A review on machine learning-based prognostics and health management for hydrogen fuel cells

Huixing Meng, Jiali Liang, Mengqian Hu, Fatemeh Salehi, Te Han,
A review on machine learning-based prognostics and health management for hydrogen fuel cells,
Journal of Loss Prevention in the Process Industries,
2025,
105833,
ISSN 0950-4230,
https://doi.org/10.1016/j.jlp.2025.105833.
(https://www.sciencedirect.com/science/article/pii/S0950423025002918)
Abstract: Due to their high efficiency, energy density, and zero-emission, hydrogen fuel cells are regarded as a promising energy scheme to alleviate environmental pollution. The reliability of fuel cells is crucial to their safety in life cycle. To accelerate the process of engineering application, it is significant to investigate prognostics and health management (PHM) methods for hydrogen fuel cells to improve their safety and reliability. PHM is an emerging discipline including state of health (SOH) estimation, remaining useful life (RUL) prediction and fault diagnosis. In the area of artificial intelligence, machine learning (ML) has been increasingly applied in PHM domain. Due to the strength of high accuracy and efficiency, ML-based PHM methods have promising application prospects in systems with complex data and multiple parameters like fuel cells. In this paper, we reviewed relevant literature in the field of ML-based PHM methods for hydrogen fuel cells mainly in the last ten years. Different algorithms present various functions such as modeling, data pretreatment, and optimization, and keep integrating and innovating to achieve optimal performance in addressing complex problems. However, in regard of the open issues that have not been solved, there remains extent for ML-based PHM to develop. We concluded future research directions in ML-based PHM methods for fuel cells, including uncertainty qualification, digital twin, generative models and prescriptive maintenance.
Keywords: Machine learning; Prognosis; Diagnosis; Prognostics and health management (PHM); Fuel cells; Hydrogen