Title :
A Two-Step Structural Damage Detection Approach Based on Wavelet Packet Analysis and Neural Network
Author :
Diao, Yan-song ; Li, Hua-jun ; Wang, Yan
Author_Institution :
Civil Eng. Coll., Qingdao Technol. Univ.
Abstract :
In this paper, a two-step structural damage detection approach based on wavelet packet analysis is presented. Firstly, the location of the damage member is determined by probabilistic neural network according to the wavelet packet node energy change. Secondly, the damage extent of the damaged member is determined by back-propagation network according to the wavelet packet node energy. The results of the numerical simulation demonstrate that the approach can detect the structural damage with good robustness
Keywords :
backpropagation; neural nets; structural engineering computing; wavelet transforms; backpropagation network; numerical simulation; probabilistic neural network; structural damage detection approach; wavelet packet analysis; Civil engineering; Cybernetics; Educational institutions; Frequency; Machine learning; Monitoring; Neural networks; Numerical simulation; Robustness; Shape; Wavelet analysis; Wavelet packets; Damage detection; back-propagation network; probabilistic neural network; wavelet packet analysis; wavelet packet node energy change;
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
DOI :
10.1109/ICMLC.2006.258404
