Time series analysis methods are being increasingly investigated for the use of Structural Health Monitoring (SHM). In this research, Autoregressive (AR) models were used to fit the acceleration time histories obtained from the ASCE Phase II Experimental SHM Benchmark Structure in undamaged and various damaged states. The coefficients of AR models were considered to be damage sensitive features and used as inputs into an Artificial Neural Network (ANN). The ANN was trained to detect and classify damage into several states. The results show that the combination of AR models and ANNs is an efficient tool for damage detection and classification.
|Title of host publication||Proceedings of the 2007 Meeting of Asian-Pacific Network of Centers for Earthquake Engineering Research|
|Number of pages||8|
|Publication status||Published - 29 May 2007|
Omenzetter, P., & De Lautour, O. R. (2007). Damage detection in ASCE SHM experimental benchmark problem. In Proceedings of the 2007 Meeting of Asian-Pacific Network of Centers for Earthquake Engineering Research (pp. 1-8) https://doi.org/10.13140/2.1.1231.5203