Artificial evolution of neural networks and its application to feedback control

Li, Y. and Häuβler, A. (1996) Artificial evolution of neural networks and its application to feedback control. Artificial Intelligence in Engineering, 10(2), pp. 143-152. (doi: 10.1016/0954-1810(95)00024-0)

Full text not currently available from Enlighten.

Abstract

This paper develops direct neural control systems with a novel structure inspired by the proportional plus derivative control. A parameter vector based uniform description of the problem of neural network design is presented. Difficulties associated with traditional mathematically-guided design methods are discussed, which lead to the development of a genetic algorithm based evolution method that overcomes these difficulties and makes direct neurocontrollers possible. Techniques are also developed to optimise the architecture in the same process of parameter training leading to a Darwin neural machine. The proposed methods are verified by examples of direct neurocontroller design for a linear and a nonlinear plant.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Li, Professor Yun
Authors: Li, Y., and Häuβler, A.
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
College/School:College of Science and Engineering > School of Engineering > Systems Power and Energy
Research Group:Intelligent Systems
Journal Name:Artificial Intelligence in Engineering
Publisher:Elsevier Science
ISSN:0954-1810
ISSN (Online):1474-0346
Published Online:19 February 1999

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
101101Evolutionary programming for nonlinear controlYun LiScience & Engineering Research Council (SERC)GR/K24987Systems Power and Energy