Structural Health Monitoring (SHM) of cantilever beam using support vector machine

Abstract

In this article, the effectiveness of Support Vector Machine (SVM) is examined for health monitoring of beam using first mode shape data at twelve different damage locations for twelve damage intensities. The SVM is used to predict the location as well as intensity of damage. The performance of SVM is studied by adding white Gaussian noise to the mode-shape data. The study is carried out in two stages - in the first stage damage location is predicted, and for that predicted location, the damage intensity is found in stage 2. The reported results demonstrate the use of SVM as a powerful tool for structural health monitoring which does not require use of data of healthy state.