Enhanced Performance of Permanent Magnet Linear Motors Under Uncertainties and Disturbances Using Fast Nonsingular Terminal Sliding Mode Control with Neural Network

This paper introduces a novel control strategy that integrates a fast nonsingular terminal sliding mode controller with an RBF neural network to improve the performance of permanent magnet linear motors amid uncertainties and external disturbances. Unlike conventional sliding mode control methods, the proposed approach integrates fast nonsingular terminal sliding mode control with a radial basis function neural network to improve convergence speed, effectively handle system uncertainties and external disturbances, and significantly reduce chattering phenomena. Stability analysis using a Lyapunov-based approach confirms the global finite-time convergence of the system to the desired trajectory. Simulation results demonstrate that the proposed control strategy performs better than conventional sliding mode controllers, offering faster response, improved robustness against disturbances, and smoother control signals. This method provides an advanced solution for high-precision and highperformance applications of permanent magnet linear motors in industrial automation.