NEURAL-NETWORK SYSTEM-IDENTIFICATION FOR IMPROVED NOISE REJECTION

Neural networks are able to approximate a large class of input-output maps and are also attractive due to their parallel structure which can lead to numerically inexpensive weight update laws. These properties make neural networks a viable paradigm for adaptive system identificat ion and control, and as a consequence the use of neural networks for i dentification and control has become an active area of research. This paper contributes to this research thrust by developing adaptive neura l identification algorithms that are able to minimize the influences o f extrinsic noise on the quality of the identified model. The developm ent relies on the use of a batch ARMarkov model, a generalization of a n ARMA model whose parameters include some of the Markov parameters of the system and whose output contains the system outputs at previous s ample instants. Through both theoretical analyses and simulation resul ts, this paper demonstrates the ability of the neural network predicat ed on a batch ARMarkov model to improve on the noise rejection propert ies of identification, based on either an ARMA model or a CARMA model developed by Watanabe et al. Although the focus here is on linear syst em identification, the paper lays a foundation for adaptive, nonlinear identification and control.