USE OF NEURAL NETWORKS IN DETECTION OF STRUCTURAL DAMAGE

Damage to structures may be caused as a result of normal operations, accidents, deterioration or severe natural events such as earthquakes and storms. Most often the extent and the location of the damage can be determined through visual inspection. However, in some cases visual inspection may not be feasible. The study reported in this paper is the first stage of a research aimed at developing automatic monitoring methods for detection of structural damage. In this feasibility study we have explored the use of the self-organization and learning capabilities of neural networks in structural damage assessment. The basic strategy is to train a neural network to recognize the behavior of the undamaged structure as well as the behavior of the structure with various possible damage states. When the trained network is subjected to the measurements of the structural response, it should be able to detect any existing damage. We have tried this basic idea on a simple structure and the results are promising.