Comparative Study of Backpropagation and Improved Counterpropagation Neural Nets in Structural Analysis and Optimization

Abstract

The present paper, describes the applications of two artificial neural networks, namely the backpropagation neural net (BPN) and the improved counterpropagation neural net (CPN) to the analysis and design of large scale space structures. Different aspects of these nets and parameters affecting the performance of each net is investigated. Two examples are studied, both of which are oriented towards structural optimization. A comparison is made on the performance of these nets The improved CPN is trained faster than BPN, especially when large scale problems are involved. The responses of BPN and improved CPN are compared for the same input.

Neural Networks for the Analysis and Design of Domes

“…In the last decade neural networks are extensively employed in structural mechanics, Refs [4][5][6][7][8][9]. In the following, some basic concepts of neural networks is summarized, however, the interested reader may also refer to excellent textbooks on this subject [13][14][15].…”

“…This necessitates bigger changes in weights in the early stages of the learning process. Using the backpropagation procedure, the network calculates delta signals for the output layer and hidden layers, using Eqs (8) and 9, respectively. These deltas are employed to compute the changes for all the weight values according to Eq.…”

“…Neural networks provide a powerful tool for approximate analysis and design of space structures. Such networks are trained using backpropagation [4][5][6] and counterpropagation networks [7][8][9].…”

Prognosis of Wind-tempted Mean Pressure Coefficients of Cross-shaped Tall Buildings Using Artificial Neural Network

“…ANN had a widespread application in the field of civil engineering since long. It was applied in the development of the backpropagation neural net and the improved counter-propagation neural net for the analysis and design of large scale space structures [17] and also for the presentation of a neurocomputing strategy combining neural networks and numerical structural optimization [18]. Again ANN was used to train efficient backpropagation neural networks for design of double-layer grids [19], to train neural networks that predict M-ф diagrams for the type of connection considered and for saddle-like connection with sufficient accuracy [20,21].…”

Neural Networks for the Approximate Analysis and Design of Double Layer Grids

“…Neural networks provide a powerful tool for approximate analysis and design of space structures. Such networks are trained using backpropagation [7][8][9][10][11] and counterpropagation networks [12][13][14][15]. For other applications of neural networks, the reader may refer to [16].…”