In this paper, efficient neural networks are trained for the analysis, design and prediction of the displacements of domes using the Backpropagation and Radial Basis Functions neural networks. The performance of these networks is compared when applied to domes. Programs are developed for accurate distribution of applied forces and wind load to the nodal points of domes. Training and testing pairs are prepared by ANSYS software.
JenkinsW.M., Neural network-based approximations for structural analysis, Developments in Neural Networks and Evolutionary Computing for Civil and Structural Engineering, Edit. ToppingB.H.V., Civil-Comp Press, Edinburgh, 1995.
5.
WaszczyszynZ., Some recent and current problems of neurocomputing in civil and structural engineering, Edit. ToppingB.H.V., Civil-Comp Press, UK, 1996, pp. 43–58.
6.
KavehA.ServatiH., Design of double layer grids using artificial neural networks, Computers and Structures, 2001: Vol. 79: 1553–1568.
7.
HajelaP.BerkeL., Neurobiological computational models in structural analysis and design, Computers and Structures, 1991: Vol. 41: 657–667.
8.
KavehA.IranmaneshA., Comparative study of backpropagation and improved counterpropagation neural nets in structural analysis and optimization, International Journal of Space Structures, 1998: Vol. 13: 177–185.
9.
IranmaneshA.KavehA., Structural Optimisation by gradient base neural networks, Int. J. Numer. Meths Engng., 1999: Vol. 46: 297–311.
10.
NeuralWare, Using NeuralWorks, NeuralWare, USA, 1993.
