Neural net based hybrid modeling of the methanol synthesis process

被引:6
作者
Potocnik, P
Grabec, I
Setinc, M
Levec, J
机构
[1] Univ Ljubljana, Fac Mech Engn, Lab Tech Phys, Ljubljana 61000, Slovenia
[2] Natl Inst Chem, Lab Catalysis & Chem React Engn, Ljubljana, Slovenia
关键词
hybrid modeling; genetic algorithms; feature selection; methanol synthesis; neural networks;
D O I
10.1023/A:1009615710515
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A Hybrid modeling approach, combining an analytical model with a radial basis function neural network is introduced in this paper. The modeling procedure is combined with genetic algorithm based feature selection designed to select informative variables from the set of available measurements. By only using informative inputs, the model's generalization ability can be enhanced. The approach proposed is applied to modeling of the liquid-phase methanol synthesis. It is shown that a hybrid modeling approach exploiting available a priori knowledge and experimental data can considerably outperform a purely analytical approach.
引用
收藏
页码:219 / 228
页数:10
相关论文
共 11 条
[1]   Combining neural and conventional paradigms for modelling, prediction and control [J].
Agarwal, M .
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 1997, 28 (01) :65-81
[2]  
BAUGHMAN R, 1995, NEURAL NETWORKS BIOP
[3]  
BUSSCHE KMV, 1996, CHEM ENG SCI, V161, P1
[4]   CHEMICAL-EQUILIBRIA IN METHANOL SYNTHESIS [J].
GRAAF, GH ;
SIJTSEMA, PJJM ;
STAMHUIS, EJ ;
JOOSTEN, GEH .
CHEMICAL ENGINEERING SCIENCE, 1986, 41 (11) :2883-2890
[5]   KINETICS OF THE 3 PHASE METHANOL SYNTHESIS [J].
GRAAF, GH ;
WINKELMAN, JGM ;
STAMHUIS, EJ ;
BEENACKERS, AACM .
CHEMICAL ENGINEERING SCIENCE, 1988, 43 (08) :2161-2168
[6]  
GRABEC I, 1997, SERIES SYNERGETICS
[7]   METHANOL SYNTHESIS IN BUBBLE COLUMN SLURRY REACTORS [J].
LEDAKOWICZ, S ;
STELMACHOWSKI, M ;
CHACUK, A ;
DECKWER, WD .
CHEMICAL ENGINEERING AND PROCESSING-PROCESS INTENSIFICATION, 1992, 31 (04) :213-219
[8]  
LEE S, 1985, 9 ANN EPRI CONTR C C, P15
[9]   Fast Learning in Networks of Locally-Tuned Processing Units [J].
Moody, John ;
Darken, Christian J. .
NEURAL COMPUTATION, 1989, 1 (02) :281-294
[10]  
POTOCNIK P, 1998, P INT ICSC S ENG INT, P307