A study of machine learning object detection performance for phased array ultrasonic testing of carbon fibre reinforced plastics

Tunukovic, Vedran and McKnight, Shaun and Mohseni, Ehsan and Pierce, S. Gareth and Pyle, Richard and Duernberger, Euan and Loukas, Charalampos and Vithanage, Randika K.W. and Lines, David and Dobie, Gordon and MacLeod, Charles N. and Cochran, Sandy and O'Hare, Tom (2024) A study of machine learning object detection performance for phased array ultrasonic testing of carbon fibre reinforced plastics. NDT and E International, 144. 103094. ISSN 0963-8695 (https://doi.org/10.1016/j.ndteint.2024.103094)

[thumbnail of Tunukovic-etal-NDTEI-2024-A-study-of-machine-learning-object-detection-performance-for-phased-array-ultrasonic-testing]
Preview
 Text. Filename: Tunukovic-etal-NDTEI-2024-A-study-of-machine-learning-object-detection-performance-for-phased-array-ultrasonic-testing.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (14MB)| Preview

Abstract

The growing adoption of Carbon Fibre Reinforced Plastics (CFRPs) in the aerospace industry has resulted in a significant reliance on Non-Destructive Evaluation (NDE) to ensure the quality and integrity of these materials. The interpretation of large amounts of data acquired from automated robotic ultrasonic scanning by expert operators is often time consuming, tedious, and prone to human error creating a bottleneck in the manufacturing process. However, with ever growing trend of computing power and digitally stored NDE data, intelligent Machine Learning (ML) algorithms have been gaining more traction than before for NDE data analysis. In this study, the performance of ML object detection models, statistical methods for defect detection, and traditional amplitude thresholding approaches for defect detection in CFRPs were compared. A novel augmentation technique was used to enhance synthetically generated datasets used for ML model training. All approaches were tested on real data obtained from an experimental setup mimicking industrial conditions, with ML models showing improvement over amplitude thresholding and statistical thresholding techniques. The advantages and limitations of all methods are reported and discussed.

ORCID iDs

Tunukovic, Vedran ORCID logoORCID: https://orcid.org/0000-0002-3102-9098, McKnight, Shaun, Mohseni, Ehsan ORCID logoORCID: https://orcid.org/0000-0002-0819-6592, Pierce, S. Gareth ORCID logoORCID: https://orcid.org/0000-0003-0312-8766, Pyle, Richard ORCID logoORCID: https://orcid.org/0000-0002-5236-7467, Duernberger, Euan, Loukas, Charalampos ORCID logoORCID: https://orcid.org/0000-0002-3465-8076, Vithanage, Randika K.W. ORCID logoORCID: https://orcid.org/0000-0002-1023-2564, Lines, David ORCID logoORCID: https://orcid.org/0000-0001-8538-2914, Dobie, Gordon ORCID logoORCID: https://orcid.org/0000-0003-3972-5917, MacLeod, Charles N. ORCID logoORCID: https://orcid.org/0000-0003-4364-9769, Cochran, Sandy and O'Hare, Tom;
CORE (COnnecting REpositories)