摘要
建立了爪极发电机的三维有限元模型,对其漏磁进行了深入的分析。通过电机参数样本空间设计,利用支持向量机对爪极发电机的漏磁系数进行非线性回归建模分析,然后基于混沌理论对爪极发电机结构参数进行优化。仿真结果表明,支持向量机用于爪极发电机非参数建模准确可行,并且是高效的,非常适合于需要大规模迭代计算的参数优化。将有限元电磁仿真与支持向量机结合用于非参数建模,以及在非参数模型的基础上用混沌进行优化,为爪极发电机及其它的电磁工程设计提供了一种新的思路。
Three dimension finite element model （3D-FEM） of the claw-pole alternator is presented in this paper, and the leakage is analysed in detial. By designing the sample space of the parameters, nonlinear regression modeling of the claw-pole alternator based on support vector machines （SVM） is introduced. Parameters optimization of the claw-pole al{ernator is also introduced which is based on chaos. Simulation results prove that the nonparametric modeling based on SVM is feasible and high efficiency, and it is very fit for the parameters optimization which needs large-scale iterative calculating. Using the integration of FEM and SVM to nonparametric modeling, and parameter optimization based on it provide a novel way for the optimum design of the claw-pole alternator and other engineering.
出处
《中国电机工程学报》
EI
CSCD
北大核心
2006年第21期138-142,共5页
Proceedings of the CSEE
基金
国家自然科学基金项目(50077005)~~
关键词
爪极发电机
三维有限元
支持向量机
漏磁系数
混沌
claw-pole alternator
three dimension finite element model
support vector machines
leakage coefficient
chaos
作者简介
鲍晓华（1972-）,男,湖北麻城人,博士研究生,研究方向为汽车发电机优化设计,xiaohua1972@163.com
王群京（1960-）,男,安徽蚌埠人,教授,博士生导师,研究方向为特种电机及其控制.
