Solar absorption chiller performance prediction based on the selection of principal component analysis

Nasruddin, Nyayu Aisyah, M. I. Alhamid, Bidyut Baran Saha, S. Sholahudin, Arnas Lubis

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, a method to predict the performance of an absorption chiller using solar thermal collectors as the energy input is analyzed rigorously. Artificial Neural Network (ANN) is developed based on experimental data to predict the performance of the solar absorption chiller system at Universitas Indonesia. In order to perform ANN accurately, some parameters such as chilled water inlet and outlet temperatures, cooling water inlet and outlet temperatures, solar hot water inlet and outlet temperatures, hot water inlet and outlet temperatures, ambient temperature and fuel consumption flow rate are chosen as the input variables. In addition, a Principle Component Analysis (PCA) is used to reduce the number of input variables for performance prediction. Without sacrificing the ANN's prediction accuracy, PCA identified the sensitive variables from all input variables. The developed ANN model combined with PCA (ANN + PCA) shows good performance which has a comparable error with ANN model, specifically the configuration 9-6-2 (9 neurons, 6 inputs, 2 outputs) of the ANN + PCA model leads to a COP root-mean-square error of 0.0145.

Original languageEnglish
Article number100391
JournalCase Studies in Thermal Engineering
Volume13
DOIs
Publication statusPublished - Mar 1 2019

Fingerprint

Principal component analysis
Neural networks
Water
Temperature
Cooling water
Fuel consumption
Mean square error
Neurons
Flow rate
Hot Temperature

All Science Journal Classification (ASJC) codes

  • Engineering (miscellaneous)
  • Fluid Flow and Transfer Processes

Cite this

Solar absorption chiller performance prediction based on the selection of principal component analysis. / Nasruddin; Aisyah, Nyayu; Alhamid, M. I.; Saha, Bidyut Baran; Sholahudin, S.; Lubis, Arnas.

In: Case Studies in Thermal Engineering, Vol. 13, 100391, 01.03.2019.

Research output: Contribution to journalArticle

@article{dd423df19176470fb588cf224041535b,
title = "Solar absorption chiller performance prediction based on the selection of principal component analysis",
abstract = "In this paper, a method to predict the performance of an absorption chiller using solar thermal collectors as the energy input is analyzed rigorously. Artificial Neural Network (ANN) is developed based on experimental data to predict the performance of the solar absorption chiller system at Universitas Indonesia. In order to perform ANN accurately, some parameters such as chilled water inlet and outlet temperatures, cooling water inlet and outlet temperatures, solar hot water inlet and outlet temperatures, hot water inlet and outlet temperatures, ambient temperature and fuel consumption flow rate are chosen as the input variables. In addition, a Principle Component Analysis (PCA) is used to reduce the number of input variables for performance prediction. Without sacrificing the ANN's prediction accuracy, PCA identified the sensitive variables from all input variables. The developed ANN model combined with PCA (ANN + PCA) shows good performance which has a comparable error with ANN model, specifically the configuration 9-6-2 (9 neurons, 6 inputs, 2 outputs) of the ANN + PCA model leads to a COP root-mean-square error of 0.0145.",
author = "Nasruddin and Nyayu Aisyah and Alhamid, {M. I.} and Saha, {Bidyut Baran} and S. Sholahudin and Arnas Lubis",
year = "2019",
month = "3",
day = "1",
doi = "10.1016/j.csite.2019.100391",
language = "English",
volume = "13",
journal = "Case Studies in Thermal Engineering",
issn = "2214-157X",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Solar absorption chiller performance prediction based on the selection of principal component analysis

AU - Nasruddin,

AU - Aisyah, Nyayu

AU - Alhamid, M. I.

AU - Saha, Bidyut Baran

AU - Sholahudin, S.

AU - Lubis, Arnas

PY - 2019/3/1

Y1 - 2019/3/1

N2 - In this paper, a method to predict the performance of an absorption chiller using solar thermal collectors as the energy input is analyzed rigorously. Artificial Neural Network (ANN) is developed based on experimental data to predict the performance of the solar absorption chiller system at Universitas Indonesia. In order to perform ANN accurately, some parameters such as chilled water inlet and outlet temperatures, cooling water inlet and outlet temperatures, solar hot water inlet and outlet temperatures, hot water inlet and outlet temperatures, ambient temperature and fuel consumption flow rate are chosen as the input variables. In addition, a Principle Component Analysis (PCA) is used to reduce the number of input variables for performance prediction. Without sacrificing the ANN's prediction accuracy, PCA identified the sensitive variables from all input variables. The developed ANN model combined with PCA (ANN + PCA) shows good performance which has a comparable error with ANN model, specifically the configuration 9-6-2 (9 neurons, 6 inputs, 2 outputs) of the ANN + PCA model leads to a COP root-mean-square error of 0.0145.

AB - In this paper, a method to predict the performance of an absorption chiller using solar thermal collectors as the energy input is analyzed rigorously. Artificial Neural Network (ANN) is developed based on experimental data to predict the performance of the solar absorption chiller system at Universitas Indonesia. In order to perform ANN accurately, some parameters such as chilled water inlet and outlet temperatures, cooling water inlet and outlet temperatures, solar hot water inlet and outlet temperatures, hot water inlet and outlet temperatures, ambient temperature and fuel consumption flow rate are chosen as the input variables. In addition, a Principle Component Analysis (PCA) is used to reduce the number of input variables for performance prediction. Without sacrificing the ANN's prediction accuracy, PCA identified the sensitive variables from all input variables. The developed ANN model combined with PCA (ANN + PCA) shows good performance which has a comparable error with ANN model, specifically the configuration 9-6-2 (9 neurons, 6 inputs, 2 outputs) of the ANN + PCA model leads to a COP root-mean-square error of 0.0145.

UR - http://www.scopus.com/inward/record.url?scp=85061318035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061318035&partnerID=8YFLogxK

U2 - 10.1016/j.csite.2019.100391

DO - 10.1016/j.csite.2019.100391

M3 - Article

VL - 13

JO - Case Studies in Thermal Engineering

JF - Case Studies in Thermal Engineering

SN - 2214-157X

M1 - 100391

ER -