Capacity determination of steel frame systems according to artifical neural network analysis

Erdem R.T.; Seker S.; Gücüyen E.; Bagci M.

Capacity determination of steel frame systems according to artifical neural network analysis

Date

2011

Authors

Publisher

CI-Premier Pte Ltd

Abstract

Many damages and losses have been occurred after the major scaled earthquakes. Researches have been developed in structural engineering along with other engineering fields with parallel to scientific developments. Determination of collapse safeties of buildings is one of the most efficient ways to observe the behavior of them. Artificial neural networks are computing systems that simulate the biological neural systems of the human brain. Neural Networks types are widely used for engineering problems. Artificial neural network analysis is known as a complex system of the neurons that are connected each other with different influence level. It is composed of a large number of highly interconnected neurons working in unison to solve specific problems. The approach is based on biological models of the human brain's functions. Computation is modeled as a large network of interconnected simple processors and artificial neural network analysis can be trained to recognize input patterns and produce appropriate output responses. The problems that have sufficient training data are suitable for artificial neural network analysis. Prediction of the complex problems and fast evaluation of new examples are the mainly advantages of artificial neural network analysis. In this study, forty steel frame systems which have constant span length and story height are analysed. Earthquake loads are calculated for the frame systems and capacity curves are obtained by using SAP2000 analysis program. The results are evaluated by artificial neural network analysis. The database includes thirty two frames data for training and eight ones for testing the network. Finally the results are compared and given in figures. Suggestions are also proposed.