Degradation model of proton exchange membrane fuel cell based on a novel hybrid method

Abstract

This paper proposes a new hybrid degradation model of Proton Exchange Membrane Fuel Cell (PEMFC) used in Fuel Cell Electric Vehicle (FCEV) operating under real conditions. This hybrid method is based on the wavelet analysis, Extreme Learning Machine (ELM) and Genetic Algorithm (GA). This new degradation model considers the influence of PEMFC load current, relative humidity, temperature, and hydrogen pressure. First, the wavelet analysis is used to decompose the voltage aging waveform of PEMFC into multiple sub-waveforms. Second, the ELM is applied to build the degradation model of each sub-waveform. Then, the overall degradation model of PEMFC is obtained by combining the degradation model of each sub-waveform. Finally, GA is adopted to improve the global optimization of the proposed degradation model. This model is experimentally validated by using actual data from 3 PEMFCs in 3 FCEVs carrying out postal mail delivery missions in the field. The results show that the proposed hybrid method can get higher accuracy than several traditional approaches.