Control and disturbance rejection with a dynamic neurocontroller

Yuanlan Wu, S. Massoud Amin, Ervin Y. Rodin

Research output: Contribution to conferencePaperpeer-review

4 Scopus citations

Abstract

This study presents a neural controller consisting of memory neurons for the purpose of real-time control problems in a class of linear systems. A rule is provided which updates weights of interconnections in the network. The dynamics of the memory neurons are subject to change; the resulting changes in system behavior are investigated. Simulation results show that neurocontroller performance varies with different desired output set-points. Furthermore, the dynamic neurocontroller containing memory neurons exhibits a greater step disturbance rejection capability than a static neurocontroller.

Original languageEnglish (US)
Pages643-648
Number of pages6
StatePublished - Dec 1 1992
Externally publishedYes
EventProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA
Duration: Nov 15 1992Nov 18 1992

Other

OtherProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92
CitySt.Louis, MO, USA
Period11/15/9211/18/92

Fingerprint Dive into the research topics of 'Control and disturbance rejection with a dynamic neurocontroller'. Together they form a unique fingerprint.

Cite this