Neural inverse optimal control for a linear induction motor

Abstract

This paper presents a discrete-time inverse optimal control for trajectory tracking applied to a three-phase linear induction motor (LIM). An on-line neural identifier, which uses a recurrent high-order neural network (RHONN) trained with the Extended Kalman Filter (EKF), is employed in order to build a mathematical model for the nonlinear system. This model is in the Nonlinear Block Controller (NBC) form. The control law calculates the input voltage signals, which are inverse optimal in the sense that they minimize a cost functional without solving the Hamilton Jacobi Bellman (HJB) equation. The applicability of the proposed control scheme is illustrated via simulation.