To improve the prediction accuracy of the remaining useful life (RUL) of the proton exchange membrane fuel cell (PEMFC), an integrated health index (IHI) including electrical and non-electrical parameters of PEMFC is established, and the RUL prediction is conducted based on the above index. Firstly, several operating conditions including the PEMFC degradation information are selected according to the information theory method. Moreover, the IHI is established by the sequential quadratic programming method. Secondly, RUL predictions based on the power and IHI are conducted by the adaptive neuro fuzzy inference system (ANFIS), respectively. Finally, different results comparisons including power and IHI differences, differences between experimental and training/predicting results, amounts of different differences in training and predicting phases, and RUL prediction results are presented in detail. The results show that the accuracy of the RUL prediction based on the IHI is higher than that based on the power. The accuracy at the time of 654 h of the ANFIS based on the IHI is improved by 40.8% and 30.4% compared with the linear fitting and ANFIS based on the power, respectively.
