基于LSSVM逆系统的磁悬浮开关磁阻电机转子位置检测

Position Detection of Bearingless Switched Reluctance Motor Based on LSSVM Inversion System

为提高磁悬浮开关磁阻电机(BSRM)角度位置的检测精度,实现其高性能无传感器控制,提出一种基于最小二乘支持向量机(LSSVM)左逆系统的转子位置软测量方法。将BSRM的数学模型进行状态空间变换,根据逆系统理论构造转子位置的左逆软测量模型,由于BSRM模型具有高度非线性及不确定性,采用LSSVM辨识左逆软测量模型,实现BSRM转子位置的检测。仿真试验结果表明,所构造的软测量模型能够较为实时准确地估计出BSRM转子位置。

To improve the detection precision of angle position and realize the sensorless control for bearingless switched reluctance motors （ BSRM ） , a soft sensing method for rotor position is proposed by using least squares support vector machine （ LS-SVM ） based on left inversion system theory. The mathematical model of BSRM is transformed in state space. And then the rotor position soft sensing model is designed by left inversion soft sensing theory. Due to the nonlinearity and uncertainty, LSSVM is used to identify left inversion soft sensing model and implement the detection of BSRM rotor position. The numerical simulations show the proposed soft sensing model can achieve real-time and accurate rotor position detection.