Method for predicting degradation of proton exchange membrane fuel cell

The invention discloses a proton exchange membrane fuel cell recession prediction method, which is based on a recession prediction model combined with a Gini Gamma correlation coefficient and an improved salat group LSTM algorithm, and takes a relative voltage loss rate as a dynamic health index, so as to make up the defects of the existing proton exchange membrane fuel cell recession prediction algorithm. And the degradation of the proton exchange membrane fuel cell can be accurately and rapidly predicted. According to the method, the voltages corresponding to different load currents are processed, the health indexes of the dynamic working condition are obtained by calculating the relative voltage loss rate, and higher accuracy is achieved. According to the method, a Gini Gamma correlation coefficient which is more suitable for processing nonlinear system correlation is adopted for extraction. According to the method, the LSTM is optimized by adding the Levy flight algorithm on the basis of the traditional S