Optimal design for Flux-intensifying Permanent Magnet Machine Based on Neural Network and Multi-objective optimization

Abstract

The optimization of flux-intensifying interior permanent magnet motor with the reverse salient rotor for electric vehicles is considered and explained. Firstly, the size parameters of an initial motor are selected and then the finite element model is established based on parametric variables. Secondly, to avoid the frequent usage of finite element analysis, a well-trained back propagation neural network model is used to replace the finite element model. Thirdly, the sequential unconstrained minimization technique and non-dominated sorting genetic algorithm-II algorithm are combined together to solve the multi-objective optimization solution with inequality constraints. Finally, the electric machine is reconstructed based on the optimal parameters extracted from Pareto front. The effectiveness of proposed approach is verified by the simulation results.