Simple recurrent neural network control for non-minimum phase nonlinear system

MaRDI QIDQ2745621zbMATH OpenFDO

Authors Xiang Li, Zhuzhi Yuan, Zengqiang Chen

Publication date 10 April 2002

Published in Control Theory \& Applications (Search for Journal in Brave)

zbMATH Keywords

cost functionnon-minimum phase nonlinear systemoptimal stabilizationrecurrent neural networkweight

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Nonlinear systems in control theory (93C10) Stabilization of systems by feedback (93D15)

Review text

A simple recurrent neural network controller is designed to stabilize a non-minimum phase nonlinear system. The main advantage of such a controller is its uniformity with the introduction of the weighted control information into the neural controller's cost function. Some simulation results are given as well.

Recommendations

• Stable receding horizon control based on recurrent networks
• Adaptive neural network output feedback stabilization of nonlinear non-minimum phase systems
• Recurrent neural networks for nonlinear output regulation
• Adaptive control of discrete-time nonlinear systems using recurrent neural networks
• Dynamic recurrent neural network for system identification and control

Cited in

(5)

• Nonlinear system compound inverse control method
• Stable receding horizon control based on recurrent networks
• Dynamic recurrent neural network for system identification and control
• Research and development of control system based on diagonal recurrent neural network
• Recurrent neural networks for nonlinear output regulation

This page was built for publication: Simple recurrent neural network control for non-minimum phase nonlinear system

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2745621)