A TWO-STEP STRUCTURAL DAMAGE DETECTION APPROACH BASED ON WAVELET PACKET ANALYSIS AND NEURAL NETWORK

摘要：

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.

关键词： Damage detection wavelet packet analysis probabilistic neural network back-propagation network wavelet packet node energy change

作者: YAN-SONG DIAO HUA-JUN LI YAN WANG

作者单位: Civil Engineering College, Qingdao Technological University, Qingdao, 266033, China;Engineering Coll Engineering College,Ocean University of China,Qingdao,266071,China Civil Engineering College, Qingdao Technological University, Qingdao, 266033, China

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 3128-3133

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）