摘要
内置式永磁同步电机(IPMSM)因其具有高功率密度、宽调速范围和高效率等优点,被广泛应用于新能源汽车中。本文以一台IPMSM模型为研究对象,针对多目标优化过程中多次有限元迭代导致的计算时间长和优化效率低的问题,提出一种基于人工神经网络(ANN)代理模型的多目标优化方法。以电机的平均转矩和转矩脉动为优化目标,将转子相关结构参数作为优化变量,使用ANN代理模型构建优化变量和优化目标的映射关系,并采用非支配排序遗传算法(NSGA-Ⅱ)对电机进行多目标优化设计。最后,通过有限元仿真分析证明了本文提出的基于ANN代理模型的多目标优化方法的正确性。
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.
作者
徐晔鎏
贾广隆
张凤阁
XU Yeliu;JIA Guanglong;ZHANG Fengge(School of Electrical Engineering,Shenyang University of Technology,Shenyang 110870)
出处
《电气技术》
2023年第5期23-29,共7页
Electrical Engineering
