Deadzone compensation based on constrained RBF neural network

DOI10.1016/J.JFRANKLIN.2004.01.001MaRDI QIDQ705937zbMATH OpenOpenAlexFDO

Authors Chiung-Hsin Tsai, Han-Tung Chuang

Publication date 16 February 2005

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.jfranklin.2004.01.001

zbMATH Keywords

back propagation methodgradient descent techniqueidentificationinverse deadzone compensationRBF neural network

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) System identification (93B30) Nonlinear systems in control theory (93C10)

Review text

Two neural networks are used for the compensation of a deadzone. A radial basis function (RBF) neural network is used for the identification of the parameters. Then the RBF network acts as a single layer neural network and is trained based on the gradient descent technique. The result is used to train the other neural network for the inverse compensation of the deadzone.

Recommendations

• Deadzone compensation in motion control systems using neural networks
• Control of robots using radial basis function neural networks with dead-zone
• Advances in Neural Networks – ISNN 2005
• Radial Basis Function (RBF) Neural Network Control for Mechanical Systems
• scientific article; zbMATH DE number 1307001

Cites work

• Adaptive control of plants with unknown dead-zones
• Deadzone compensation in motion control systems using neural networks
• scientific article; zbMATH DE number 1202498 (Why is no real title available?)
• Lagrange programming neural networks
• Neural networks for nonlinear dynamic system modelling and identification
• Training multilayer neural networks using fast global learning algorithm -- least-squares and penalized optimization methods

Cited in

(5)

• Control of robots using radial basis function neural networks with dead-zone
• Deadzone compensation in motion control systems using neural networks
• Adaptive fuzzy funnel control for nonlinear systems with input deadzone and saturation
• Advances in Neural Networks – ISNN 2005
• Sliding mode control with adaptive fuzzy dead-zone compensation of an electro-hydraulic servo-system

This page was built for publication: Deadzone compensation based on constrained RBF neural network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q705937)