Deploying Machine Learning for Radiography of Aerospace Welds
Authors:
- Topias TyystjärviTTTopias Tyystjärvi
- Peter FridolfPFPeter Fridolf
- Anders RosellARAnders Rosell
- Iikka VirkkunenIVIikka Virkkunen
Open Access
- 28 January 2024
- journal article
- research article
- Published by Springer Nature in Journal of Nondestructive Evaluation
- Vol. 43 (1) , 1-13
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.Keywords
Funding Information
- Aalto University
This publication has 39 references indexed in Scilit:
- Automatic Defect Recognition in X-Ray Testing Using Computer Vision2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- A survey of transfer learningJournal of Big Data, 2016
- A human factors perspective on the use of automated aids in the evaluation of NDT dataAIP Conference Proceedings, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- GDXray: The Database of X-ray Images for Nondestructive TestingJournal of Nondestructive Evaluation, 2015
- Edge-centric ComputingACM SIGCOMM Computer Communication Review, 2015
- Deep learningNature, 2015
- The rise of “big data” on cloud computing: Review and open research issuesInformation Systems, 2015
- Comparison of the CRLC Models Describing the Helmholtz Type Cells for the Nondestructive Photoacoustic SpectroscopyMetrology and Measurement Systems, 2014