NEURAL NET BASED MODEL PREDICTIVE CONTROL

被引：103

作者：

SAINTDONAT, J

BHAT, N

MCAVOY, TJ

机构：

[1] Department of Chemical Engineering, University of Maryland, MD, 20742, College Park

来源：

INTERNATIONAL JOURNAL OF CONTROL | 1991年 / 54卷 / 06期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1080/00207179108934221

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Neural networks hold great promise for application in the general area of process control. This paper focuses on using a back propagation network in an optimization based model predictive control scheme. Since an analytical expression for the gradient of the neural net model can be derived and this expression can be calculated in parallel, extremely fast computation times are possible. The control approach is illustrated on a pH CSTR example.

引用

页码：1453 / 1468

页数：16

共 21 条

[1] USE OF NEURAL NETS FOR DYNAMIC MODELING AND CONTROL OF CHEMICAL PROCESS SYSTEMS [J].

BHAT, N ;

MCAVOY, TJ .

COMPUTERS & CHEMICAL ENGINEERING, 1990, 14 (4-5) :573-583

[2]

BHAT N, 1989, 1989 AM AUT CONTR C, P1336

[3]

BHAT NV, 1990, 1990 AICHE ANN M CHI

[4]

BIRKY G, 1989, IFAC DYCORD S MAASTR, P147

[5] MULTISTEP NONLINEAR PREDICTIVE CONTROLLER [J].

BRENGEL, DD ;

SEIDER, WD .

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 1989, 28 (12) :1812-1822

[6]

EATON JW, 1989, 1988 P IFAC WORKSH M, P129

[7]

GINGRICH C, 1990, P INSTRUMENT SOC AM

[8]

HERNANDEX E, 1990, P AM CONTROL C

[9]

HIMMELBLAU D, 1990, P INT JOINT C NEURAL, P1631

[10] MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

NEURAL NETWORKS, 1989, 2 (05) :359-366

← 1 2 3 →