Structural Health Monitoring With Autoregressive Support Vector Machines
- 17 February 2009
- journal article
- Published by ASME International in Journal of Vibration and Acoustics
- Vol. 131 (2), 021004
- https://doi.org/10.1115/1.3025827
Abstract
The use of statistical methods for anomaly detection has become of interest to researchers in many subject areas. Structural health monitoring in particular has benefited from the versatility of statistical damage-detection techniques. We propose modeling structural vibration sensor output data using nonlinear time-series models. We demonstrate the improved performance of these models over currently used linear models. Whereas existing methods typically use a single sensor’s output for damage detection, we create a combined sensor analysis to maximize the efficiency of damage detection. From this combined analysis we may also identify the individual sensors that are most influenced by structural damage.Keywords
This publication has 15 references indexed in Scilit:
- Damage diagnosis using a kernel-based methodInsight - Non-Destructive Testing and Condition Monitoring, 2007
- An introduction to structural health monitoringPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2006
- The application of machine learning to structural health monitoringPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2006
- Real-time nondestructive structural health monitoring using support vector machines and waveletsPublished by SPIE-Intl Soc Optical Eng ,2005
- A tutorial on support vector regressionStatistics and Computing, 2004
- VIBRATION-BASED DAMAGE DETECTION USING STATISTICAL PROCESS CONTROLMechanical Systems and Signal Processing, 2001
- Damage identification using support vector machinesSmart Materials and Structures, 2001
- Structural Health Monitoring Using Statistical Process ControlJournal of Structural Engineering, 2000
- A Summary Review of Vibration-Based Damage Identification MethodsThe Shock and Vibration Digest, 1998
- Comparing support vector machines with Gaussian kernels to radial basis function classifiersIEEE Transactions on Signal Processing, 1997