Machine learning based models for defect detection in composites inspected by Barker coded thermography: A qualitative analysis

• Published in: Advances in engineering software (1992) 2023-04, Vol.178, p.103425, Article 103425
• Main Authors: Parvez M, Muzammil, Mishra, Shailendra Kumar, Nandini, K., Ahammad, Sk Hasane, Inthiyaz, Syed, Altahan, Baraa Riyadh, Smirani, Lassaad K., Hossain, Md. Amzad, Rashed, Ahmed Nabih Zaki
• Format: Article
• Language: English
• Subjects: Anomaly detection; Barker code excitation; Infrared non-destructive testing (IRNDT); One class support vector machine; Support vector machine
• ISSN: 0965-9978
• DOI: 10.1016/j.advengsoft.2023.103425

•Machine learning and artificial intelligence have evolved as enablers for automation in various industrial applications.•Barker-coded thermography is an active thermal non-destructive testing technique for examining subsurface features in industrial components.•This article introduces supervised and unsupervised machine learning models for automatic defect detection in composite specimens inspected by the barker-coded stimulus.•This work provides supervised and unsupervised machine learning methods to detect defects in composite specimens examined with a barker automatically coded stimulus.•The suggested technology is tested using a carbon fiber-reinforced polymer sample with synthetically reproduced flat bottom hole flaws.•The one-class backing vector machine is chosen for the unsupervised class of operation, whereas the supervised technique modifies the traditional SVM.•The qualitative comparison suggests that the unsupervised approach presents a less than 1% marginal difference in defect detection from its supervised counterpart. Machine learning and artificial intelligence have evolved as enablers for automation in various industrial applications. Barker-coded thermography is an active thermal non-destructive testing technique for examining subsurface features in industrial components. This article introduces supervised and unsupervised machine learning models for automatic defect detection in composite specimens inspected by the barker-coded stimulus. This work provides supervised and unsupervised machine learning methods to detect defects in composite specimens examined with a barker automatically coded stimulus. The suggested technology is tested using a carbon fiber-reinforced polymer sample with synthetically reproduced flat bottom hole flaws. The one-class Support vector machine is chosen for the unsupervised class of operation, whereas the supervised technique modifies the traditional Support Vector Machine (SVM). The qualitative comparison suggests that the unsupervised approach presents a less than 1% marginal difference in defect detection from its supervised counterpart.