Degradation Prediction of PEMFC Based on Data-Driven Method With Adaptive Fuzzy Sampling
Jiashu Jin, Yuepeng Chen, Changjun Xie, Fen Wu
Abstract
Durability is one of the concerns in the large-scale application of proton exchange membrane fuel cells (PEMFC). The objective of this paper is to propose a data-driven approach to achieve long-term prediction. Echo state network-cycle reservoir with jump (ESN-CRJ) is an extended network based on state echo network (ESN). ESN model is used to extract state information in reservoir and transmitted to CRJ for voltage prediction of stack. In addition, an adaptive fuzzy sampling (AFS) method is adopted to sample the training data in this paper. The degradation phenomenon is realized in the stack voltage drop, the place where the voltage drop is rapid contains more degradation information, which needs to be extracted more by the prediction model. Experimental results show that the ESN-CRJ with AFS can be an improvement of 22.02% in long-term prediction under the static current. Under the quasi-dynamic current, the long-term prediction accuracy can be an improvement of 25.06%. Consequently, the proposed approach can achieve well performance in the remaining useful life prediction.