A multi-scale hybrid degradation index for proton exchange membrane fuel cells

Abstract

An accurate degradation index can help users understand the aging state of proton exchange membrane fuel cells and take appropriate maintenance measures to improve durability. The degradation of membranes and electrodes is one of the most important causes leading to the performance degradation of proton exchange membrane fuel cells. This paper proposes a multi-scale hybrid degradation index that combines the degradation of membranes and electrodes to estimate the aging state of proton exchange membrane fuel cells. Firstly, different degradation models are utilized to estimate the degradation indexes such as average radius of Pt particles, electrochemical surface area, and membrane thickness. A multi-sale hybrid degradation index is then designed to fuse all the previous indexes based on the quantified effects of electrode and membrane degradation. Finally, based on the automatic machine learning algorithm and the aging experimental data of proton exchange membrane fuel cells, the proposed hybrid degradation index is verified. Experimental results show that the proposed hybrid degradation index can accurately predict the future aging states and the remaining useful life of proton exchange membrane fuel cells.