Fractional Order Complementary Non-singular Terminal Sliding Mode Control of PMSM Based on Neural Network

Abstract

Aiming at the sensitivity problems of uncertain factors such as parameter variation, external disturbance and friction for the permanent magnet synchronous motor control system of electric vehicle, a fractional order complementary non-singular terminal sliding mode control method based on neural network is proposed. The mathematical model of permanent magnet synchronous motor with uncertain factors was established. The sliding mode controller was designed by combining the generalized sliding mode surface and the complementary sliding mode surface, which shortened the arrival time from the state trajectory to sliding mode surface. The fractional calculus operator with filtering characteristics was used to improve the position tracking accuracy and reduce the chattering. As for the variety of uncertain disturbances, the neural network was used to estimate the system total uncertainty and compensate online to further improve the dynamic response ability and anti-interference ability. Finally, the simulation results verify the effectiveness and feasibility of the proposed method, which can provide theoretical and technical support for improving the control accuracy of permanent magnet synchronous motor and the development of electric vehicles.