Sensors fusion for faults detection in plants: a case study of PEM electrolyser
DOI:
https://doi.org/10.17979/ja-cea.2025.46.12137Keywords:
Sensor fusion, Faults detection, Fuzzy logic, PEM electrolyserAbstract
Control systems are often equipped with fault detection sub-systems which utilise signals from sensors to detect abnormalities in the plant. However, when the sensor itself fails, the fault may escape undetected, and failure will occur. To solve this problem, the concept of sensor data fusion can be utilised to fuse signals from one sensor with another one within the system and the resulting fusion can be used for fault detection. The fusion of different but correlated signals can give better information about a potential fault rather than relying on signal from only one sensor in the plant. This situation ensures that even when sensors fail, faults can be detected. The benefit of the proposed solution is demonstrated in a real case with a 1 Nm3/h-H2 PEM electrolyser.
References
Abiola, A., Manzano, F.S., Andújar, J.M., 2023. A Novel Deep Reinforcement Learning (DRL) Algorithm to Apply Artificial Intelligence-Based Maintenance in Electrolysers. Algorithms 16. https://doi.org/10.3390/a16120541
Bessarabov, D., Millet, P., 2018. Fundamentals of Water Electrolysis. PEM Water Electrolysis. Elsevier, 43–73. https://doi.org/10.1016/b978-0-12-811145-1.00003-4
Caparrós, J.J., Vivas, F.J., Segura, F., Andújar, J.M., 2021. Optimized Balance of Plant for a Medium-size PEM Electrolyzer. SNE Simulation Notes Europe 31, 133–141. https://doi.org/10.11128/sne.31.tn.10574
Galar, D., Kumar, U., 2017. Sensors and Data Acquisition. EMaintenance. Elsevier, 1–72. https://doi.org/10.1016/b978-0-12-811153-6.00001-4
Kheirrouz, M., Melino, F., Ancona, M.A., 2022. Fault detection and diagnosis methods for green hydrogen production: A review., International Journal of Hydrogen Energy. https://doi.org/10.1016/j.ijhydene.2022.06.115
Masali, M.H., I, R.B., Zargarzadeh, H., 2024. Sensor Fusion for Incipient Hydrogen Detection Using Deep Learning. International Journal of Research Publication and Reviews 5. https://doi.org/10.55248/gengpi.5.0924.2419
Mouzakitis, A., 2013. Classification of fault diagnosis methods for control systems. Measurement and Control (United Kingdom) 46, 303–308. https://doi.org/10.1177/0020294013510471
Ross, E.A., Wagterveld, R.M., Stigter, J.D., Mayer, M.J.J., Keesman, K.J., 2023. Sensor data fusion in electrochemical applications: An overview and its application to electrochlorination monitoring., Computers and Chemical Engineering. https://doi.org/10.1016/j.compchemeng.2022.108128
Vélez, M.Á., Sánchez, O., Romero, S., Andújar, J.M., 2010. A new methodology to improve interpretability in neuro-fuzzy TSK models. Applied Soft Computing Journal 10, 578–591. https://doi.org/10.1016/j.asoc.2009.08.027
Wang, J., Yang, Z., Chen, K., Zhou, D., 2017. Practices of detecting and removing nuisance alarms for alarm overloading in thermal power plants. Control Engineering Practice 67, 21–30. https://doi.org/10.1016/j.conengprac.2017.07.003
Zhong, Y., Yang, Y., Diao, L., Song, K., Li, R., Yao, N., Ma, T., Lin, W., 2024. Design of multi-sensor fusion water state observer for proton exchange membrane fuel cell based on particle filter. Energy Conversion and Management 320. https://doi.org/10.1016/j.enconman.2024.118978
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Abiodun Abiola, Francisca Segura, José Manuel Andújar, Javier Barragán
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
