基于GABP-NSGA-Ⅱ的开关磁阻电机系统级多目标优化设计  

A System-Level Multi-Objective Optimization Design for Switched Reluctance Motors Based on GABP-NSGA-II

作　　者：陈刚[1] 邓琪 CHEN Gang;DENG Qi(College of Electrical and Information Engineering,Hunan University of Technology,Zhuzhou Hunan 412007,China)

机构地区：[1]湖南工业大学电气与信息工程学院,湖南株洲412007

出　　处：《湖南工业大学学报》2024年第3期32-37,共6页Journal of Hunan University of Technology

基　　金：国家自然科学基金资助项目(62173136)。

摘　　要：为提升开关磁阻电机(SRM)的系统驱动性能,提出一种基于遗传算法(GA)优化反向传播(BP)神经网络和非支配排序遗传算法(NSGA-II)相结合的多目标优化设计方法,旨在降低其转矩脉动、提高其平均转矩和效率。通过灵敏度分析,选择对开关磁阻电机优化目标影响较大的3个本体参数(匝数、转子极弧系数、气隙)和两个控制参数(开通角、关断角)作为决策变量,采用有限元分析、GA-BP法建模和NSGA-II算法进行多目标寻优,得到最优解。仿真结果表明,运用GA-BP-NSGA-II优化设计方法对提升开关磁阻电机的系统驱动性能有显著效果。In view of an improvement of the system driving performance of Switched Reluctance Motors(SRM),a multi-objective optimization design method has thus been proposed with a combination of a genetic algorithm(GA)optimized back propagation(BP)neural network and non-dominated sorting genetic algorithm II(NSGA-II),so as to reduce its torque ripple and improve its average torque and efficiency.Based on a sensitivity analysis,three ontology parameters(turns,rotor pole arc coefficient,air gap)and two control parameters(turn on angle,turn off angle),which have a significant impact on the optimization objectives of SRM(switched reluctance motors),are selected as decision variables,followed by an application of the finite element analysis,GA-BP modeling,and NSGA-II algorithm for a multi-objective optimization to obtain the optimal solution.

关 键 词：开关磁阻电机 多目标优化 遗传算法优化反向传播神经网络 非支配排序遗传算法(NSGA-II) 

分 类 号：TM352[电气工程—电机]