摘要
提出了一种基于扩展径向基函数(RBF)神经网络的动态模糊神经网络(D-FNN)的开关磁阻电机无位置传感器控制的新方法。动态模糊神经网络系统以在线采样的相绕组的电流和磁链为输入,以转子位置角度为输出,从而建立起电流和磁链、转子位置角度的非线性映射关系;训练完成后,用D-FNN输出结果取代位置传感器角度信号,实现电机无位置传感器运行。仿真和实验结果表明:由D-FNN获得的角度信号和由位置传感器获得的角度信号相比误差小,电机能够准确换相,且输出转矩波动小,转速曲线平滑,电机在无位置传感器下运行良好。
A new approach for the position sensorless control of the switched reluctance motor (SRM) using dynamic fuzzy neural network (D-FNN) is presented. D-FNN establishes the nonlinear mapping with the input based on the winding line current and flux linkage and the output based on the angle of the rotor position. When training is completed, D-FNN output results replace the angle signal of position sensor and realize the SRM position sensorless operation. The simulation and experimental results show that there is tiny error of switching signals between estimation and reality. The SRM can operate with little torque fluctuation and slight speed vibration.
出处
《传感器与微系统》
CSCD
北大核心
2011年第1期66-69,89,共5页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(50977080)
关键词
开关磁阻电机
动态模糊神经网络
无位置传感器
转子位置检测
switched reluctance motor ( SRM )
dynamic fuzzy neural network (D-FNN)
position sensorlesscontrol
rotor position detection