Abstract
The objective of this study is to demonstrate that artificial neural networks (ANNs) serve as useful aids to heating, ventilating and air-conditioning (HVAC) system design. The design process for sizing fluid systems in HVAC is simulated by using ANNs. Four ANNs have been constructed in a personal computer, one for air duct sizing and three for pipe sizing. The air duct network was trained to output the friction rate and duct size. The three pipe sizing neural networks product pressure drops and pipe diameters. By using the trained artificial neural networks, we can obtain data instantly with errors less than 3%. Thus, ANNs are shown to simplify traditional methods and procedures in HVAC pipe and air duct sizing.
| Original language | English |
|---|---|
| Pages (from-to) | 282-286 |
| Number of pages | 5 |
| Journal | International Journal of Modelling and Simulation |
| Volume | 19 |
| Issue number | 3 |
| State | Published - Dec 1 1999 |
Fingerprint
ASJC Scopus subject areas
- Hardware and Architecture
- Modeling and Simulation
- Software
- Safety, Risk, Reliability and Quality
- Chemical Health and Safety
Cite this
HVAC pipe/duct sizing using artificial neural networks. / Yeh, Shaw Jee D; Wong, Kaufui.
In: International Journal of Modelling and Simulation, Vol. 19, No. 3, 01.12.1999, p. 282-286.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - HVAC pipe/duct sizing using artificial neural networks
AU - Yeh, Shaw Jee D
AU - Wong, Kaufui
PY - 1999/12/1
Y1 - 1999/12/1
N2 - The objective of this study is to demonstrate that artificial neural networks (ANNs) serve as useful aids to heating, ventilating and air-conditioning (HVAC) system design. The design process for sizing fluid systems in HVAC is simulated by using ANNs. Four ANNs have been constructed in a personal computer, one for air duct sizing and three for pipe sizing. The air duct network was trained to output the friction rate and duct size. The three pipe sizing neural networks product pressure drops and pipe diameters. By using the trained artificial neural networks, we can obtain data instantly with errors less than 3%. Thus, ANNs are shown to simplify traditional methods and procedures in HVAC pipe and air duct sizing.
AB - The objective of this study is to demonstrate that artificial neural networks (ANNs) serve as useful aids to heating, ventilating and air-conditioning (HVAC) system design. The design process for sizing fluid systems in HVAC is simulated by using ANNs. Four ANNs have been constructed in a personal computer, one for air duct sizing and three for pipe sizing. The air duct network was trained to output the friction rate and duct size. The three pipe sizing neural networks product pressure drops and pipe diameters. By using the trained artificial neural networks, we can obtain data instantly with errors less than 3%. Thus, ANNs are shown to simplify traditional methods and procedures in HVAC pipe and air duct sizing.
UR - http://www.scopus.com/inward/record.url?scp=0033357297&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033357297&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:0033357297
VL - 19
SP - 282
EP - 286
JO - International Journal of Modelling and Simulation
JF - International Journal of Modelling and Simulation
SN - 0228-6203
IS - 3
ER -