Neural Networks for Non-Linear Dynamic System Modelling and Identification

摘要

Many real world systems exhibit complex nonlinear characteristics and cannot betreated satisfactorily using linear systems theory. A neural network which has the ability to learn sophisticated nonlinear relationships provides an ideal means of modeling complicated nonlinear systems. The issues related to the identification of nonlinear discrete time dynamic systems using neural networks are addressed. The network architectures, namely the multilayer perceptron, the radial basis function network, and the functional link network are presented and several learning or identification algorithms are derived. Advantages and disadvantages of these structures are discussed and illustrated using simulated and real data. Particular attention is given to the connections between existing techniques for nonlinear stystems identification and some aspects of neural network methodology; this demonstrated that certain techniques employed in the neural network context have long been developed by the control engineering community.