Intelligent structure health diagnosis based on neural networks

Identifying changes in the vibrational signatures of a structure is a promising tool in structural health diagnosis. Neural networks can be used for this purpose. This paper investigates the feasibility of using analytically generated training samples to train neural networks. This network, trained with analytically generated states of damage, was used to diagnose damage states obtained experimentally from a series of shaking table tests of s five-story steel frame. The results show that neural networks have a strong potential for making on-line structural health diagnosis a practical reality.