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

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.