Damage detection on an aluminum plate from the cross-correlation of diffuse field using the support vector machine

Abstract

In order to assess the damage detectability of the structural health monitoring method using diffuse fields, a laboratory experiment is conducted on an aluminum plate where two accelerometers are mounted as receivers. Two types of damages, a nonlinear material attachment and a punctuated hole, are considered. A hand-held impact hammer is used for the excitation, whereby the hammer is moved over grid points drawn on the aluminum plate, and thus the diffuse fields are generated by superposing the wave fields by many excitations randomly sampled. From the cross-correlation of diffuse fields between two receivers, we extract the coherent wave field in cases with and without damages. To detect the damage, a novel damage detection algorithm using a support vector machine is suggested based on the reduced features, transformed from several statistical parameters of damaged and undamaged noise cross-correlation functions, aided by the principal component analysis. The performance of the proposed algorithm is analyzed for the number of sources and damage types.