期刊
SENSORS
卷 22, 期 11, 页码 -出版社
MDPI
DOI: 10.3390/s22114130
关键词
deep learning; semantic segmentation; laser welding; seam tracking
资金
- Six Top Talents High-level talents selection and cultivation projects in Jiangsu Province [GDZB-040]
In this study, a weld tracking module was designed to capture real-time images of the weld in order to obtain accurate position information of the weld joint. By utilizing an encoder-decoder architecture to design a lightweight network structure and introducing a channel attention mechanism, the network model achieved faster segmentation speed and higher segmentation accuracy.
Laser welding is an indispensable link in most types of industrial production. The realization of welding automation by industrial robots can greatly improve production efficiency. In the research and development of the welding seam tracking system, information on the position of the weld joint needs to be obtained accurately. For laser welding images with strong and complex interference, a weld tracking module was designed to capture real-time images of the weld, and a total of 737, 1920 x 1200 pixel weld images were captured using the device, of which 637 were used to create the dataset, and the other 100 were used as images to test the segmentation success rate. Based on the pixel-level segmentation capability of the semantic segmentation network, this study used an encoder-decoder architecture to design a lightweight network structure and introduced a channel attention mechanism. Compared to ERF-Net, SegNet, and DFA-Net, the network model in this paper has a fast segmentation speed and higher segmentation accuracy, with a success rate of 96% and remarkable segmentation results.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据