We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
THICKNESS MEASUREMENT OF IMMERSION METAL CARBON SLIDE BASED ON IMAGE SEGMENTATION.
- Authors
ZHENG, A. Y.; CHANG, C. Y.; LIU, W. M.; QIAO, S. G.
- Abstract
The thickness of a metal-immersed carbon slide mounted on a train's flow shoe was measured by using machine vision and deep learning. A method for measuring the thickness of carbon slide plate based on improved U²-Net is proposed. Aiming at the problem that the edge feature extraction is not obvious, a new feature extraction module is designed. Efficient Channel Attention (ECA) mechanism and pool residual structure are used to make the network more suitable for metal-immersed carbon slide image segmentation. The experimental results show that the improved U²-Net network accuracy reaches 99,4 %, and the average absolute error is only 0,4 %. The thickness measurement accuracy of metallized carbon slide using improved U²-Net network reaches 0,5 mm.
- Subjects
U2 (Performer); IMAGE segmentation; THICKNESS measurement; COMPUTER vision; DEEP learning; FEATURE extraction; CARBON
- Publication
Metalurgija, 2024, Vol 63, Issue 3/4, p451
- ISSN
0543-5846
- Publication type
Article