Implementation and validation of an artificial neural network for predicting the performance of a liquid desiccant dehumidifier

Abdulrahman Th Mohammad, Sohif Mat, M. Y. Sulaiman, Kamaruzzaman Sopian, Abduljalil A. Al-Abidi

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

In the current paper, an artificial neural network (ANN) model for predicting the performance of a liquid desiccant dehumidifier in terms of the water condensation rate and dehumidifier effectiveness is proposed. Six air and desiccant inlet parameters were used as inputs for the ANN. To determine the performance of the ANN technique for predicting the performance of the dehumidifier, actual experimental test data were obtained from a previous study, that tested a packed column dehumidifier with a total height of 0.6 m and a specific packing material surface area of 77 m2/m3, using triethylene glycol as the desiccant. In the experiment, 54 data samples were used in a series of runs. MATLAB code was designed to study feed forward back propagation with traingdm, learngdm, MSE, and tansig as the training, learning, performance, and transfer functions, respectively. Up to 70% of the experimental data was used to train the model; the remaining 30% was used to test the output. The results show that the 6-3-3-1 network structure was the best model for predicting water condensation rate, whereas the 6-6-6-1 network structure was the best model for predicting dehumidifier effectiveness. The maximum percentage difference between the ANN and experimental value for water condensation rate and dehumidifier effectiveness were 8.13% and 9.0485%, respectively. The model for the water condensation rate and dehumidifier effectiveness could be further improved by modifying the number of hidden layers.

Original languageEnglish
Pages (from-to)240-250
Number of pages11
JournalEnergy Conversion and Management
Volume67
DOIs
Publication statusPublished - 2013

Fingerprint

Condensation
Neural networks
Liquids
Water
Glycols
Backpropagation
MATLAB
Transfer functions
Air
Experiments

Keywords

  • ANN
  • Condensation rate
  • Dehumidifier
  • Effectiveness

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Fuel Technology
  • Nuclear Energy and Engineering
  • Renewable Energy, Sustainability and the Environment

Cite this

Implementation and validation of an artificial neural network for predicting the performance of a liquid desiccant dehumidifier. / Mohammad, Abdulrahman Th; Mat, Sohif; Sulaiman, M. Y.; Sopian, Kamaruzzaman; Al-Abidi, Abduljalil A.

In: Energy Conversion and Management, Vol. 67, 2013, p. 240-250.

Research output: Contribution to journalArticle

@article{1c979a131391442f92a66adc3faa8ea8,
title = "Implementation and validation of an artificial neural network for predicting the performance of a liquid desiccant dehumidifier",
abstract = "In the current paper, an artificial neural network (ANN) model for predicting the performance of a liquid desiccant dehumidifier in terms of the water condensation rate and dehumidifier effectiveness is proposed. Six air and desiccant inlet parameters were used as inputs for the ANN. To determine the performance of the ANN technique for predicting the performance of the dehumidifier, actual experimental test data were obtained from a previous study, that tested a packed column dehumidifier with a total height of 0.6 m and a specific packing material surface area of 77 m2/m3, using triethylene glycol as the desiccant. In the experiment, 54 data samples were used in a series of runs. MATLAB code was designed to study feed forward back propagation with traingdm, learngdm, MSE, and tansig as the training, learning, performance, and transfer functions, respectively. Up to 70{\%} of the experimental data was used to train the model; the remaining 30{\%} was used to test the output. The results show that the 6-3-3-1 network structure was the best model for predicting water condensation rate, whereas the 6-6-6-1 network structure was the best model for predicting dehumidifier effectiveness. The maximum percentage difference between the ANN and experimental value for water condensation rate and dehumidifier effectiveness were 8.13{\%} and 9.0485{\%}, respectively. The model for the water condensation rate and dehumidifier effectiveness could be further improved by modifying the number of hidden layers.",
keywords = "ANN, Condensation rate, Dehumidifier, Effectiveness",
author = "Mohammad, {Abdulrahman Th} and Sohif Mat and Sulaiman, {M. Y.} and Kamaruzzaman Sopian and Al-Abidi, {Abduljalil A.}",
year = "2013",
doi = "10.1016/j.enconman.2012.12.005",
language = "English",
volume = "67",
pages = "240--250",
journal = "Energy Conversion and Management",
issn = "0196-8904",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Implementation and validation of an artificial neural network for predicting the performance of a liquid desiccant dehumidifier

AU - Mohammad, Abdulrahman Th

AU - Mat, Sohif

AU - Sulaiman, M. Y.

AU - Sopian, Kamaruzzaman

AU - Al-Abidi, Abduljalil A.

PY - 2013

Y1 - 2013

N2 - In the current paper, an artificial neural network (ANN) model for predicting the performance of a liquid desiccant dehumidifier in terms of the water condensation rate and dehumidifier effectiveness is proposed. Six air and desiccant inlet parameters were used as inputs for the ANN. To determine the performance of the ANN technique for predicting the performance of the dehumidifier, actual experimental test data were obtained from a previous study, that tested a packed column dehumidifier with a total height of 0.6 m and a specific packing material surface area of 77 m2/m3, using triethylene glycol as the desiccant. In the experiment, 54 data samples were used in a series of runs. MATLAB code was designed to study feed forward back propagation with traingdm, learngdm, MSE, and tansig as the training, learning, performance, and transfer functions, respectively. Up to 70% of the experimental data was used to train the model; the remaining 30% was used to test the output. The results show that the 6-3-3-1 network structure was the best model for predicting water condensation rate, whereas the 6-6-6-1 network structure was the best model for predicting dehumidifier effectiveness. The maximum percentage difference between the ANN and experimental value for water condensation rate and dehumidifier effectiveness were 8.13% and 9.0485%, respectively. The model for the water condensation rate and dehumidifier effectiveness could be further improved by modifying the number of hidden layers.

AB - In the current paper, an artificial neural network (ANN) model for predicting the performance of a liquid desiccant dehumidifier in terms of the water condensation rate and dehumidifier effectiveness is proposed. Six air and desiccant inlet parameters were used as inputs for the ANN. To determine the performance of the ANN technique for predicting the performance of the dehumidifier, actual experimental test data were obtained from a previous study, that tested a packed column dehumidifier with a total height of 0.6 m and a specific packing material surface area of 77 m2/m3, using triethylene glycol as the desiccant. In the experiment, 54 data samples were used in a series of runs. MATLAB code was designed to study feed forward back propagation with traingdm, learngdm, MSE, and tansig as the training, learning, performance, and transfer functions, respectively. Up to 70% of the experimental data was used to train the model; the remaining 30% was used to test the output. The results show that the 6-3-3-1 network structure was the best model for predicting water condensation rate, whereas the 6-6-6-1 network structure was the best model for predicting dehumidifier effectiveness. The maximum percentage difference between the ANN and experimental value for water condensation rate and dehumidifier effectiveness were 8.13% and 9.0485%, respectively. The model for the water condensation rate and dehumidifier effectiveness could be further improved by modifying the number of hidden layers.

KW - ANN

KW - Condensation rate

KW - Dehumidifier

KW - Effectiveness

UR - http://www.scopus.com/inward/record.url?scp=84872088155&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872088155&partnerID=8YFLogxK

U2 - 10.1016/j.enconman.2012.12.005

DO - 10.1016/j.enconman.2012.12.005

M3 - Article

VL - 67

SP - 240

EP - 250

JO - Energy Conversion and Management

JF - Energy Conversion and Management

SN - 0196-8904

ER -