环形绕组结构开关磁阻电机自选相神经网络无位置传感器控制方法  

Position Sensorless Control Method of Neural Network with Automatic Input Phase Selection for SRM with Toroidal Winding Structure

作　　者：邵明志 陈燕[1] 孙海涛[1] 朱银羿 王瑞浩 赵振宇 SHAO Mingzhi;CHEN Yan;SUN Haitao;ZHU Yinyi;WANG Ruihao;ZHAO Zhenyu(School of Electrical and Power Engineering,Taiyuan University of Technology,Taiyuan Shanxi 030024,China)

机构地区：[1]太原理工大学电气与动力工程学院,山西太原030024

出　　处：《电子器件》2024年第5期1261-1267,共7页Chinese Journal of Electron Devices

基　　金：山西省科技厅基础研究计划项目(20210302124327);山西省省筹资金资助回国留学人员科研项目(2022-065)。

摘　　要：针对环形绕组结构开关磁阻电机单相采用神经网络角度估计时,转子角度的某些位置估计误差较大的问题,提出了一种适用于环形绕组结构开关磁阻电机的自选相神经网络无位置传感器控制方法。该方法通过分析神经网络拟合的特点,结合转子位置的对称性,采取神经网络输入量优化和电感分区等措施,减小了转子估计误差,实现了对转子位置的准确估计。最后通过仿真验证了所提方法的有效性。In order to solve the problem that some position estimation errors of rotor angle are large when single-phase neural network angle estimation of switched ReLUctance motor with ring winding structure is adopted,a self-selected phase neural network sensorless control method for switched ReLUctance motor with ring winding structure is proposed.By analyzing the characteristics of neural network fitting and combining with the symmetry of rotor position,measures such as optimizing the input of neural network and inductance partition are adopted,which reduce the estimation error of rotor and realize the accurate estimation of rotor position.Finally,the effectiveness of the method is verified by simulation.

关 键 词：开关磁阻电机 环形绕组结构 神经网络 无位置传感器控制 

分 类 号：TM352[电气工程—电机]