Neural networks based adaptive predictors for nonlinear dynamical systems

Develops a novel predictive model based on multilayer neural networks for nonlinear dynamical systems. Two isomorphic multilayer neural networks are used together to implement the proposed predictor. One is the learning network which learns the input-output behavior of the system. The other is the prediction network, which gets its weights mapped from the learning network and generates the predicted estimate of the system output based on input signals prior in time to those of the learning network. Simulation results show that this neural-network-based adaptive predictor can deal with systems with a wide variety of characteristics involving large unknown nonlinearity, the presence of large time delay, and stochastic disturbance