Automated defect detection in digital radiography of aerospace welds using deep learning
Автоматическое обнаружение дефектов при цифровой радиографии аэрокосмических сварных соединений с использованием глубокого обучения
2022-02-24
SCID: 54.1/4mmfmv6m
Discuss with AI
aerospace weldsdeep learningdigital radiographysemantic segmentationvirtual flaw augmentation
Figures from the paper
Abstract (AI)
Abstract Aerospace welds are non-destructively evaluated (NDE) during manufacturing to identify defective parts that may pose structural risks, often using digital radiography. The analysis of these digital radiographs is time consuming and costly. Attempts to automate the analysis using conventional computer vision methods or shallow machine learning have not, thus far, provided performance equivalent to human inspectors due to the high reliability requirements and low contrast to noise ratio of the defects. Modern approaches based on deep learning have made considerable progress towards reliable automated analysis. However, limited data sets render current machine learning solutions insufficient for industrial use. Moreover, industrial acceptance would require performance demonstration using standard metrics in non-destructive evaluation, such as probability of detection (POD), which are not commonly used in previous studies. In this study, data augmentation with virtual flaws was used to overcome data scarcity, and compared with conventional data augmentation. A semantic segmentation network was trained to find defects from computed radiography data of aerospace welds. Standard evaluation metrics in non-destructive testing were adopted for the comparison. Finally, the network was deployed as an inspector’s aid in a realistic environment to predict flaws from production radiographs. The network achieved high detection reliability and defect sizing performance, and an acceptable false call rate. Virtual flaw augmentation was found to significantly improve performance, especially for limited data set sizes, and for underrepresented flaw types even at large data sets. The deployed prototype was found to be easy to use indicating readiness for industry adoption.
Key Findings
1
A prototype deployed on production radiographs was easy to use, indicating readiness for adoption as an inspector-assistance tool.
2
A semantic segmentation network was trained to detect and size defects in computed radiographs of aerospace welds.
3
The deep-learning system achieved high detection reliability, strong defect-sizing performance, and an acceptable false-call rate.
4
The study evaluated performance using standard nondestructive-testing metrics, including probability of detection, supporting industrial relevance.
5
Virtual-flaw data augmentation significantly improved detection performance, particularly with limited datasets and underrepresented flaw types.
Research Object
digital radiographs of aerospace welds containing manufacturing defects
Research Subject
deep-learning-based automated defect detection, segmentation, sizing performance, detection reliability, and false call rate, including the effects of virtual flaw augmentation
Publication Details
Publication Date
2022-02-24
Journal
Publisher
ISSN
Cited by
84
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
Deep Residual Learning for Image Recognition2016
ImageNet classification with deep convolutional neural networks2017
ImageNet: A large-scale hierarchical image database2009
Learning Deep Features for Discriminative Localization2016
Object Detection With Deep Learning: A Review2019
Augmented Ultrasonic Data for Machine Learning2021
Cited by4
Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey2023
Advances and Challenges in Deep Learning for Automated Welding Defect Detection: A Technical Survey2025
Deploying Machine Learning for Radiography of Aerospace Welds2024
Towards Enhancing Automated Defect Recognition (ADR) in Digital X-ray Radiography Applications: Synthesizing Training Data through X-ray Intensity Distribution Modeling for Deep Learning Algorithms2023