Identification and control of nonlinear systems using Fuzzy Hammerstein models

被引:51
作者
Abonyi, J
Babuska, R
Botto, MA
Szeifert, F
Nagy, L
机构
[1] Delft Univ Technol, Dept Informat Technol & Syst, NL-2600 GA Delft, Netherlands
[2] Delft Univ Technol, Control Engn Lab, NL-2600 GA Delft, Netherlands
[3] Univ Veszprem, Dept Proc Engn, H-8201 Veszprem, Hungary
[4] Univ Tecn Lisboa, Inst Super, P-1049001 Lisbon, Portugal
[5] Univ Tecn Lisboa, Dept Mech Engn, P-1049001 Lisbon, Portugal
关键词
D O I
10.1021/ie990629e
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
This paper addresses the identification and control of nonlinear systems by means of Fuzzy Hammerstein (FH) models, which consist of a static fuzzy model connected in series with a linear dynamic model. For the identification of nonlinear dynamic systems with the proposed FH models, two methods are proposed. The first one is an alternating optimization algorithm that iteratively refines the estimate of the linear dynamics and the parameters of the static fuzzy model. The second method estimates the parameters of the nonlinear static model and of the linear dynamic model simultaneously by using a constrained recursive least-squares algorithm. The obtained FH model is incorporated in a model-based predictive control scheme and a new constraint-handling method is presented. A simulated water-heater process is used as an illustrative example. A comparison with an affine neural network and a linear model is given. Simulation results show that the proposed FR modeling approach is useful for modular parsimonious modeling and model-based control of nonlinear systems.
引用
收藏
页码:4302 / 4314
页数:13
相关论文
共 41 条
[1]  
Abonyi J, 2000, NINTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE 2000), VOLS 1 AND 2, P835, DOI 10.1109/FUZZY.2000.839140
[2]   Hybrid fuzzy convolution modelling and identification of chemical process systems [J].
Abonyi, J ;
Nagy, L ;
Szeifert, F .
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2000, 31 (04) :457-466
[3]   Adaptive fuzzy inference system and its application in modelling and model based control [J].
Abonyi, J ;
Nagy, L ;
Szeifert, F .
CHEMICAL ENGINEERING RESEARCH & DESIGN, 1999, 77 (A4) :281-290
[4]  
ABONYI J, 1999, P FUZZ IEEE 99 SEOUL, P951
[5]   ESTIMATION OF RESIDENCE TIME IN CONTINUOUS-FLOW SYSTEMS WITH DYNAMICS [J].
ANDERSSON, T ;
PUCAR, P .
JOURNAL OF PROCESS CONTROL, 1995, 5 (01) :9-17
[6]  
BABUSKA R, 1997, P 7 IFSA WORLD C PRA, P348
[7]  
Babuska R., 1998, INT SER INTELL TECHN
[8]  
BALAKRISHNAN V, 1994, ADV MBPC
[9]  
Bloemen H. H. J., 1999, Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304), P4595, DOI 10.1109/CDC.1999.833267
[10]   Convolution model based predictive controller for a nonlinear process [J].
Bodizs, A ;
Szeifert, F ;
Chovan, T .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 1999, 38 (01) :154-161