感应电机矢量控制系统的神经网络转速辨识

Speed Identification of Vector Controlled Induction Motor Using Neural Networks

在给定的无速度传感器感应电机间接矢量控制系统中,利用基于BP算法的两层神经网络,根据期望状态与实际状态之间的偏差来调整神经网络模型的权值,达到实时辨识电机转速的目的。该方法简单、直观,不仅利用了神经网络的优点,又能适应感应电机调速系统实时控制的要求。仿真结果验证了该方法的有效性。

An indirect vector control strategy of speed sensorless induction motor is given in this paper. The two - layered back - propagation neural network technique is used to provide a real time speed estimation of the induction motor. The error between the desired state variable and the actual state variable is back propagated to adjust the weight of the neural model, and then the speed can be identified exactly. The algorithm is simple and intuitionistic, it can not only take advantage of neural net- works, but fit the demands of the real time control of the induction motor. The simulation results show that the system is effective.