition-based Maintenance, System-level Prognostics, Machine Learning, Neural Networks, Condensate Extraction System, Energy Systems

References
Adams, M. L. (2017). Power plant centrifugal pumps: problem analysis and troubleshooting. CRC Press.
Behera, S., Misra, R., & Sillitti, A. (2021). Multiscale deep bidirectional gated recurrent neural networks based prognostic method for complex non-linear degradation systems. Information Sciences, 554, 120–144.
Cao, D., Wang, Y., Duan, J., Zhang, C., Zhu, X., Huang, C., . . . others (2020). Spectral temporal graph neural network for multivariate time-series forecasting. Advances in neural information processing systems, 33, 17766–17778.
Gomes, J. P. P., Rodrigues, L. R., Galvão, R. K. H., & Yoneyama, T. (2013). System level rul estimation for multiple-component systems. In Annual conference of the phm society (Vol. 5).
Ifeanyi, A. O., Coble, J. B., & Saxena, A. (2024). A deep learning approach to within-bank fault detection and diagnostics of fine motion control rod drives. International Journal of Prognostics and Health Management, 15(1).
Kim, S., Choi, J.-H., & Kim, N. H. (2021). Challenges and opportunities of system-level prognostics. Sensors, 21(22), 7655.
Lee, S., Hassan, Y. A., Abdulsattar, S. S., & Vaghetto, R. (2014). Experimental study of head loss through an loca-generated fibrous debris bed deposited on a sump strainer for generic safety issue 191. Progress in Nuclear Energy, 74, 166–175.
RuÍz-Tagle Palazuelos, A., & Droguett, E. L. (2021). Systemlevel prognostics and health management: A graph convolutional network–based framework. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 235(1), 120–135.
Silva, R., Shirvan, K., Piqueira, J. R. C., Marques, R. P., et al. (2020). Development of the asherah nuclear power plant simulator for cyber security assessment. In Proceedings of the international conference on nuclear security, vienna, austria (pp. 10–14).
Wang, H., Peng, M.-j., Wu, P., & Cheng, S.-y. (2016). Improved methods of online monitoring and prediction in condensate and feed water system of nuclear power plant. Annals of Nuclear Energy, 90, 44–53.
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Philip, S. Y. (2020). A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1), 4–24.
Section
Doctoral Symposium Summaries