On-line identification and adaptive trajectory tracking for nonlinear stochastic continuous time systems using differential neural networks

Identification of nonlinear stochastic processes via differential neural ne tworks is discussed. A new "dead-zone" type learning law for the weight dyn amics is suggested. By a stochastic Lyapunov-like analysis the stability co nditions for the identification error as well as for the neural network wei ghts are established. The adaptive trajectory tracking using the obtained n eural network model is realized for the subclass of stochastic completely c ontrollable processes linearly dependent on control. The upper bounds for t he identification and adaptive tracking errors are established, (C) 2001 El sevier Science Ltd. All rights reserved.