To guarantee the safety and avoid disaster, the scholars, the engineers and technicians are paying great attention to the research of identification of the structural damage real-timely, on-line and accurately. The damage identification is a polytechnic method constructed on the damage theory, sensor technology, signal analysis, computer science and artificial networks. This paper mainly studies the method based on the combination of the static modal analysis and artificial networks.Firstly, the principle of structural damage detection by using artificial neural network (ANN) is expounded in the paper. Some main achievements are summarized. Secondly, the paper is verified theoretically that the natural frequency changes of structure contain the information such as location and degree of the damage. Finally, based on this theory, we simulated different damages of suspended beam and shaft to extract natural frequency, then considered the natural frequency as the input parameter of BP and RBF neural network through matlab, and detected the structural damage by the trained networks. The results show the effectiveness of this method. |