Thickness measurement of immersion metal carbon slide based on image segmentation
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 U<sup>2</sup>-Net is proposed. Aiming at the problem that the edge feature ex...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Croatian Metallurgical Society
2024-01-01
|
| Series: | Metalurgija |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/456163 |
| Summary: | 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 U<sup>2</sup>-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 U<sup>2</sup>-Net network reaches 0,5 mm. |
|---|---|
| ISSN: | 0543-5846 1334-2576 |