Independent Component Analysis for Improved Defect Detection in Guided Wave

J. DOBSON, P. CAWLEY

Abstract


This paper proposes a novel approach for separating defect signals from coherent noise in guided wave monitoring data. This is achieved using independent component analysis (ICA), a technique which decomposes monitoring data into constituent signal elements. ICA is applied to guided wave signals from a range of industrial inspection scenarios, with analysis performed on test data from pipe loops that have been subject to multiple temperature cycles both in undamaged and damaged states. In addition to processing data from experimental damaged conditions, simulated damage signals have been added to `undamaged' experimental data, so enabling multiple different damage scenarios to be investigated. In all scenarios investigated the independent component analysis algorithm was able to extract the defect signal, rejecting coherent noise.

doi: 10.12783/SHM2015/234


Full Text:

 Subscribers Only