Neural network sliding mode control based on improved fruit-fly optimization algorithm for permanent magnet synchronous motor systems

Abstract

Aiming at permanent magnet synchronous motor chaotic system, an equivalent control method of neural network sliding mode based on improved fruit fly optimization algorithm is proposed. When the output of the RBF neural network is used as the boundary layer of the sliding mode equivalent control, it overcomes the difficulty of selection the saturation function boundary layer and the chattering phenomenon in the traditional sliding mode equivalent control. The improved fruit fly optimization algorithm is applied to globally optimize the parameters of the sliding mode controller, so as to suppress the chaotic phenomenon of the permanent magnet synchronous motor more effectively. Simulation results show that this strategy has high control precision and rapid response speed.