NONLINEAR PARAMETER-ESTIMATION - A CASE-STUDY COMPARISON

被引:147
作者
BIEGLER, LT [1 ]
DAMIANO, JJ [1 ]
BLAU, GE [1 ]
机构
[1] DOW CHEM CO,MIDLAND,MI 48640
关键词
CHEMICAL EQUIPMENT - Optimization - CHEMICAL REACTIONS - Reaction Kinetics - MATHEMATICAL TECHNIQUES - Nonlinear Equations;
D O I
10.1002/aic.690320105
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
In order to demonstrate the difficulties of parameter estimation in the industrial environment and the limitations of existing methods, a parameter estimation problem formulated by the Dow Chemical Company is presented and solved. This test problem consists of a stiff differential/algebraic (DAE) model that describes complex kinetics and requires the estimation of nine parameters from batch reactor data. Here the model was inadequate to describe the data, the error structure was not specified and the starting guesses led to a nontrivial optimization problem. Only five acceptable solutions were finally submitted. We present and compare these results. Each solution was obtained using different strategies. In most cases the form of the model was also changed to accommodate the algorithms used and to ease the solution procedure.
引用
收藏
页码:29 / 45
页数:17
相关论文
共 15 条
[1]  
BARD Y, 1974, NONLINEAR PARAMETER
[2]   A NEW METHOD OF CONSTRAINED OPTIMIZATION AND A COMPARISON WITH OTHER METHODS [J].
BOX, MJ .
COMPUTER JOURNAL, 1965, 8 (01) :42-52
[3]  
BYRNE GD, 1981, F COMPUTER AIDED PRO, V1, P403
[4]  
CARNAHAN B, 1981, F COMPUTER AIDED CHE, V1, P225
[5]   SOLUTION OF STIFF DIFFERENTIAL-EQUATIONS AND USE OF IMBEDDING TECHNIQUES [J].
CHAN, YNI ;
BIRNBAUM, I ;
LAPIDUS, L .
INDUSTRIAL & ENGINEERING CHEMISTRY FUNDAMENTALS, 1978, 17 (03) :133-148
[6]   AN EFFICIENT COMPUTATIONAL TECHNIQUE FOR GENERALIZED APPLICATION OF MAXIMUM-LIKELIHOOD TO IMPROVE CORRELATION OF EXPERIMENTAL-DATA [J].
FARISS, RH ;
LAW, VH .
COMPUTERS & CHEMICAL ENGINEERING, 1979, 3 (1-4) :95-104
[7]  
FLETCHER R, 1971, AERE6799 REP
[8]  
GEAR GW, 1971, IEEE T CIRCUIT THEOR, V18, P89
[9]  
Gill PE, 1981, PRACTICAL OPTIMIZATI
[10]   A NEW FLEXIBLE AND EASY-TO-USE GENERAL-PURPOSE REGRESSION PROGRAM FOR HANDLING A VARIETY OF SINGLE- AND MULTI-RESPONSE SITUATIONS [J].
KLAUS, R ;
RIPPIN, DWT .
COMPUTERS & CHEMICAL ENGINEERING, 1979, 3 (1-4) :105-115