A Methodology for Advanced Manufacturing Defect Detection through Self-Supervised Learning on X-ray Images
Open Access
- 26 March 2024
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 14 (7) , 2785
Abstract
In industrial quality control, especially in the field of manufacturing defect detection, deep learning plays an increasingly critical role. However, the efficacy of these advanced models is often hindered by their need for large-scale, annotated datasets. Moreover, these datasets are mainly based on RGB images, which are very different from X-ray images. Addressing this limitation, our research proposes a methodology that incorporates domain-specific self-supervised pretraining techniques using X-ray imaging to improve defect detection capabilities in manufacturing products. We employ two pretraining approaches, SimSiam and SimMIM, to refine feature extraction from manufacturing images. The pretraining stage is carried out using an industrial dataset of 27,901 unlabeled X-ray images from a manufacturing production line. We analyze the performance of the pretraining against transfer-learning-based methods in a complex defect detection scenario using a Faster R-CNN model. We conduct evaluations on both a proprietary industrial dataset and the publicly available GDXray dataset. The findings reveal that models pretrained with domain-specific X-ray images consistently outperform those initialized with ImageNet weights. Notably, Swin Transformer models show superior results in scenarios rich in labeled data, whereas CNN backbones are more effective in limited-data environments. Moreover, we underscore the enhanced ability of the models pretrained with X-ray images in detecting critical defects, crucial for ensuring safety in industrial settings. Our study offers substantial evidence of the benefits of self-supervised learning in manufacturing defect detection, providing a solid foundation for further research and practical applications in industrial quality control.Keywords
Funding Information
- Department of Education, Universities and Research of the Basque Country (KK-2022/00049)
- ELKARTEK program (KK-2022/00049)
This publication has 39 references indexed in Scilit:
- Deep learning-based detection of aluminum casting defects and their typesEngineering Applications of Artificial Intelligence, 2022
- Inspection of sandblasting defect in investment castings by deep convolutional neural networkThe International Journal of Advanced Manufacturing Technology, 2022
- Target Detection by Target Simulation in X-ray TestingJournal of Nondestructive Evaluation, 2022
- Automated Defect Recognition of Castings Defects Using Neural NetworksJournal of Nondestructive Evaluation, 2021
- Aluminum Casting Inspection using Deep Object Detection Methods and Simulated Ellipsoidal DefectsMachine Vision and Applications, 2021
- Self-attention guided model for defect detection of aluminium alloy casting on X-ray imageComputers and Electrical Engineering, 2020
- Automated detection of defects with low semantic information in X-ray images based on deep learningJournal of Intelligent Manufacturing, 2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- GDXray: The Database of X-ray Images for Nondestructive TestingJournal of Nondestructive Evaluation, 2015
- Microsoft COCO: Common Objects in Context2014