Real-Time Output Trajectory Tracking using a Discrete Neural Backstepping Controller

Abstract

This paper deals with adaptive tracking for discrete-time MIMO nonlinear systems in presence of bounded disturbances. A high order neural network (HONN) structure is used to approximate a control law designed by the backstepping technique, applied to a block strict feedback form (BSFF). The learning algorithm for the HONN is based on an Extended Kalman Filter (EKF). This paper also includes the respective stability analysis, using the Lyapunov approach. The proposed scheme is implemented in real-time to control a three phase induction motor, as to track a time-variying speed reference and a constant flux magnitude reference.