Classification of flaw severity using pattern recognition for guided wave-based structural health monitoring

• Published in: Ultrasonics Vol. 54; no. 1; pp. 247 - 258
• Main Authors: Miller, Corey A., Hinders, Mark K.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2014
• Subjects: Aircraft - instrumentation; Algorithms; Aluminum; Aluminum - analysis; Aluminum - chemistry; Classification; Equipment Design; Equipment Failure Analysis - methods; Feature selection; Fingerprints; Health monitoring (engineering); Lamb waves; Materials Testing - methods; Pattern classification; Pattern Recognition, Automated - methods; Plates (structural members); Reconstruction; Scattering; Ultrasonography - methods; Lamb waves; Feature selection; Pattern classification
• ISSN: 0041-624X; 1874-9968
• DOI: 10.1016/j.ultras.2013.04.020

•A new method of flaw severity characterization using pattern classification is presented.•We explore advanced analysis techniques for studying multi-mode Lamb wave signals.•Pattern classification provides a formal method of characterizing flaw interaction.•Several feature selection techniques are explored that are unique for damage detection.•Experimental data shows agreement between predicted and known class labels. In this paper, the authors present a formal classification routine to characterize flaw severity in an aircraft-grade aluminum plate using Lamb waves. A rounded rectangle flat-bottom hole is incrementally introduced into the plate, and at each depth multi-mode Lamb wave signals are collected to study the changes in received signal due to mode conversion and scattering from the flaw. Lamb wave tomography reconstructions are used to locate and size the flaw at each depth, however information about the severity of the flaw is obscured when the flaw becomes severe enough that scattering effects dominate. The dynamic wavelet fingerprint is then used to extract features from the raw Lamb wave signals, and supervised pattern classification techniques are used to identify flaw severity with up to 80.7% accuracy for a training set and up to 51.7% accuracy on a series of validation data sets extracted from independent plate samples.