Structural damage detection by integrating independent component analysis and support vector machine

Abstract

Structural damage detection in an early stage is very important for reducing catastrophic failures and prolonging the service life of structures. In this article, a novel approach that integrates independent component analysis (ICA) and support vector machines (SVMs) is presented. The procedure involves extracting independent components from measured sensor data through ICA, and then using these components as input data for an SVM classifier. The experiment presented employs benchmark data from University of British Columbia in order to examine the effectiveness of the method. Results show that the accuracy of damage detection using the proposed method is significantly better than that of the approach by integrating ICA and artificial neural network. Furthermore, the prediction output can be used to identify different types and levels of structure damages.