Non-linear adaptive control via laguerre expansion of volterra kernels

Abstract

A truncated Wiener-Volterra functional series is used to represent the input-output relation of a non-linear dynamic system. By expanding Volterra kernels using orthonormal Laguerre functions, a Wiener-type non-linear model consisting of a Laguerre network followed by a memoryless Taylor expansion function is obtained. When functional series and Laguerre series truncations are allowed, an appropriate choice of the Laguerre filter pole permits a description of the process dynamics with a small number of parameters. Because the resulting model is linear in the parameters, those parameters can be estimated using a simple recursive least-squares (RLS) algorithm. Furthermore, a predictive control law is derived on the basis of the model and an industrial plant adaptive control simulation is performed. This method can be used for the modelling and control of a large class of non-linear dynamic systems.