Use of the wavelet packet transform for pattern recognition in a structural health monitoring application

Abstract

In the last decades, a huge effort has been dedicated to the development of vibration-based techniques for damage detection. In this article, an algorithm based on the wavelet packet transform and the Karhunen–Loéve transform is analysed to perform a pattern recognition application for the structural health monitoring purpose. In this article, the wavelet packet transform is used to decompose the signals coming from an accelerometer on a vibrating composite beam. The configuration of the beam has been changed and the wavelet packet transform was tested as a feature extraction tool. Then the Karhunen–Loéve transform was applied to the data to classify the different patterns and to test its capability of pattern recognition.