| 磁悬浮开关磁阻电机多目标优化设计 |
| |
| 引用本文： | 孙玉坤,袁野,黄永红,胡文宏,项倩雯,周云红.磁悬浮开关磁阻电机多目标优化设计[J].电机与控制学报,2016(11):32-39. |
| |
| 作者姓名： | 孙玉坤 袁野 黄永红 胡文宏 项倩雯 周云红 |
| |
| 作者单位： | 1. 南京工程学院 电力工程学院,江苏 南京,210000;2. 江苏大学 电气信息工程学院,江苏 镇江,212013 |
| |
| 基金项目： | 国家自然科学基金(51377074;51307077)，江苏省优势学科建设工程资助项目，江苏省青年科学自然基金(BK20150510;BK20150524)，江苏大学研究生创新工程项目(KYXX_0002) |
| |
| 摘 要： | 研究了一种基于极限学习机(extreme learning machine,ELM)与带精英策略非支配排序遗传算法(improved non-dominated sorting genetic algorithm,NSGA-II)的单绕组磁悬浮开关磁阻电机(single winding bearingless switched reluctance motor,SWBSRM)多目标优化设计方法。结合有限元分析(finite element analysis,FEA),分析了SWBSRM悬浮力、转矩随各结构参数变化的一般规律,得到ELM非参数模型。针对该训练模型并结合NSGA-II进行全局寻优,获得使悬浮力、转矩同时更优的结构参数数值组合。通过对比优化前后电机输出悬浮力、转矩大小,验证了以ELM、NSGA-II为基础的SWBSRM结构多目标优化设计的有效性。
|
| 关 键 词： | 单绕组磁悬浮开关磁阻电机 多目标优化设计 极限学习机 带精英策略非支配排序遗传算法 |
Multi-objective optimal design of single winding bearinglessswitched reluctance motor |
| |
| Abstract: | A novel approach was studied using Extreme Learning Machine and Non-dominated Sorting Ge-netic Algorithm was improved to achieve the multi-objective optimal design of single winding bearingless switched reluctance motor. General rules of radial force and average torque due to the various structure parameters were given based on finite element analyses ( FEA) , and the ELM non-parametric model of SWBSRM was obtained. The improved Non-dominated Sorting Genetic Algorithm was used to search for optimal solution, by which radial force and average torque were improved simultaneously. The proposed optimal design was verified by comparing the performance of the optimized motors with the original. |
| |
| Keywords: | single winding bearingless switched reluctance motor multi-objective optimal design extreme learning machine improved non-dominated sorting genetic algorithm |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
