Echo state network-based model reference adaptive predefined time control for magnetic levitation linear synchronous motor

To enhance the transient performance and robustness of a magnetic levitation linear synchronous motor, this paper proposes an echo state network (ESN)-based model reference adaptive predefined-time control. The proposed preset time speed error reference model enables users to define the decay rate of the tracking error and the convergence time required for the speed error to reach zero. The ESN is employed to compensate for mismatched unknown disturbances, and to expedite the convergence of the ESN, a predefined-time adaptation law is designed. By integrating predefined-time stability theory with model reference adaptive control, a model reference adaptive predefined-time speed tracking controller is developed, where the convergence time is determined by a single tunable parameter and independent of the initial conditions of the system state. Theoretical analysis demonstrates that the error between the actual tracking error and the reference model output converges to a neighborhood around the origin within the predefined time. Finally, simulation results validate the efficacy and superiority of the proposed controller in achieving robust and fast transient performance.