基于改进WOA优化BP神经网络的车用PMSM参数辨识

基于改进WOA优化BP神经网络的车用PMSM参数辨识

Vehicle PMSM Parameter Identification Based on Optimization of BP Neural Network by Improved WOA

Permanent magnet synchronous motor (PMSM) is widely used in new energy vehicles and other fields, and its precise control mostly depends on accurate motor parameters. The improved whale optimization algorithm (WOA) is used to optimize the initial weights and thresholds of BP neural network. Based on the improved BP neural network, a high-precision PMSM parameter identification method is proposed, which realizes the parameter identification of PMSM stator resistance, d-axis inductance, q-axis inductance and flux linkage. The simulation results show that, compared with traditional BP neural network and BP neural network method optimized by traditional WOA algorithm, the proposed method has higher identification accuracy, and the identification errors of the four parameters are all less than 2%. The effectiveness of the method is further verified on the experimental platform.