Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network

Sholahudin; Keisuke Ohno; Seiichi Yamaguchi; Kiyoshi Saito

doi:10.18462/iir.icr.2019.1244

Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network

Sholahudin, Keisuke Ohno, Seiichi Yamaguchi, Kiyoshi Saito

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Identification for system dynamic behaviour is necessary to develop control strategy. In this paper, the dynamic performance of air conditioning (AC) system is predicted using artificial neural network (ANN) approach. The ANN is developed to predict exergy efficiency, coefficient of performance (COP), and cooling capacity. The controllable parameters including compressor speed and evaporator and condenser fan speed are considered as the input. The datasets for prediction are generated by AC system simulator. The system was simulated by randomly varying compressor speed and evaporator and condenser fan speed with N-sample signal input. The dynamic ANN configuration with Bayesian regularization is proposed to predict one-step ahead of system performance behaviour. The results show that the developed ANN in present study yields good prediction accuracy for all outputs. Accordingly, ANN can be further applied for predictive control application in AC system to control cooling capacity while maintaining system efficiency.

Original language	English
Title of host publication	ICR 2019 - 25th IIR International Congress of Refrigeration
Editors	Vasile Minea
Publisher	International Institute of Refrigeration
Pages	4061-4068
Number of pages	8
ISBN (Electronic)	9782362150357
DOIs	https://doi.org/10.18462/iir.icr.2019.1244
Publication status	Published - 2019
Event	25th IIR International Congress of Refrigeration, ICR 2019 - Montreal, Canada Duration: 2019 Aug 24 → 2019 Aug 30

Publication series

Name	Refrigeration Science and Technology
Volume	2019-August
ISSN (Print)	0151-1637

Conference

Conference	25th IIR International Congress of Refrigeration, ICR 2019
Country/Territory	Canada
City	Montreal
Period	19/8/24 → 19/8/30

Keywords

Air Conditioning
Exergy
Neural Network
System Identification

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering
Mechanical Engineering
Condensed Matter Physics

Access to Document

10.18462/iir.icr.2019.1244

Cite this

Sholahudin, Ohno, K., Yamaguchi, S., & Saito, K. (2019). Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network. In V. Minea (Ed.), ICR 2019 - 25th IIR International Congress of Refrigeration (pp. 4061-4068). Article 1244 (Refrigeration Science and Technology; Vol. 2019-August). International Institute of Refrigeration. https://doi.org/10.18462/iir.icr.2019.1244

Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network. / Sholahudin; Ohno, Keisuke; Yamaguchi, Seiichi et al.
ICR 2019 - 25th IIR International Congress of Refrigeration. ed. / Vasile Minea. International Institute of Refrigeration, 2019. p. 4061-4068 1244 (Refrigeration Science and Technology; Vol. 2019-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sholahudin, Ohno, K, Yamaguchi, S & Saito, K 2019, Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network. in V Minea (ed.), ICR 2019 - 25th IIR International Congress of Refrigeration., 1244, Refrigeration Science and Technology, vol. 2019-August, International Institute of Refrigeration, pp. 4061-4068, 25th IIR International Congress of Refrigeration, ICR 2019, Montreal, Canada, 19/8/24. https://doi.org/10.18462/iir.icr.2019.1244

Sholahudin, Ohno K, Yamaguchi S , Saito K. Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network. In Minea V, editor, ICR 2019 - 25th IIR International Congress of Refrigeration. International Institute of Refrigeration. 2019. p. 4061-4068. 1244. (Refrigeration Science and Technology). doi: 10.18462/iir.icr.2019.1244

@inproceedings{53887f0eaf17468c8c9099f23b1300ac,

title = "Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network",

abstract = "Identification for system dynamic behaviour is necessary to develop control strategy. In this paper, the dynamic performance of air conditioning (AC) system is predicted using artificial neural network (ANN) approach. The ANN is developed to predict exergy efficiency, coefficient of performance (COP), and cooling capacity. The controllable parameters including compressor speed and evaporator and condenser fan speed are considered as the input. The datasets for prediction are generated by AC system simulator. The system was simulated by randomly varying compressor speed and evaporator and condenser fan speed with N-sample signal input. The dynamic ANN configuration with Bayesian regularization is proposed to predict one-step ahead of system performance behaviour. The results show that the developed ANN in present study yields good prediction accuracy for all outputs. Accordingly, ANN can be further applied for predictive control application in AC system to control cooling capacity while maintaining system efficiency.",

keywords = "Air Conditioning, Exergy, Neural Network, System Identification",

author = "Sholahudin and Keisuke Ohno and Seiichi Yamaguchi and Kiyoshi Saito",

note = "Publisher Copyright: {\textcopyright} 2019 International Institute of Refrigeration. All rights reserved.; 25th IIR International Congress of Refrigeration, ICR 2019 ; Conference date: 24-08-2019 Through 30-08-2019",

year = "2019",

doi = "10.18462/iir.icr.2019.1244",

language = "English",

series = "Refrigeration Science and Technology",

publisher = "International Institute of Refrigeration",

pages = "4061--4068",

editor = "Vasile Minea",

booktitle = "ICR 2019 - 25th IIR International Congress of Refrigeration",

}

TY - GEN

T1 - Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network

AU - Sholahudin,

AU - Ohno, Keisuke

AU - Yamaguchi, Seiichi

AU - Saito, Kiyoshi

PY - 2019

Y1 - 2019

N2 - Identification for system dynamic behaviour is necessary to develop control strategy. In this paper, the dynamic performance of air conditioning (AC) system is predicted using artificial neural network (ANN) approach. The ANN is developed to predict exergy efficiency, coefficient of performance (COP), and cooling capacity. The controllable parameters including compressor speed and evaporator and condenser fan speed are considered as the input. The datasets for prediction are generated by AC system simulator. The system was simulated by randomly varying compressor speed and evaporator and condenser fan speed with N-sample signal input. The dynamic ANN configuration with Bayesian regularization is proposed to predict one-step ahead of system performance behaviour. The results show that the developed ANN in present study yields good prediction accuracy for all outputs. Accordingly, ANN can be further applied for predictive control application in AC system to control cooling capacity while maintaining system efficiency.

AB - Identification for system dynamic behaviour is necessary to develop control strategy. In this paper, the dynamic performance of air conditioning (AC) system is predicted using artificial neural network (ANN) approach. The ANN is developed to predict exergy efficiency, coefficient of performance (COP), and cooling capacity. The controllable parameters including compressor speed and evaporator and condenser fan speed are considered as the input. The datasets for prediction are generated by AC system simulator. The system was simulated by randomly varying compressor speed and evaporator and condenser fan speed with N-sample signal input. The dynamic ANN configuration with Bayesian regularization is proposed to predict one-step ahead of system performance behaviour. The results show that the developed ANN in present study yields good prediction accuracy for all outputs. Accordingly, ANN can be further applied for predictive control application in AC system to control cooling capacity while maintaining system efficiency.

KW - Air Conditioning

KW - Exergy

KW - Neural Network

KW - System Identification

UR - http://www.scopus.com/inward/record.url?scp=85082675421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85082675421&partnerID=8YFLogxK

U2 - 10.18462/iir.icr.2019.1244

DO - 10.18462/iir.icr.2019.1244

M3 - Conference contribution

AN - SCOPUS:85082675421

T3 - Refrigeration Science and Technology

SP - 4061

EP - 4068

BT - ICR 2019 - 25th IIR International Congress of Refrigeration

A2 - Minea, Vasile

PB - International Institute of Refrigeration

T2 - 25th IIR International Congress of Refrigeration, ICR 2019

Y2 - 24 August 2019 through 30 August 2019

ER -

Identification of vapour compression air conditioning system behaviour using Bayesian regularization neural network

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this