一种开关磁阻电机建模方法的研究与实现  

Research and Implementation of a Switched Reluctance Motor Modeling Method

作　　者：刘杰[1] 秦晓飞[1] 李峰[1] LIU Jie QIN Xiao-fei LI Feng(School of Oplical-Electrical and Computer Engineering, University of Shanghai for Science and Technology)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093

出　　处：《测控技术》2017年第6期84-87,91,共5页Measurement & Control Technology

基　　金：上海高校青年教师培训资助计划(ZZS115008)

摘　　要：由于开关磁阻电机的非线性特点,难以建立一个精确的开关磁电机的模型,为了精准建立开关磁阻电机模型,利用径向基函数神经网络良好的非线性映射能力在获取准确磁链样本数据基础上训练神经网络,利用训练的径向基神经网络构建开关磁阻电机非线性模型。在此基础上,采用角度位置控制和电压脉宽调制控制相结合的方法搭建开关磁阻电机驱动控制系统的仿真框架。仿真结果表明:利用径向基函数神经网络的方法可以克服开关磁阻电机的非线性问题,所建立的开关磁阻电机模型可以正常稳定运行。从而证明上述方法的合理有效性。Because of the non-linearity,it is difficult to establish a precise model of the switched magneto-electrical machine.In order to establish the switched reluctance motor（SRM） model accurately,based on the radial basis function（RBF） neural network,the neural network is trained on the basis of obtaining the accurate flux data,and the non-linear model of the SRM is constructed by using the trained RBF neural network.On this basis,a simulation framework of SRM drive control system is built by combining angle position control and voltage pulse-width modulation control.The simulation results show that the RBF neural network can overcome the nonlinear problem of SRM,and the SRM model can run normally and stably.The rationality and validity of the above methods are proved.

关 键 词：开关磁阻电机 非线性 径向基函数神经网络 角度位置控制 脉宽调制 

分 类 号：TM351[电气工程—电机]