Bakhary, Norhisham and Hao, H. and Deeks, A. J. (2010) Structure damage detection using neural network with multi-stage substructuring. Advances in Structural Engineering, 13 (1). 95 -110. ISSN 1369-4332
Full text not available from this repository.
Official URL: http://dx.doi.org/10.1260/1369-43184.108.40.206
Artificial neural network (ANN) method has been proven feasible by manyresearchers in detecting damage based on vibration parameters. However, the maindrawback of ANN method is the requirement of enormous computational effortespecially when complex structures with large degrees of freedom are involved.Consequently, almost all the previous works described in the literature limited thestructural members to a small number of large elements in the ANN model whichresulted ANN model being insensitive to local damage. This study presents anapproach to detect small structural damage using ANN method with progressivesubstructure zooming. It uses the substructure technique together with a multi-stageANN models to detect the location and extent of the damage. Modal parameters suchas frequencies and mode shapes are used as input to ANN. To demonstrate theeffectiveness of this approach, a two-span continuous concrete slab structure and athree-storey portal frame are used as examples. Different damage scenarios have beenintroduced by reducing the local stiffness of the selected elements at different locationsin the structures. The results show that this technique successfully detects all thesimulated damages in the structure.
|Uncontrolled Keywords:||damage detection, neural networks, substructure, modal data|
|Subjects:||T Technology > TA Engineering (General). Civil engineering (General)|
|Deposited By:||Liza Porijo|
|Deposited On:||18 Jul 2012 01:48|
|Last Modified:||13 Feb 2017 00:40|
Repository Staff Only: item control page