ニューラルネットワークを使用した非線形離散時間システムの制御

概要

論文の詳細を見る
Feedback linearization theory has offered an effective means to the control of nonlinear systems. The central idea of the approach is to transform a state space model of a plant into new coordinates where nonlinearities can be cancelled (fully or partially) by feedback. The major challenge in performing such cancellation is the need to know precise models of the nonlinearities. One approach to address this challenge is to use neural networks capable of determining the nonlinearities. In this paper we investigate discrete time systems. Computer simulations verify the theoretical result.
久留米工業大学の論文
1998-12-20