Damage quantification method using artificial neural network and static response with limited sensors

In this paper an effective method for structural damage identification via incomplete static response and artificial neural network is proposed. The presented method is based on the condensed stiffness matrices to formulate incomplete static responses as input parameters to the Feed-forward back propagation neural network. The performance of the proposed method for damage detection and estimation has been investigated using three examples, namely, two-span continuous beam, plane steel bridge and two story frame with and without noise in the static displacements containing several damages. Also, the effect of the discrepancy in stiffness between the finite element model and the actual tested system has been investigated. The obtained results indicate that the proposed method perform quite well in spite of the incomplete data and modeling errors.