Damage assessment in structure from changes in static parameter using neural networks

摘要: Damage to structures may occur as a result of normal operations, accidents, deterioration or severe natural events such earthquakes and storms. Most often the extent location damage be determined through visual inspection. However, in some cases this not feasible. The basic strategy applied study is train neural network recognize behaviour undamaged structure well with various possible damaged states. When trained subjected measured response, it should able detect any existing damage. This idea on simple cantilever beam. Strain displacement are used candidates for identification by back-propagation network. superiority strain over has been observed