Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Artificial Neural Network-Based Prediction of Wind Pressure Coefficients on Buildings

Artificial Neural Network-Based Prediction of Wind Pressure Coefficients on Buildings Wind load acting on a building in presence of one or more interfering buildings usually varies when compared to isolated buildings. This effect of variations in wind loads due to presence of other interfering building is termed interference effect. This effect on wind loads is mainly governed by parameters such as geometry, orientation of the structures with respect to wind direction and upstream terrain conditions. The provisions made in design codes and standards with regard to the effect of interfering structures are inadequate for proper estimation of wind loads. As such, the structural designers opt for wind tunnel experiments to get accurate wind loading on these structures. Computational fluid dynamics (CFD) and artificial neural network (ANN) approaches are other alternative methods emerging in recent years. This paper discusses on the ANN approach to predict the pressure coefficients on building faces due to interference, which may be used further in calculating wind loads. Mean pressure coefficients on each face of principal building (building under investigation) are predicted and analyzed for 45º wind angle, in presence of an interfering building at different locations upstream of the principal building. There is a good agreement between the predicted results and those obtained using wind tunnel. The results show that ANN approach can serve as a better tool to predict wind loads at preliminary stage and make an initial estimation for different interfering cases compared to methods like CFD and experimental which are complex, time consuming and costlier. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of The Institution of Engineers (India): Series A Springer Journals

Loading next page...
 
/lp/springer-journals/artificial-neural-network-based-prediction-of-wind-pressure-Bm7pAGWjAn

References (19)

Publisher
Springer Journals
Copyright
Copyright © The Institution of Engineers (India) 2021
ISSN
2250-2149
eISSN
2250-2157
DOI
10.1007/s40030-021-00524-1
Publisher site
See Article on Publisher Site

Abstract

Wind load acting on a building in presence of one or more interfering buildings usually varies when compared to isolated buildings. This effect of variations in wind loads due to presence of other interfering building is termed interference effect. This effect on wind loads is mainly governed by parameters such as geometry, orientation of the structures with respect to wind direction and upstream terrain conditions. The provisions made in design codes and standards with regard to the effect of interfering structures are inadequate for proper estimation of wind loads. As such, the structural designers opt for wind tunnel experiments to get accurate wind loading on these structures. Computational fluid dynamics (CFD) and artificial neural network (ANN) approaches are other alternative methods emerging in recent years. This paper discusses on the ANN approach to predict the pressure coefficients on building faces due to interference, which may be used further in calculating wind loads. Mean pressure coefficients on each face of principal building (building under investigation) are predicted and analyzed for 45º wind angle, in presence of an interfering building at different locations upstream of the principal building. There is a good agreement between the predicted results and those obtained using wind tunnel. The results show that ANN approach can serve as a better tool to predict wind loads at preliminary stage and make an initial estimation for different interfering cases compared to methods like CFD and experimental which are complex, time consuming and costlier.

Journal

Journal of The Institution of Engineers (India): Series ASpringer Journals

Published: Mar 29, 2021

There are no references for this article.