Adaptive control of distillation column using adaptive critic design

Petia Koprinkova-Hristova, Yancho Todorov, Nicolae Paraschiv, Marius Olteanu, Margarita Terziyska

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

The paper aims at synthesis of an adaptive controller of the distillate output flow rate of a binary distillation column. The disturbance of the process is the change of concentration of the inlet compound. The Adaptive Critic Design (ACD) approach was applied to predict on time the future effect of disturbance and to adapt the distillate output flow rate in order to prevent deviations from the desired distillate concentration. The key element of ACD-The critic-is a fast trainable recurrent neural network named Echo state network (ESN). The simulation investigations demonstrated that the proposed adaptive control scheme outperforms a classical non-adaptive controller with respect to the settling time and the reaction delay.

Original languageEnglish
Title of host publicationProceedings of the 2017 21st International Conference on Process Control, PC 2017
EditorsM. Kvasnica, M. Fikar
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages434-439
Number of pages6
ISBN (Electronic)978-1-5386-4011-1
DOIs
Publication statusPublished - 11 Jul 2017
MoE publication typeA4 Article in a conference publication
Event21st International Conference on Process Control, PC 2017 - Strbske Pleso, Slovakia
Duration: 6 Jun 20179 Jun 2017

Conference

Conference21st International Conference on Process Control, PC 2017
CountrySlovakia
CityStrbske Pleso
Period6/06/179/06/17

Fingerprint

Adaptive Design
Distillation
Distillation columns
Adaptive Control
Flow Rate
Disturbance
Flow rate
Echo State Network
Controller
Controllers
Recurrent neural networks
Output
Recurrent Neural Networks
Deviation
Synthesis
Binary
Predict
Simulation

Keywords

  • adaptive control
  • Adaptive Critic Design
  • binary distillation column
  • Echo state network

Cite this

Koprinkova-Hristova, P., Todorov, Y., Paraschiv, N., Olteanu, M., & Terziyska, M. (2017). Adaptive control of distillation column using adaptive critic design. In M. Kvasnica, & M. Fikar (Eds.), Proceedings of the 2017 21st International Conference on Process Control, PC 2017 (pp. 434-439). [7976253] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PC.2017.7976253
Koprinkova-Hristova, Petia ; Todorov, Yancho ; Paraschiv, Nicolae ; Olteanu, Marius ; Terziyska, Margarita. / Adaptive control of distillation column using adaptive critic design. Proceedings of the 2017 21st International Conference on Process Control, PC 2017. editor / M. Kvasnica ; M. Fikar. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 434-439
@inproceedings{4cd9d0b0bdca4c36906344f2c7a87f37,
title = "Adaptive control of distillation column using adaptive critic design",
abstract = "The paper aims at synthesis of an adaptive controller of the distillate output flow rate of a binary distillation column. The disturbance of the process is the change of concentration of the inlet compound. The Adaptive Critic Design (ACD) approach was applied to predict on time the future effect of disturbance and to adapt the distillate output flow rate in order to prevent deviations from the desired distillate concentration. The key element of ACD-The critic-is a fast trainable recurrent neural network named Echo state network (ESN). The simulation investigations demonstrated that the proposed adaptive control scheme outperforms a classical non-adaptive controller with respect to the settling time and the reaction delay.",
keywords = "adaptive control, Adaptive Critic Design, binary distillation column, Echo state network",
author = "Petia Koprinkova-Hristova and Yancho Todorov and Nicolae Paraschiv and Marius Olteanu and Margarita Terziyska",
year = "2017",
month = "7",
day = "11",
doi = "10.1109/PC.2017.7976253",
language = "English",
pages = "434--439",
editor = "M. Kvasnica and M. Fikar",
booktitle = "Proceedings of the 2017 21st International Conference on Process Control, PC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Koprinkova-Hristova, P, Todorov, Y, Paraschiv, N, Olteanu, M & Terziyska, M 2017, Adaptive control of distillation column using adaptive critic design. in M Kvasnica & M Fikar (eds), Proceedings of the 2017 21st International Conference on Process Control, PC 2017., 7976253, Institute of Electrical and Electronics Engineers Inc., pp. 434-439, 21st International Conference on Process Control, PC 2017, Strbske Pleso, Slovakia, 6/06/17. https://doi.org/10.1109/PC.2017.7976253

Adaptive control of distillation column using adaptive critic design. / Koprinkova-Hristova, Petia; Todorov, Yancho; Paraschiv, Nicolae; Olteanu, Marius; Terziyska, Margarita.

Proceedings of the 2017 21st International Conference on Process Control, PC 2017. ed. / M. Kvasnica; M. Fikar. Institute of Electrical and Electronics Engineers Inc., 2017. p. 434-439 7976253.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Adaptive control of distillation column using adaptive critic design

AU - Koprinkova-Hristova, Petia

AU - Todorov, Yancho

AU - Paraschiv, Nicolae

AU - Olteanu, Marius

AU - Terziyska, Margarita

PY - 2017/7/11

Y1 - 2017/7/11

N2 - The paper aims at synthesis of an adaptive controller of the distillate output flow rate of a binary distillation column. The disturbance of the process is the change of concentration of the inlet compound. The Adaptive Critic Design (ACD) approach was applied to predict on time the future effect of disturbance and to adapt the distillate output flow rate in order to prevent deviations from the desired distillate concentration. The key element of ACD-The critic-is a fast trainable recurrent neural network named Echo state network (ESN). The simulation investigations demonstrated that the proposed adaptive control scheme outperforms a classical non-adaptive controller with respect to the settling time and the reaction delay.

AB - The paper aims at synthesis of an adaptive controller of the distillate output flow rate of a binary distillation column. The disturbance of the process is the change of concentration of the inlet compound. The Adaptive Critic Design (ACD) approach was applied to predict on time the future effect of disturbance and to adapt the distillate output flow rate in order to prevent deviations from the desired distillate concentration. The key element of ACD-The critic-is a fast trainable recurrent neural network named Echo state network (ESN). The simulation investigations demonstrated that the proposed adaptive control scheme outperforms a classical non-adaptive controller with respect to the settling time and the reaction delay.

KW - adaptive control

KW - Adaptive Critic Design

KW - binary distillation column

KW - Echo state network

UR - http://www.scopus.com/inward/record.url?scp=85027497265&partnerID=8YFLogxK

U2 - 10.1109/PC.2017.7976253

DO - 10.1109/PC.2017.7976253

M3 - Conference article in proceedings

AN - SCOPUS:85027497265

SP - 434

EP - 439

BT - Proceedings of the 2017 21st International Conference on Process Control, PC 2017

A2 - Kvasnica, M.

A2 - Fikar, M.

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Koprinkova-Hristova P, Todorov Y, Paraschiv N, Olteanu M, Terziyska M. Adaptive control of distillation column using adaptive critic design. In Kvasnica M, Fikar M, editors, Proceedings of the 2017 21st International Conference on Process Control, PC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 434-439. 7976253 https://doi.org/10.1109/PC.2017.7976253