The interior permanent magnet synchronous motor (IPMSM) has the advantages of high power density, wide speed range and high efficiency, so it is widely used in new energy vehicles. In this paper, an IPMSM model is used as the research object, and a multi-objective optimization method based on an artificial neural network (ANN) surrogate model is proposed to address the problems of long computation time and low optimization efficiency due to multiple finite element analysis iterations in the multi-objective optimization process. Taking the average torque and torque ripple of the IPMSM as the optimization objectives and part of the rotor structure parameters as the optimization variables, the ANN surrogate model is used to construct the relationship between the optimization variables and the optimization objectives, and the NSGA-Ⅱ is used for the multi-objective optimization design of the IPMSM. Finally, the correctness of the multi-objective optimization method based on ANN surrogate model proposed in this paper is verified by the finite element analysis results.