Abstract: The performance of the power battery will inevitably deteriorate with the use, which directly affects the performance and use of the electric vehicle. Predicting the remaining life of the power battery during use can determine the optimal maintenance and replacement timing of the power battery, thereby effectively extending the life of the power battery and increasing the driving range of the electric vehicle. Therefore, the extended particle filter algorithm is used to predict the remaining life of the power battery. First, carry out the cycle aging experiment of lithium ion power battery, and obtain the capacity attenuation data of its life cycle. Then, the battery capacity decay model is established by double exponential fitting method and its accuracy is verified. Finally, using the model parameters as the state quantity, the extended particle filter algorithm is used to estimate and update the model parameters in real time, and the number of remaining cycles and the credibility of the prediction results are obtained. The simulation results show that the prediction results of the remaining life of the power battery based on the extended particle filter algorithm are more accurate than those based on the standard particle filter.