Fast Nonsingular Terminal Sliding Control for Permanent Magnet Linear Motor via Extreme Learning Machine Estimator

This paper proposes a novel extreme-learning-machine-based fast nonsingular terminal sliding mode (FNTSM) control strategy for permanent magnet linear motor (PMLM) with partially known dynamics. The proposed control strategy consists of two components: a FNTSM controller, and an estimator based on extreme learning machine (ELM), which is implemented to estimate the equivalent control of the FNTSM control. Compared with conventional sliding mode control implemented, the proposed control strategy not only assures the finite-time error convergence and strong robustness, but also requires no prior knowledge of the system parameters since the ELM is used to estimate the equivalent control in the process of designing controller. Numerical simulation results are given to verify excellent tracking performance of the proposed control strategy and show its advantages over some existing approaches.