Title
A Hybrid Data Driven Technique For Long Term Monitoring Of Structures
Abstract
Data interpretation is a challenging step for the monitoring of structures. Moving Principal Component Analysis (MPCA) has shown promising performance as a model free damage detection algorithm, which can be implemented for long-term monitoring of civil structures. Regardless of all the advantages associated with MPCA, it still has a main drawback which makes it less effective for long-term monitoring of critical structures. MPCA should be improved significantly in terms of time to detection. Therefore, the objective of this paper is to investigate and develop a new data interpretation approach based on principal component analysis but with less delay in detection. The efficiency of this innovative data interpretation approach (MPCASVM) is further investigated with the data from both lab study and a unique real-life structure. It has been observed from both lab and real-life study that MPCA-SVM outperforms MPCA in terms of time to detection.
Publication Date
1-1-2013
Publication Title
Structural Health Monitoring 2013: A Roadmap to Intelligent Structures - Proceedings of the 9th International Workshop on Structural Health Monitoring, IWSHM 2013
Volume
2
Number of Pages
1969-1976
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
84945205988 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84945205988
STARS Citation
Malekzadeh, M. and Catbas, N., "A Hybrid Data Driven Technique For Long Term Monitoring Of Structures" (2013). Scopus Export 2010-2014. 7493.
https://stars.library.ucf.edu/scopus2010/7493