Research of proton exchange membrane fuel cell degradation index and prediction method for automotive vehicles

Comprehensively describing proton exchange membrane fuel cell (PEMFC) degradation behavior and accurately predicting degradation under dynamic operating conditions have become a prerequisite for automotive PEMFC health maintenance and life extension control. In this paper, a PEMFC comprehensive degradation index that incorporates time-varying physical parameters with multi-scale degradation information is proposed. The nonlinear degradation tendency of exchange current density at dynamic operating conditions is considered in this index. Then a Holt-Winters convolutional neural network (H-W CNN) prediction framework is proposed. The PEMFC reversible degradation features are enhanced by the Holt-Winters smoothing algorithm and a multivariate CNN model is constructed to conduct PEMFC multi-step degradation prediction under insufficient degradation data. Experimental result shows that the degradation index can characterize the comprehensive degradation of PEMFC under dynamic operating conditions. For mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) under 3 h prediction horizon, the H-W CNN prediction framework improves the performance by 38.8%, 38.4%, 37.9% compared to echo state network (ESN). Under 15 to 45 h prediction horizon, the H-W CNN demonstrates better learning potential for PEMFC reversible degradation and degradation trend prediction ability compared with long short-term memory networks (LSTM), ESN d univariate CNN models.