Computational & Technology Resources
an online resource for computational,
engineering & technology publications
ARTIFICIAL INTELLIGENCE APPLICATIONS IN CIVIL AND STRUCTURAL ENGINEERING
Edited by: B. Kumar and B.H.V. Topping
Analysis and Design of Double Layer Grids using Neural Networks
A. Kaveh and H. Servati
Iran University of Science and Technology, Tehran, Iran
A. Kaveh, H. Servati, "Analysis and Design of Double Layer Grids using Neural Networks", in B. Kumar, B.H.V. Topping, (Editors), "Artificial Intelligence Applications in Civil and Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 93-101, 1999. doi:10.4203/ccp.62.4.2
Keywords: double layer grids, neural networks, backpropagation, maximum deflection, weight, design, data ordering..
In this paper efficient neural networks are trained for design of double layer grids. Square oblique-on-oblique grids with spans varying between 25 and 75 meters are considered. Backpropagation algorithm is employed for training efficient neural networks for evaluation of the maximum deflection, weight, and design of double layer grids. A special method is developed for data ordering to reduce the nonlinearity of the data and to increase the speed of training. This approach also provides the necessary stability. Additional neural nets are trained and tested for design of grids using the developed data ordering.
purchase the full-text of this paper (price £20)