Neural net backlash compensation with Hebbian tuning using dynamic inversion

A dynamic inversion compensation scheme is presented For backlash. The comp ensator uses the backstepping technique with neural networks (NN) For inver ting the backlash nonlinearity in the Feedforward path. Instead of a deriva tive, which cannot be implemented. a filtered derivative is used. Full rigo rous stability proofs are given using filtered derivative. Compared with ad aptive backstepping control schemes, we do not require the unknown paramete rs to be linear parametrizable. No regression matrices are needed. The tech nique provides a general procedure for using NN to determine the dynamic pr einverse of an invertible dynamical system. A modified Hebbian algorithm is presented for NN Tuning which yields a stable closed-loop system. Using th is method yields a relatively simple adaptation structure and offers comput ational advantages over gradient descent based algorithms. (C) 2001 Elsevie r Science Ltd. All rights reserved.