Postprint version. Published in Proceedings of the 15th Annual ASCE Engineering Mechanics Conference 2002: New York, New York, June 2, 2002. ©American Society of Civil Engineers.
At the time of publication, the author Mohammad N.Noori was affiliated with North Carolina State University. Currently, August 2008, he is the Dean of the College of Engineering at California Polytechnic State University - San Luis Obispo.
Accurate spatial and temporal estimation of wind loads on structures plays an important role in the design and construction of buildings in coastal regions and open terrains. The common approach to this problem is using codes and standards obtained from wind-tunnel tests on isolated structures. The use of artificial neural networks for finding specific patterns in data obtained from wind-tunnel and field tests has been reported in the literature. In this study localized radial basis functions neural networks are proposed and successfully used for estimation of wind loads on a three-story shear building using a state-space model of the structure.