WeldNet:A voxel-based deep learning network for point cloud annular weld seam detection  

作　　者：WANG Hui RONG YouMin XU JiaJun XIANG SongMing PENG YiFan HUANG Yu 

机构地区：[1]State Key Laboratory of Intelligent Manufacturing Equipment and Technology,Huazhong University of Science and Technology,Wuhan 430074,China [2]School of Mechanical Science and Engineering,Huazhong University of Science and Technology,Wuhan 430074,China

出　　处：《Science China(Technological Sciences)》2024年第4期1215-1225,共11页中国科学（技术科学英文版）

基　　金：supported by the Key Research&Development Plan of China(Grant No.2022YFB3404800);the Key Research&Development Plan of Hubei Province(Grant No.2021BAA195);the National Natural Science Foundation of China(Grant No.52188102)。

摘　　要：Weld seam detection is an important part of automated welding.At present,few studies have been conducted on annular weld seams,and a lot of defects exist in the point cloud model of the tube sheet obtained by RGB-D cameras and photography methods.Aiming at the above problems,this paper proposed an annular weld seam detection network named WeldNet where a voxel feature encoding layer was adaptively improved for annular weld seams,the sparse convolutional network and region proposal network(RPN)were used to detect annular weld seam position,and an annular weld seam detection loss function was designed.Further,an annular weld seam dataset was established to train the network.Compared with the random sampling consistency(RANSAC)method,WeldNet has a higher detection accuracy,as well as a higher detection success rate which has increased by 23%.Compared with U-Net,WeldNet has been proven to achieve a better detection result,and the intersection over the union of the weld seam detection is improved by 17.8%.

关 键 词：deep learning point cloud weld seam detection WELDING annular weld seam 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程] TG441.7[金属学及工艺—焊接]