About
Contact
Help
Sending publications
How to publish
Advanced Search
View Item 
  •   Home
  • Facultad de Ciencias Físicas y Matemáticas
  • Artículos de revistas
  • View Item
  •   Home
  • Facultad de Ciencias Físicas y Matemáticas
  • Artículos de revistas
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse byCommunities and CollectionsDateAuthorsTitlesSubjectsThis CollectionDateAuthorsTitlesSubjects

My Account

Login to my accountRegister
Biblioteca Digital - Universidad de Chile
Revistas Chilenas
Repositorios Latinoamericanos
Tesis LatinoAmericanas
Tesis chilenas
Related linksRegistry of Open Access RepositoriesOpenDOARGoogle scholarCOREBASE
My Account
Login to my accountRegister

A predictive control scheme based on neural networks

Artículo
Thumbnail
Open/Download
IconSuarez_Alejandro.pdf (576.4Kb)
Publication date
2006
Metadata
Show full item record
Cómo citar
Suárez, Alejandro M.
Cómo citar
A predictive control scheme based on neural networks
.
Copiar
Cerrar

Author
  • Suárez, Alejandro M.;
  • Duarte Mermoud, Manuel;
  • Bassi, Danilo F.;
Abstract
Purpose - To develop a new predictive control scheme based on neural networks for linear and non-linear dynamical systems. Design/methodology/approach - The approach relies on three different multilayer neural networks using input-output information with delays. One NN is used to identify the process under control, the other is used to predict the future values of the control error and finally the third one is used to compute the magnitude of the control input to be applied to the plant. Findings - This scheme has been tested by controlling discrete-time SISO and MBIO processes already known in the control literature and the results have been compared with other control approaches with no predictive effects. Transient behavior of the new algorithm, as well as the steady state one, are observed and analyzed in each case studied. Also, online and offline neural network training are compared for the proposed scheme. Research limitations/implications - The theoretical proof of stability of the proposed scheme still remains to be studied. Conditions under which non-linear plants together with the proposed controller present a stable behavior have to be derived. Practical implications - The main advantage of the proposed method is that the predictive effect allows to suitable control complex non-linear process, eliminating oscillations during the transient response. This will be useful for control engineers to control complex industrial plants. Originality/value - This general approach is based on predicting the future control errors through a predictive neural network, taking advantage of the NN characteristics to approximate any kind of relationship. The advantage of this predictive scheme is that the knowledge of the future reference values is not needed, since the information used to train the predictive NN is based on present and past values of the control error. Since the plant parameters are unknown, the identification NN is used to back-propagate the control error from the output of the plant to the output of the controller. The weights of the controller NN are adjusted so that the present and future values of the control error are minimized.
Identifier
URI: https://repositorio.uchile.cl/handle/2250/124994
ISSN: 0368-492X
Quote Item
KYBERNETES Volume: 35 Issue: 9-10 Pages: 1579-1606 Published: 2006
Collections
  • Artículos de revistas
xmlui.footer.title
31 participating institutions
More than 73,000 publications
More than 110,000 topics
More than 75,000 authors
Published in the repository
  • How to publish
  • Definitions
  • Copyright
  • Frequent questions
Documents
  • Dating Guide
  • Thesis authorization
  • Document authorization
  • How to prepare a thesis (PDF)
Services
  • Digital library
  • Chilean academic journals portal
  • Latin American Repository Network
  • Latin American theses
  • Chilean theses
Dirección de Servicios de Información y Bibliotecas (SISIB)
Universidad de Chile

© 2020 DSpace
  • Access my account