Fuzzy multi-model based adaptive predictive control and its application to thermoplastic injection molding

Many chemical processes are inherently nonlinear. A single linear model is ineffective for these processes. Several local linear models may be developed for different operating conditions. A combination of these local models, through a fuzzy logic representation, results in an overall model for a wi...

Full description

Saved in:
Bibliographic Details
Published in:Canadian journal of chemical engineering Vol. 79; no. 2; pp. 263 - 272
Main Authors: Li, Mingzhong, Yang, Yi, Gao, Furong, Wang, Fuli
Format: Journal Article
Language:English
Published: Hoboken Wiley Subscription Services, Inc., A Wiley Company 01.04.2001
Wiley
Subjects:
Applied sciences
competitive learning algorithm
Exact sciences and technology
fuzzy multi-model
injection molding
Injection moulding
Machinery and processing
Moulding
Plastics
Polymer industry, paints, wood
predictive control
Technology of polymers
weighted recursive least squares algorithm
Fuzzy logic
Thermoplastics
Least squares method
Process control
Injection molding
Recursive method
SISO system
Non linear system
Learning algorithm
Adaptive control
Predictive control
ISSN:0008-4034, 1939-019X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many chemical processes are inherently nonlinear. A single linear model is ineffective for these processes. Several local linear models may be developed for different operating conditions. A combination of these local models, through a fuzzy logic representation, results in an overall model for a wider operation range. In this paper, on‐line improvements and a fuzzy multi‐model have been proposed for predictive control implementation. Firstly, assuming that the premises of the fuzzy rules keep their original structures, the linear parameters in the rule consequents are on‐line updated by a weighted recursive least squares algorithm at each sample interval. Secondly, a batch learning algorithm is proposed to tune the fuzzy rule premises using a competitive learning algorithm. The effectiveness of the proposed improvements is demonstrated with experimental applications to the filling velocity control of thermoplastic injection molding De nombreux procédés chimiques sont par nature non linéaires. Un modèle linéaire simple est donc inefficace pour ces procédés. Plusieurs modèles linéaires locaux peuvent ětre mis au point pour différentes conditions de fonetionnement. Une combinaison de ces modèles locaux, par une représentation en logique floue, peut donner un modèle global pour une gamme plus large de fonctionnement. Dans cet article, des améliorations en ligne et un multi‐modèle flou sont proposés pour la mise en place d'un contrǒle prédictif. Premièrement, en supposant que les prémissses des règles floues gardent leurs structures originales, les paramètres linéaires dans les conséquences des règles sont mises à jour en ligne par un algorithme de moindres carrés récurrents pondéré à chaque intervalle d'échantillon. Deuxièmement, on propose un algorithme d'apprentissage discontinu pour ajuster les premisses des règles floues à l'aide d'un algorithme d'apprentissage compétitif. L'efficacité des améliorations proposées est démontrée par des applications expérimentales du contrǒle de la Vitesse de remplissage en moulage par injection de thermoplastique
Bibliography:Hong Kong Research Grants Council - No. HKUST6032/98P.
ark:/67375/WNG-MGDCPSH7-7
ArticleID:CJCE5450790209
istex:CEA06FBCF2FA02F9DBF4C90DA4CF8EF5A362B07F
Currently with School of Information Science and Engineering, Northeastern University, Shenyang, 110006, China.
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0008-4034
1939-019X
DOI:10.1002/cjce.5450790209