Abstract

In this paper, a new approach to design nonlinear adaptive PI multi-controllers, for SISO systems, based on neural local linear principal components analysis (PCA) models is proposed. The PCA neural networks only implements the integral term of the PI multi-controller, a proportional term is added to obtain a PI structure. A modi ed normalized Harris performance index is used for evaluating the controller performance. Some experimental results obtained with a nonlinear three tank benchmark model are presented, showing the adaptive PI-PCA multicontroller performance compared to neural linear PI controllers.
Original languageEnglish
Title of host publicationCONTROLO'2014 – Proceedings of the 11th Portuguese Conference on Automatic Control
EditorsPaulo António Moreira, Aníbal Matos, Germano Veiga
Place of PublicationCham, Switzerland
PublisherSpringer International Publishing
Pages103-112
Number of pages10
Volume321
ISBN (Electronic)978-3-319-10380-8
ISBN (Print)978-3-319-10379-2
DOIs
Publication statusPublished - 2015
Event11th Portuguese Conference on Automatic Control - Porto, Portugal
Duration: 21 Jul 201423 Jul 2014

Publication series

NameLecture Notes in Electrical Engineering (LNEE)
PublisherSpringer International Publishing
Volume321
ISSN (Print)1876-1100

Conference

Conference11th Portuguese Conference on Automatic Control
CountryPortugal
CityPorto
Period21/07/1423/07/14

Keywords

  • multi-models
  • nonlinear adaptive PI control
  • principal component analysis

Fingerprint Dive into the research topics of 'Neural PCA Controller Based on Multi-Models'. Together they form a unique fingerprint.

  • Cite this

    Palma, L. F. F. D. B., Coito, F. J. A. V. D., & Gil, P. J. C. D. S. (2015). Neural PCA Controller Based on Multi-Models. In P. A. Moreira, A. Matos, & G. Veiga (Eds.), CONTROLO'2014 – Proceedings of the 11th Portuguese Conference on Automatic Control (Vol. 321, pp. 103-112). (Lecture Notes in Electrical Engineering (LNEE); Vol. 321). Cham, Switzerland: Springer International Publishing. https://doi.org/10.1007/978-3-319-10380-8_11