Automated Impact Damage Detection Technique for Composites Based on Thermographic Image Processing and Machine Learning Classification

Muflih Alhammad; Nicolas P Avdelidis; Clemente Ibarra-Castanedo; Muhammet E Torbali; Marc Genest; Hai Zhang; Argyrios Zolotas; Xavier P V Maldgue

doi:10.3390/s22239031

Automated Impact Damage Detection Technique for Composites Based on Thermographic Image Processing and Machine Learning Classification

Sensors (Basel). 2022 Nov 22;22(23):9031. doi: 10.3390/s22239031.

Authors

Muflih Alhammad¹, Nicolas P Avdelidis^{1

2}, Clemente Ibarra-Castanedo², Muhammet E Torbali¹, Marc Genest³, Hai Zhang^{2

4}, Argyrios Zolotas¹, Xavier P V Maldgue²

Affiliations

¹ School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 0AL, UK.
² Computer Vision and Systems Laboratory, Department of Electrical and Computer Engineering, University Laval, Quebec City, QC G1V 0A6, Canada.
³ National Research Council Canada, Ottawa, ON K1A 0R6, Canada.
⁴ Centre for Composite Materials and Structures (CCMS), Harbin Institute of Technology, Harbin 150001, China.

Abstract

Composite materials are one of the primary structural components in most current transportation applications, such as the aerospace industry. Composite material diagnostics is a promising area in the fight against structural damage in aircraft and spaceships. Detection and diagnostic technologies often provide analysts with a valuable and rapid mechanism to monitor the health and safety of composite materials. Although many attempts have been made to develop damage detection techniques and make operations more efficient, there is still a need to develop/improve existing methods. Pulsed thermography (PT) technology was used in this study to obtain healthy and defective data sets from custom-designed composite samples having similar dimensions but different thicknesses (1.6 and 3.8). Ten carbon fibre-reinforced plastic (CFRP) panels were tested. The samples were subjected to impact damage of various energy levels, ranging from 4 to 12 J. Two different methods have been applied to detect and classify the damage to the composite structures. The first applied method is the statistical analysis, where seven different statistical criteria have been calculated. The final results have proved the possibility of detecting the damaged area in most cases. However, for a more accurate detection technique, a machine learning method was applied to thermal images; specifically, the Cube Support Vector Machine (SVM) algorithm was selected. The prediction accuracy of the proposed classification models was calculated within a confusion matrix based on the dataset patterns representing the healthy and defective areas. The classification results ranged from 78.7% to 93.5%, and these promising results are paving the way to develop an automated model to efficiently evaluate the damage to composite materials based on the non-distractive testing (NDT) technique.

Keywords: composite materials; damage diagnosis; impact damage; infrared thermography; machine learning; principal component thermography; pulsed phase thermography; support vector machine; thermographic images.

MeSH terms

Algorithms
Image Processing, Computer-Assisted* / methods
Machine Learning
Support Vector Machine
Thermography*

Grants and funding

This research received no external funding.