For the problem of remaining life prediction of fuel cell system, a method for remaining life prediction of fuel cell system based on Wiener process and Bayesian method is proposed. The method is based on the Wiener process and utilizes historical data to obtain the characteristic trends of fuel cells and establish a degradation model and estimate unknown parameters using the maximum likelihood estimation method. Based on the degradation model, the real-time condition data of the system is then incorporated to update the model parameters and predict the remaining life of the system. Simulation results demonstrate that this approach can predict the fuel cell voltage trend with low error, and the decay trend aligns well with historical data.