Abstract In this paper, the damage location of a bridge is identified using probabilistic neural networks. At first, modal parameters are identified from the ambient vibration data, and are utilized as the feature vectors for probabilistic neural networks. The class to be identified is defined according to the location of damaged structural members. To deal with a lot of structural members, the number of classes is reduced by grouping neighboring elements to one class. The effectiveness of the proposed method was demonstrated by means of a numerical example analysis on a simply supported bridge model with multiple girders, and by a field test on the northernmost span of the old Hannam Grand Bridge over the Han River in Seoul, Korea.
Damage localization for bridges using probabilistic neural networks
KSCE Journal of Civil Engineering ; 11 , 2 ; 111-120
2007-03-01
10 pages
Article (Journal)
Electronic Resource
English
Transportation Research Record | 2010
|