Optimum System Modelling Using Recent Gradient Methods

Abstract

<p> A study of gradient optimization techniques, in particular as applied to system modelling problems, is made. Three efficient techniques are used to derive optimum second-order and third-order models for a seventh-order system. The optimization techniques are the Fletcher-Powell method, a more recent method proposed by Fletcher and a method based on a more general objective function proposed by Jacobson and Oksman.</p> <p> The approximation is carried out in the time domain. Least squares and least pth criteria are used, and almost minimax results are obtained for large values of p. Values of p up to 10^12 are successfully used. The results are compared with other minimax type algorithms.</p>