Efficient health indicators for the prediction of the remaining useful life of proton exchange membrane fuel cells

Abstract

Proton Exchange Membrane Fuel Cells (PEMFCs) are devices that convert hydrogen into energy through a chemical process called electrolysis. They hold promise in reducing the harmful environmental effects of fossil fuels and could potentially replace current energy systems in the near future if certain challenges are overcome. One major challenge in Proton Exchange Membrane Fuel Cell (PEMFC) performance is its durability. This issue, although common in many industrial assets, holds even more significance in PEMFCs due to their high costs and the need for reliable operation. Predictive Maintenance (PM), as a part of Prognostic and Health Management (PHM), focuses on addressing the durability problem by predicting the Remaining Useful Life (RUL) of PEMFCs. In this study, machine learning was used to predict the RUL of a stack of five PEMFCs operating under both static and quasi-dynamic conditions, resulting in two distinct datasets. Multiple health indicators were tested by combining domain expertise and the characteristics of PEMFC data to estimate the RUL.The results reveal that the power-time fraction health indicator accurately predicted the RUL in the static regime with an impressive R2 value of 99% and an RMSE error of 4.59e-07, using the random forest regressor. This analysis was also extended to the quasidynamic regime for validation, achieving an R2 of 95% and an RMSE of 0.06, which demonstrates the strong potential of this health indicator. Additionally, Explainable AI was employed for the first time in this context to enhance the transparency of the results. This work serves as an excellent starting point for further exploration of new health indicators and highlights the power of machine learning in addressing the crucial issue of predicting the RUL of PEMFCs.