PWM整流器的径向基函数神经网络控制新方法

A New Control Method Based on Radial Basis Function Neural Network for PWM Rectifier

摘要: 提出了一种用于PWM单位功率因数整流器的神经网络（neural network，NN）控制方法．运用预测电流对电压型PWM整流器的有功、无功电流实现解耦，电压环采用基于径向基函数（radial basis function，RBF）神经网络自适应调整参数的PI控制器．仿真结果表明，这种PI控制器可以在线调整PI参数，快速跟踪整流器的变化过程，使PWM整流器获得较好的动、静态特性，并对电网负载扰动有较强的适应能力．

Abstract: A control method based on neural network(NN)for PWM rectifier with unity power factor is presented.In a voltage source PWM rectifier,predictive current is adopted to decouple the active and reactive current flow of the rectifier,and an adaptive PI controller based on radial basis function neural network(RBFNN)is used in the voltage loop to adjust the parameters.Simulation results show that the controller built in the paper is able to adjust the PI parameters online,trace the changing process of the rectifier quickly,and consequently the PWM rectifier has good dynamic and static performances,and high adaptability for the power supply and load disturbances.