Damage assessment of structures from changes in curvature damage factor using artificial neural network

Abstract

This paper presents a neural network based approach to detect and assess the structural damage. The basic strategy applied in this study is to train a neural network to recognize the behaviour of the undamaged structure as well as the structure with various possible damaged states. Curvature damage factor (CDF) is used as a possible candidate for the damage identification by error back-propagation training algorithm (EBPTA). When this trained network is subjected to the measured response, it should be able to detect any existing damage. This idea is applied on a cantilever beam and a plane frame. The results show the efficiency of the developed algorithm.