Automated structural health monitoring based on adaptive kernel spectral clustering

详细信息    查看全文

• 作者：Rocco Langone^a ; ^{rocco.langone@esat.kuleuven.be} ; Edwin Reynders^b ; Siamak Mehrkanoon^a ; Johan A.K. Suykens^a
• 关键词：Structural health monitoring ; Data normalization ; Novelty detection ; Bridge engineering ; Adaptive kernel spectral clustering
• 刊名：Mechanical Systems and Signal Processing
• 出版年：2017
• 出版时间：June 2017
• 年：2017
• 卷：90
• 期：Complete
• 页码：64-78
• 全文大小：2351 K
• 卷排序：90

文摘

An SHM approach unifying data normalization and damage detection is presented. The proposed methodology is based on an adaptive kernel spectral clustering model. An online calibration procedure is devised to adapt the initial hyper-parameters. Two different damage indicators are introduced.