Version 1
: Received: 24 April 2024 / Approved: 25 April 2024 / Online: 28 April 2024 (04:53:12 CEST)
How to cite:
Žnidarič, L.; Gradišar, Ž.; Juričić, Đ. Predicting the Remaining Useful Life of Solid Oxide Fuel Cell Systems Using Adaptive Trend Models of Health Indicators. Preprints2024, 2024041651. https://doi.org/10.20944/preprints202404.1651.v1
Žnidarič, L.; Gradišar, Ž.; Juričić, Đ. Predicting the Remaining Useful Life of Solid Oxide Fuel Cell Systems Using Adaptive Trend Models of Health Indicators. Preprints 2024, 2024041651. https://doi.org/10.20944/preprints202404.1651.v1
Žnidarič, L.; Gradišar, Ž.; Juričić, Đ. Predicting the Remaining Useful Life of Solid Oxide Fuel Cell Systems Using Adaptive Trend Models of Health Indicators. Preprints2024, 2024041651. https://doi.org/10.20944/preprints202404.1651.v1
APA Style
Žnidarič, L., Gradišar, Ž., & Juričić, Đ. (2024). Predicting the Remaining Useful Life of Solid Oxide Fuel Cell Systems Using Adaptive Trend Models of Health Indicators. Preprints. https://doi.org/10.20944/preprints202404.1651.v1
Chicago/Turabian Style
Žnidarič, L., Žiga Gradišar and Đani Juričić. 2024 "Predicting the Remaining Useful Life of Solid Oxide Fuel Cell Systems Using Adaptive Trend Models of Health Indicators" Preprints. https://doi.org/10.20944/preprints202404.1651.v1
Abstract
Degradation is an inevitable companion in the operation of solid oxide fuel cell (SOFC) systems since it directly deteriorates the reliability of the system’s operation and the system’s durability. Both are seen as barriers that limit the extensive commercial use of SOFC systems. Therefore diagnosis and prognosis are valuable tools that can contribute to raising the reliability of the system operation, efficient health management, increased durability and implementation of predictive maintenance techniques. Remaining useful life (RUL) prediction has been extensively studied in many areas like batteries and proton-exchange membrane fuel cell (PEM) systems, and a range of different approaches has been proposed. On the other hand, results available in the domain of SOFC systems are still relatively limited. Moreover, methods relying on detailed process models and models of degradation turned out to have limited applicability for in-field applications. Therefore, in this paper, we propose an effective, data-driven approach to predicting RUL where the trend of the health index is modelled by an adaptive linear model, which is updated at all times during the system operation. This allows for a closed-form solution of the probability distribution of the RUL, which is the main novelty of this paper. Such a solution requires no computational load and is as such very convenient for the application in ordinary low-cost control systems. The performance of the approach is demonstrated first on the simulated case studies and then on the data obtained from a long-term experiment on a laboratory SOFC system. From the tests conducted so far it turns out that, the quality of the RUL prediction is usually rather low at the beginning of the system operation, but then gradually improves while the system is approaching the end-of-life (EOL), making it a viable tool for prognosis.
Keywords
prognosis; linear trend modeling; solid oxide fuel cells; remaining useful life
Subject
Engineering, Control and Systems Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
