Title :
Analyzing multi-story buildings using hopfield neural network
Author :
Fakhrmoosavi, Seyyedeh Hoora ; Setayeshi, Saeed ; Mohammadi, Seyyed Davood Ojaghzadeh ; Bahar, Arash ; Beik, Hossein Arab Ali
Author_Institution :
Dept. of Comput. Eng., Islamic Azad Univ., Tehran, Iran
Abstract :
A simplified method based on neural network is presented to determine the displacements, forces and moments of a loaded structure. Different values of loads, bay length, and story height can be applied to the structure. The results are used for preliminary design of structure, although in many cases the difference between the results obtained by this approach and exact values can be ignored. Thus, the cost of design, which is due to iterative procedure of finding forces and determining the size of members, will be decreased significantly. Obtained results for a sample structure are compared with exact values.
Keywords :
CAD; Hopfield neural nets; structural engineering computing; Hopfield neural network; design; multistory buildings; structural loads; structure bay length; Bismuth; Content addressable memory; Hopfield network; Neural Network; multi-story building; preliminary design;
Conference_Titel :
Advanced Computer Theory and Engineering (ICACTE), 2010 3rd International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-6539-2
DOI :
10.1109/ICACTE.2010.5579584
