Back to Search
Start Over
Defect detection for industrial neutron radiographic images based on modified YOLO network.
- Source :
-
Nuclear Instruments & Methods in Physics Research Section A . Nov2023, Vol. 1056, pN.PAG-N.PAG. 1p. - Publication Year :
- 2023
-
Abstract
- Neutron radiography (NR) has been widely used in non-destructive investigations. Since the industrial neutron radiographic images (NRIs) usually suffer from unclear defect features, insufficient data volume, and low efficiency of manual detection, we propose a proof-of-concept defect-detection method based on the modified YOLO network for the degraded NRIs in this paper. Firstly, 6336 radiographic images including crack, inclusion, blow hole, and residual core are built as the defect-detection dataset. Secondly, the types and the relative coordinates of defects are labeled by a graphical image annotation tool (i.e., Labelimg). Finally, the adaptive spatial feature fusion (ASFF) and convolutional block attention module (CBAM) are introduced to the modified YOLO network to enhance its ability of small-size defect detection. Experimental results demonstrate that the proposed method can achieve the average accuracy of 98.1% and detection rate of 85.985 frames per second (FPS) with a single NVIDIA GeForce RTX 4090 GPU on the built radiographic image dataset. In addition, the proposed method shows a good potential in detecting the above defects contained in the real NRIs. • A YOLO network-based automatic defect detection method with higher accuracy and lower detection time is proposed. • Data augmentation is employed to build a large-scale radiographic-image dataset with 6336 defect images. • ASFF and CBAM are used to solve the inconsistency of different-scale features and enhance the small-size detection ability. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 01689002
- Volume :
- 1056
- Database :
- Academic Search Index
- Journal :
- Nuclear Instruments & Methods in Physics Research Section A
- Publication Type :
- Academic Journal
- Accession number :
- 172974913
- Full Text :
- https://doi.org/10.1016/j.nima.2023.168694