基于RBF网络和MRAS的鱼雷永磁同步电机无速度传感器控制方法

Speed-Sensorless Control Method of Torpedo PMSM Based on RBF and MRAS

为提高鱼雷永磁同步电机(PMSM)控制系统性能,提出了一种基于径向基函数(RBF)网络和模型参考自适应系统(MRAS)的鱼雷PMSM无速度传感器控制方法,用于鱼雷PMSM无速度传感器矢量控制系统的转速估计。该方法选取PMSM本身作为参考模型,PMSM电流模型作为可调模型,仅利用q轴的估算电流与实际电流之差作为误差信号,将误差信号送入RBF网络进行调节后得到估计转速。仿真试验结果表明,该方法在低速和调速时均能准确检测到转子的速度,具有良好的静动态运行性能。

To improve the performance of the permanent magnet synchronous motor（PMSM） control system, this paper presents a method based on model reference adaptive system（MRAS） and radial basis function （RBF） network for rota- tional speed estimation of torpedo PMSM speed-sensorless vector control system. This method selects PMSM as the reference model, and selects current model of PMSM as the adjustable model. It only needs the q-axis error signal be- tween estimated current and actual current, then sends the error signal into the RBF network for adjustment, hence the estimated rotational speed is gained. Simulation indicates that the present method can obtain precise estimation of the rotational speed under the condition of low speed or speed regulation, and has good static and dynamic performances.