Neural control of a batch distillation

D.C. Cressy, Ian T. Nabney, A. Simper

Research output: Contribution to journalArticle

Abstract

The purpose of the work reported here was to investigate the application of neural control to a common industrial process. The chosen problem was the control of a batch distillation. In the first phase towards deployment, a complex software simulation of the process was controlled. Initially, the plant was modelled with a neural emulator. The neural emulator was used to train a neural controller using the backpropagation through time algorithm. A high accuracy was achieved with the emulator after a large number of training epochs. The controller converged more rapidly, but its performance varied more widely over its operating range. However, the controlled system was relatively robust to changes in ambient conditions.
Original languageEnglish
Pages (from-to)115-123
Number of pages9
JournalNeural Computing and Applications
Volume1
Issue number2
Publication statusPublished - 1993

Fingerprint

Distillation
Backpropagation
Controllers

Bibliographical note

The original publication is available at www.springerlink.com

Keywords

  • neural control
  • emulator
  • backpropagation through time

Cite this

Cressy, D. C., Nabney, I. T., & Simper, A. (1993). Neural control of a batch distillation. Neural Computing and Applications, 1(2), 115-123.
Cressy, D.C. ; Nabney, Ian T. ; Simper, A. / Neural control of a batch distillation. In: Neural Computing and Applications. 1993 ; Vol. 1, No. 2. pp. 115-123.
@article{ed04bfc5df724508b700033cb2fd9aec,
title = "Neural control of a batch distillation",
abstract = "The purpose of the work reported here was to investigate the application of neural control to a common industrial process. The chosen problem was the control of a batch distillation. In the first phase towards deployment, a complex software simulation of the process was controlled. Initially, the plant was modelled with a neural emulator. The neural emulator was used to train a neural controller using the backpropagation through time algorithm. A high accuracy was achieved with the emulator after a large number of training epochs. The controller converged more rapidly, but its performance varied more widely over its operating range. However, the controlled system was relatively robust to changes in ambient conditions.",
keywords = "neural control, emulator, backpropagation through time",
author = "D.C. Cressy and Nabney, {Ian T.} and A. Simper",
note = "The original publication is available at www.springerlink.com",
year = "1993",
language = "English",
volume = "1",
pages = "115--123",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer",
number = "2",

}

Cressy, DC, Nabney, IT & Simper, A 1993, 'Neural control of a batch distillation', Neural Computing and Applications, vol. 1, no. 2, pp. 115-123.

Neural control of a batch distillation. / Cressy, D.C.; Nabney, Ian T.; Simper, A.

In: Neural Computing and Applications, Vol. 1, No. 2, 1993, p. 115-123.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural control of a batch distillation

AU - Cressy, D.C.

AU - Nabney, Ian T.

AU - Simper, A.

N1 - The original publication is available at www.springerlink.com

PY - 1993

Y1 - 1993

N2 - The purpose of the work reported here was to investigate the application of neural control to a common industrial process. The chosen problem was the control of a batch distillation. In the first phase towards deployment, a complex software simulation of the process was controlled. Initially, the plant was modelled with a neural emulator. The neural emulator was used to train a neural controller using the backpropagation through time algorithm. A high accuracy was achieved with the emulator after a large number of training epochs. The controller converged more rapidly, but its performance varied more widely over its operating range. However, the controlled system was relatively robust to changes in ambient conditions.

AB - The purpose of the work reported here was to investigate the application of neural control to a common industrial process. The chosen problem was the control of a batch distillation. In the first phase towards deployment, a complex software simulation of the process was controlled. Initially, the plant was modelled with a neural emulator. The neural emulator was used to train a neural controller using the backpropagation through time algorithm. A high accuracy was achieved with the emulator after a large number of training epochs. The controller converged more rapidly, but its performance varied more widely over its operating range. However, the controlled system was relatively robust to changes in ambient conditions.

KW - neural control

KW - emulator

KW - backpropagation through time

M3 - Article

VL - 1

SP - 115

EP - 123

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 2

ER -

Cressy DC, Nabney IT, Simper A. Neural control of a batch distillation. Neural Computing and Applications. 1993;1(2):115-123.