The invention relates to a fuel cell, and discloses a proton exchange membrane fuel cell model optimizing process method. According to the technical scheme of the invention, structural parameters of a fuel cell are inquired at first, then working parameters and output voltages under different output currents of the fuel cell are measured by instruments, after the mean value of error sum of squares of the estimated output voltages of a fuel cell model and actually-measured output voltages is defined as an objective function for optimal modeling, model parameters are obtained by an optimization technique, and the model is provided for researching the proton exchange membrane fuel cell. The model obtained by the method is higher in precision and stronger in stability. When modeling is performed repeatedly for multiple times, all of the optimal value, the worst value, the mean value, and the standard deviation of the objective function values of the model are smaller, wherein the optimal value, the worst value, the mean value represent the precision of the model, and the standard deviation represents the stability of the model. When modeling is performed for the proton exchange membrane fuel cell by the method, better convergence is achieved.