Predicting the pressure coefficients in a naturally ventilated test room using artificial neural networks

The objective of this work is to investigate the use of artificial neural networks for the prediction of air pressure coefficients across the openings in a light weight single-sided naturally ventilated test room. Experimental values have been used for the training of the network. The outside ambien...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Building and environment 2003-03, Vol.38 (3), p.399-407
Hauptverfasser: Kalogirou, Soteris, Eftekhari, Mahroo, Marjanovic, Ljiljana
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The objective of this work is to investigate the use of artificial neural networks for the prediction of air pressure coefficients across the openings in a light weight single-sided naturally ventilated test room. Experimental values have been used for the training of the network. The outside ambient temperature, wind velocity and direction are monitored. The pressure coefficients at the top and bottom of the openings have been estimated from the recorded data of air pressures and velocities across the openings together with indoor air temperatures. The collected data together with the air heater load and a factor indicating whether the opening is in the windward (1) or leeward (0) direction are used as input to the neural network and the estimated pressure coefficients as the output. A general regression neural network was employed with two hidden layers. The training was performed with satisfactory accuracy and correlation coefficients of 0.9539 and 0.9325 have been obtained for the two coefficients, respectively. Satisfactory results have been obtained when unknown data were used as input to the network with correlation coefficients of 0.9575 and 0.9320, respectively. These are slightly better than the training values due to the variability of the data contained in the validation data set.
ISSN:0360-1323
1873-684X
DOI:10.1016/S0360-1323(02)00032-X