Design Optimization of PMSM for Electric Vehicles Based on an Intelligent Surrogate Model Selection Method

To optimize the performance of permanent magnet synchronous motor (PMSM), a multidisciplinary design optimization (MDO) method is proposed which considers both motor structure and controller design. Surrogate models are constructs to save computing resources and accelerate the optimization process. In order to solve the problem that the selection of surrogate model depends heavily on the experience of engineers, an intelligent surrogate model selection method (ISMSM) is proposed to obtain a proper surrogate model. Based on ISMSM and the MDO method, the PMSM design parameters are optimized, and the results show a significant improvement in overall performance.