Adaptive Control of Distillation Column using Adaptive Critic Design

Petia Koprinkova-Hristova; Yancho Todorov; Marius Olteanu; Nikolae Paraschiv; Margarita Terziyska

doi:10.1109/PC.2017.7976253

Adaptive Control of Distillation Column using Adaptive Critic Design

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

3 Citations (Scopus)

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. Intelligent approach called Adaptive Critic Design (ACD) was applied to predict on time the 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 called 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 language	English
Title of host publication	Proceedings of the 2017 21st International Conference on Process Control
Publisher	IEEE
ISBN (Electronic)	978-1-5386-4011-1
DOIs	https://doi.org/10.1109/PC.2017.7976253
Publication status	Published - 17 Jul 2017
MoE publication type	A4 Article in a conference publication
Event	International Conference on Process Control - Štrbské Pleso, Slovakia Duration: 6 Jun 2017 → 9 Jun 2017 Conference number: 21 http://www.kirp.chtf.stuba.sk/pc17/

Conference

Conference	International Conference on Process Control
Country/Territory	Slovakia
City	Štrbské Pleso
Period	06/06/2017 → 09/06/2017
Internet address	http://www.kirp.chtf.stuba.sk/pc17/

Keywords

Process control
intelligent systems

Access to Document

10.1109/PC.2017.7976253

OpenUrl availability

Full text

Cite this

@inproceedings{34456687c7fd4a4887f17dba241c6af2,

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. Intelligent approach called Adaptive Critic Design (ACD) was applied to predict on time the 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 called 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 = "Process control, intelligent systems",

author = "Petia Koprinkova-Hristova and Yancho Todorov and Marius Olteanu and Nikolae Paraschiv and Margarita Terziyska",

year = "2017",

month = jul,

day = "17",

doi = "10.1109/PC.2017.7976253",

language = "English",

booktitle = "Proceedings of the 2017 21st International Conference on Process Control",

publisher = "IEEE",

address = "United States",

note = "International Conference on Process Control ; Conference date: 06-06-2017 Through 09-06-2017",

url = "http://www.kirp.chtf.stuba.sk/pc17/",

}

TY - GEN

T1 - Adaptive Control of Distillation Column using Adaptive Critic Design

AU - Koprinkova-Hristova, Petia

AU - Todorov, Yancho

AU - Olteanu, Marius

AU - Paraschiv, Nikolae

AU - Terziyska, Margarita

N1 - Conference code: 21

PY - 2017/7/17

Y1 - 2017/7/17

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. Intelligent approach called Adaptive Critic Design (ACD) was applied to predict on time the 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 called 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. Intelligent approach called Adaptive Critic Design (ACD) was applied to predict on time the 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 called 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 - Process control

KW - intelligent systems

U2 - 10.1109/PC.2017.7976253

DO - 10.1109/PC.2017.7976253

M3 - Conference contribution

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

PB - IEEE

T2 - International Conference on Process Control

Y2 - 6 June 2017 through 9 June 2017

ER -

Adaptive Control of Distillation Column using Adaptive Critic Design

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this