Deploying Machine Learning for Radiography of Aerospace Welds
Применение машинного обучения для радиографического контроля сварных соединений в аэрокосмической отрасли
2024-01-28
SCID: 54.1/s6xrdkma
Discuss with AI
automatic defect recognitionindustrial radiographylaser weldsprobability of detectionweld segmentation
Figures from the paper
Abstract (AI)
Abstract Artificial intelligence is providing new possibilities for analysis in the field of industrial radiography. As capabilities evolve, there is the need for knowledge concerning how to deploy these technologies in practice and benefit from the new automatically generated information. In this study, automatic defect recognition based on machine learning was deployed as an aid in industrial radiography of laser welds in an aerospace component, and utilized to produce statistics for improved quality control. A multi-model approach with an added weld segmentation step improved the inference speed and decreased false calls to improve field use. A user interface with visualization options was developed to display the evaluation results. A dataset of 451 radiographs was automatically analysed, yielding 10037 indications with size and location information, providing capability for statistical analysis beyond what is practical to carry out with manual annotation. The distribution of indications was modeled as a product of the probability of detection and an exponentially decreasing underlying flaw distribution, opening the possibility for model reliability assessment and predictive capabilities on weld defects. An analysis of the indications demonstrated the capability to automatically detect both large-scale trends and individual components and welds that were more at risk of failing the inspection. This serves as a step towards smarter utilization of non-destructive evaluation data in manufacturing.
Key Findings
1
A multi-model approach with weld segmentation increased inference speed and reduced false calls, improving suitability for field use.
2
A visualization interface was developed, and automated analysis of 451 radiographs produced 10,037 indications with defect size and location information.
3
Automated indication analysis identified both large-scale defect trends and individual components or welds at greater risk of inspection failure.
4
Machine-learning-based automatic defect recognition was deployed to support industrial radiography of laser welds in an aerospace component.
5
Modeling indication distributions as detection probability multiplied by an exponentially decreasing flaw distribution enables weld-defect reliability assessment and prediction.
Research Object
laser welds in an aerospace component examined by industrial radiography
Research Subject
machine-learning-based automatic defect recognition and statistical analysis of weld indications for quality control, reliability assessment, and failure-risk identification
Publication Details
Publication Date
2024-01-28
Journal
Publisher
ISSN
Cited by
22
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
ImageNet classification with deep convolutional neural networks2017
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
ImageNet: A large-scale hierarchical image database2009
A survey on Image Data Augmentation for Deep Learning2019
A survey of transfer learning2016
Automated defect detection in digital radiography of aerospace welds using deep learning2022