Development of ANN-based models to predict the static response and dynamic response of a heat exchanger in a real MVAC system

Qinhua Hu; Albert T.P. So; W. L. Tse; Qingchang Ren

doi:10.1088/1742-6596/23/1/013

Development of ANN-based models to predict the static response and dynamic response of a heat exchanger in a real MVAC system

Qinhua Hu
, Albert T.P. So
, W. L. Tse
, Qingchang Ren

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

17 Citations (Scopus)

2 Downloads (CityUHK Scholars)

Abstract

This paper presents a systematic approach to develop artificial neural network (ANN) models to predict the performance of a heat exchanger operating in real mechanical ventilation and air-conditioning (MVAC) system. Two approaches were attempted and presented. Every detailed components of the MVAC system have been considered and we attempt to model each of them by one ANN. This study used the neural network technique to obtain a static and a dynamic model for a heat exchanger mounted in an air handler unit (AHU), which is the key component of the MVAC system. It has been verified that almost all of the predicted values of the ANN model were within 95% - 105% of the measured values, with a consistent mean relative error (MRE) smaller than 2.5%. The paper details our experiences in using ANNs, especially those with back-propagation (BP) structures. Also, the weights and biases of our trained-up ANN models are listed out, which serve as good reference for readers to deal with their own situations. © 2005 IOP Publishing Ltd.

Original language	English
Pages (from-to)	110-121
Journal	Journal of Physics: Conference Series
Volume	23
Issue number	1
DOIs	https://doi.org/10.1088/1742-6596/23/1/013
Publication status	Published - 1 Jan 2005

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Funding

The work detailed within this paper was funded by Strategic Research Grant of City University of Hong Kong with reference no. 7001535.

Publisher's Copyright Statement

This full text is made available under CC-BY 3.0. https://creativecommons.org/licenses/by/3.0/

Access Output

10.1088/1742-6596/23/1/013

371262343.pdfFinal Published version, 355 KBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{43199ad6711045488b06fc7dd0da85bf,

title = "Development of ANN-based models to predict the static response and dynamic response of a heat exchanger in a real MVAC system",

abstract = "This paper presents a systematic approach to develop artificial neural network (ANN) models to predict the performance of a heat exchanger operating in real mechanical ventilation and air-conditioning (MVAC) system. Two approaches were attempted and presented. Every detailed components of the MVAC system have been considered and we attempt to model each of them by one ANN. This study used the neural network technique to obtain a static and a dynamic model for a heat exchanger mounted in an air handler unit (AHU), which is the key component of the MVAC system. It has been verified that almost all of the predicted values of the ANN model were within 95\% - 105\% of the measured values, with a consistent mean relative error (MRE) smaller than 2.5\%. The paper details our experiences in using ANNs, especially those with back-propagation (BP) structures. Also, the weights and biases of our trained-up ANN models are listed out, which serve as good reference for readers to deal with their own situations. {\textcopyright} 2005 IOP Publishing Ltd.",

author = "Qinhua Hu and So, \{Albert T.P.\} and Tse, \{W. L.\} and Qingchang Ren",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].",

year = "2005",

month = jan,

day = "1",

doi = "10.1088/1742-6596/23/1/013",

language = "English",

volume = "23",

pages = "110--121",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing",

number = "1",

}

TY - JOUR

T1 - Development of ANN-based models to predict the static response and dynamic response of a heat exchanger in a real MVAC system

AU - Hu, Qinhua

AU - So, Albert T.P.

AU - Tse, W. L.

AU - Ren, Qingchang

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2005/1/1

Y1 - 2005/1/1

N2 - This paper presents a systematic approach to develop artificial neural network (ANN) models to predict the performance of a heat exchanger operating in real mechanical ventilation and air-conditioning (MVAC) system. Two approaches were attempted and presented. Every detailed components of the MVAC system have been considered and we attempt to model each of them by one ANN. This study used the neural network technique to obtain a static and a dynamic model for a heat exchanger mounted in an air handler unit (AHU), which is the key component of the MVAC system. It has been verified that almost all of the predicted values of the ANN model were within 95% - 105% of the measured values, with a consistent mean relative error (MRE) smaller than 2.5%. The paper details our experiences in using ANNs, especially those with back-propagation (BP) structures. Also, the weights and biases of our trained-up ANN models are listed out, which serve as good reference for readers to deal with their own situations. © 2005 IOP Publishing Ltd.

AB - This paper presents a systematic approach to develop artificial neural network (ANN) models to predict the performance of a heat exchanger operating in real mechanical ventilation and air-conditioning (MVAC) system. Two approaches were attempted and presented. Every detailed components of the MVAC system have been considered and we attempt to model each of them by one ANN. This study used the neural network technique to obtain a static and a dynamic model for a heat exchanger mounted in an air handler unit (AHU), which is the key component of the MVAC system. It has been verified that almost all of the predicted values of the ANN model were within 95% - 105% of the measured values, with a consistent mean relative error (MRE) smaller than 2.5%. The paper details our experiences in using ANNs, especially those with back-propagation (BP) structures. Also, the weights and biases of our trained-up ANN models are listed out, which serve as good reference for readers to deal with their own situations. © 2005 IOP Publishing Ltd.

UR - https://www.scopus.com/pages/publications/25844445994

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-25844445994&origin=recordpage

U2 - 10.1088/1742-6596/23/1/013

DO - 10.1088/1742-6596/23/1/013

M3 - RGC 21 - Publication in refereed journal

SN - 1742-6588

VL - 23

SP - 110

EP - 121

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

IS - 1

ER -

Development of ANN-based models to predict the static response and dynamic response of a heat exchanger in a real MVAC system

Abstract

Bibliographical note

Funding

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this