Deep Learning-Based Automated Detection of Welding Defects in Pressure Pipeline Radiograph
Source abstract
Abstract
This study applies deep learning-based object detection technology to defect detection in weld radiographs, proposing a technical solution for accurately identifying the types and locations of defects in weld X-ray radiographs. The research encompasses the construction of a defect dataset, the design of a multi-model object detection network, and the development of an automated film evaluation algorithm. This technology significantly enhances the efficiency and accuracy of detecting and identifying harmful defects on weld radiographs, providing critical technical support for ensuring the safe operation and efficient maintenance of pipelines of pressure equipment.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Non-Destructive Testing Techniques · Ultrasonics and Acoustic Wave Propagation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Chongqing Special Equipment Inspection and Research Institute, Chongqing 401121, China
Key Laboratory of Electromechanical Equipment Security in Western Complex Environment, State Administration for Market Regulation, Chongqing 401121, China
School of Materials Science & Engineering, Beijing Institute of Technology, Beijing 100081, China
Chongqing Innovation Center, Beijing Institute of Technology, Chongqing 401100, China
Funding
Research Institution Performance Incentive Guidance Special Project · Science and Technology Project · Chongqing Administration for Market Regulation
References (21)
Show source-provided references
1. On the effect of the attention mechanism for automatic welding defects detection based on deep learning10.1016/j.eswa.2025.126386 ↗
2. Welding defects classification by weakly supervised semantic segmentatio10.1016/j.ndteint.2023.102899 ↗
3. Research on X-ray weld seam defect detection and size measurement method based on neural network self-optimization10.1016/j.engappai.2024.108045 ↗
4. Ensemble-based deep learning model for welding defect detection and classification10.1016/j.engappai.2024.108961 ↗
5. Wang, X., He, F., and Huang, X. (2024). A new method for deep learning detection of defects in X-ray images of pressure vessel welds. Sci. Rep., 14.10.1038/s41598-024-56794-9 ↗
6. A comprehensive review of welding defect recognitionfrom X-ray images10.1016/j.jmapro.2025.02.039 ↗
7. Weld defect identification and characterization in radiographic images using deep learning: Review10.1088/2631-8695/acdf3f ↗
8. Intelligent recognition of radiographic inspection film images of China-Russia east line pipeline
9. Dry sliding wear characteristics of NiP/TiN duplex coated aluminum alloy and wear analysis using response surface method10.1007/s11665-022-06695-7 ↗
10. Nondestructive testing of radiographic plug welds in nuclear power plant pipelines
11. Radiographic testing and process evaluation of BOSS welds in nuclear power plant
12. A three-dimensional spatial model method is used to evaluate welding defects in radiographic testing films
13. Study on the key technology for automatic detection of weld defect by radiography
14. Research on Processing Algorithms for X-ray Digital Images of Welding Defects
15. Defects Recognition Based on Support Vector Machine within Radiographic Testing Weld
16. Welding Defect Detection of X-Ray Images Based on Faster R-CNN Model
17. X-ray image detection model for multi-type welding defects based on improved RetinaNet
18. Liu, M., Chen, Y., He, L., Zhang, Y., and Xie, J. (2021). LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image. arXiv.
19. Application of artificial intelligence technology in radiographic inspection film evaluation system
20. Defect signal intelligent recognition of weld radiographs based on YOLO V5-IMPROVEMENT10.1016/j.jmapro.2023.05.058 ↗
21. Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning10.1007/s12008-023-01327-3 ↗