To identify the pattern of changes in vibrational signatures of a structure is a promising approach for on-line structure monitoring. Artificial neural networks, developed by researchers in cognitive sciences and artificial intelligence, can be used for this purpose. The main benefit of using artificial neural networks is their ability to diagnose signals that are fuzzy or imprecise. In this paper, neural networks were used to analyze the changes in vibrational signatures of a five-story, three dimensional, steel frame. The neural networks were first trained with a set of experimental data obtained from shake-table test results of the model. The capability of the neural networks to diagnose new signals was then tested against a separate set of experimental data. The results show that application of artificial neural networks in analyzing the changes in vibrational signatures of structures has considerable potential to structural damage diagnosis and condition monitoring.
|Number of pages||16|
|Journal||Journal of Engineering Mechanics|
|Publication status||Published - 1994 Feb|
All Science Journal Classification (ASJC) codes
- Mechanics of Materials
- Mechanical Engineering