Neural Modeling and Control of a Distillation Column

James Edward Steck; K. Krishnamurthy; Bruce M. McMillin; Gary G. Leininger

doi:10.1109/IJCNN.1991.155432

Neural Modeling and Control of a Distillation Column

James Edward Steck
, K. Krishnamurthy
, Bruce M. McMillin
, Gary G. Leininger

Mechanical and Aerospace Engineering

Missouri University of Science and Technology

Research output: Contribution to journal › Article › peer-review

Abstract

Control of a nine-stage three-component distillation column is considered. The control objective is achieved using a neural estimator and a neural controller. The neural estimator is trained to represent the chemical process accurately, and the neural controller is trained to give an input to the chemical process which will yield the desired output. Training of both the neural networks is accomplished using a recursive least squares training algorithm implemented on an Intel iPSC/2 multicomputer (hypercube). Simulated results are presented for a numerical example.

Original language	American English
Journal	Proceedings of the International Joint Conference on Neural Networks (1991, Seattle, WA)
DOIs	https://doi.org/10.1109/IJCNN.1991.155432
State	Published - Jul 1 1992

Keywords

Chemical Equipment
Control Algorithms
Control Systems, Nonlinear
Distillation Column Control
Learning Algorithms
Learning Systems
Neural Network Controllers
Neural Networks - Applications

Disciplines

Computer Sciences
Mechanical Engineering

Access to Document

10.1109/IJCNN.1991.155432License: Unspecified

Neural Modeling and Control of a Distillation ColumnFinal published version, 314 KBLicense: Unspecified

Cite this

@article{52f43a5dc33942c2bf847de767cdfe9f,

title = "Neural Modeling and Control of a Distillation Column",

abstract = " Control of a nine-stage three-component distillation column is considered. The control objective is achieved using a neural estimator and a neural controller. The neural estimator is trained to represent the chemical process accurately, and the neural controller is trained to give an input to the chemical process which will yield the desired output. Training of both the neural networks is accomplished using a recursive least squares training algorithm implemented on an Intel iPSC/2 multicomputer (hypercube). Simulated results are presented for a numerical example.",

keywords = "Chemical Equipment, Control Algorithms, Control Systems, Nonlinear, Distillation Column Control, Learning Algorithms, Learning Systems, Neural Network Controllers, Neural Networks - Applications",

author = "Steck, \{James Edward\} and K. Krishnamurthy and McMillin, \{Bruce M.\} and Leininger, \{Gary G.\}",

year = "1992",

month = jul,

day = "1",

doi = "10.1109/IJCNN.1991.155432",

language = "American English",

journal = "Proceedings of the International Joint Conference on Neural Networks (1991, Seattle, WA)",

}

TY - JOUR

T1 - Neural Modeling and Control of a Distillation Column

AU - Steck, James Edward

AU - Krishnamurthy, K.

AU - McMillin, Bruce M.

AU - Leininger, Gary G.

PY - 1992/7/1

Y1 - 1992/7/1

N2 - Control of a nine-stage three-component distillation column is considered. The control objective is achieved using a neural estimator and a neural controller. The neural estimator is trained to represent the chemical process accurately, and the neural controller is trained to give an input to the chemical process which will yield the desired output. Training of both the neural networks is accomplished using a recursive least squares training algorithm implemented on an Intel iPSC/2 multicomputer (hypercube). Simulated results are presented for a numerical example.

AB - Control of a nine-stage three-component distillation column is considered. The control objective is achieved using a neural estimator and a neural controller. The neural estimator is trained to represent the chemical process accurately, and the neural controller is trained to give an input to the chemical process which will yield the desired output. Training of both the neural networks is accomplished using a recursive least squares training algorithm implemented on an Intel iPSC/2 multicomputer (hypercube). Simulated results are presented for a numerical example.

KW - Chemical Equipment

KW - Control Algorithms

KW - Control Systems, Nonlinear

KW - Distillation Column Control

KW - Learning Algorithms

KW - Learning Systems

KW - Neural Network Controllers

KW - Neural Networks - Applications

UR - https://scholarsmine.mst.edu/mec_aereng_facwork/3447

U2 - 10.1109/IJCNN.1991.155432

DO - 10.1109/IJCNN.1991.155432

M3 - Article

JO - Proceedings of the International Joint Conference on Neural Networks (1991, Seattle, WA)

JF - Proceedings of the International Joint Conference on Neural Networks (1991, Seattle, WA)

ER -

Neural Modeling and Control of a Distillation Column

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this