基于多目标遗传算法的表贴式无轴承永磁电机优化设计

Optimized Design of the Bearing-less Surface-mounted Permanent Magnet Motor Based on Multi-Objective Genetic Algorithm

为了改善表贴式无轴承永磁电机的悬浮力和转矩的性能,提出了一种结合多目标遗传算法的响应面法,对电机结构进行优化设计。首先,构建优化目标的响应面,并得到优化目标的回归方程;其次,利用多目标遗传算法对优化目标的回归方程进行寻优,得到了理想的悬浮力、悬浮力脉动和转矩;最后,对多目标优化得出的最优结果进行有限元分析,验证了该优化算法的可行性。

In order to improve the suspension force and torque performance of the bearing-less surface-mounted permanent magnet motor,a kind of response surface method combined with the multi-objective genetic algorithm is proposed,to optimize the motor structural design.First,the response surface of the optimization objective is established and the regression equation of the optimization objective is obtained.Secondly,seeking excellence for the regression equation of the optimization target is performed by using the multi-objective genetic algorithm,to achieve the ideal suspension force,suspension force pulsation and torque.Finally,the optimal results of the multi-objective optimization are analyzed by finite element analysis,to verify the feasibility of the optimization algorithm.