Using radial basis function neural network for PMSM to overcome the changing load

Abstract

This paper presents a using Radial Basis Function Neural Network (RBFNN) for PMSM to overcome the changing load. Firstly, a mathematic model of the PMSM drive is derived; then, to increase the performance of the PMSM drive system, a Fuzzy PI controller in which an RBFNN adjusts its parameters is applied to the speed controller for coping with the effect of the system dynamic uncertainty and the external load. Secondly, the Very high-speed integrated circuit Hardware Description Language (VHDL) is adopted to describe the behaviour of the speed control IC which includes the circuits of space vector pulse width modulation (SVPWM), coordinate transformation, RBFNN, and Fuzzy PI. Thirdly, the simulation work is performed by MATLAB/Simulink and ModelSim co-simulation mode, provided by Electronic Design Automation (EDA) Simulator Link. The PMSM, inverter, and speed command are performed in Simulink, and the speed controller of the PMSM drive is executed in ModelSim. Finally, the co-simulation results validate the effectiveness of the proposed algorithm based speed control system