An adaptive feature extraction algorithm for multiple typical seam tracking based on vision sensor in robotic arc welding
An adaptive feature extraction algorithm for multiple typical seam tracking based on vision sensor in robotic arc welding
复制标题
机器人弧焊中基于视觉传感器的多典型焊缝跟踪自适应特征提取算法
DOI：
10.1016/j.sna.2019.111533
复制
发表时间：
2019-10-01
影响因子：
4.6
通讯作者：
Chen, Shanben
中科院分区：
文献类型：
--
作者：
Xiao, Runquan;Xu, Yanling;Chen, Shanben
智能机器人焊接是现代焊接制造中不可缺少的组成部分，而基于视觉的焊缝跟踪是实现智能焊接的关键技术之一。然而，在焊接实践中，大多数图像处理算法的适应性和稳健性都存在不足。针对这一问题，提出了一种基于激光视觉传感器的自适应特征提取算法。根据激光条纹图像，将典型的焊缝分为连续焊缝和不连续焊缝。训练一种更快的R-CNN模型来自动识别焊缝类型和定位激光条纹ROI。焊接前，通过点云处理确定初始焊点，实现焊接导引。在焊缝跟踪过程中，采用两步提取算法提取焊缝边缘，采用Steger算法检测激光条纹。根据两种焊缝的特点，设计了相应的焊缝中心提取算法。为了保证算法的稳定性，提出了先验模型。测试结果表明，该算法对多个典型焊缝具有良好的适应性，即使在复杂的工作条件下也能保持令人满意的鲁棒性和精度。(C)2019爱思唯尔B.V.保留所有权利。
Intelligent robotic welding is an indispensable part of modern welding manufacturing, and vision-based seam tracking is one of the key technologies to realize intelligent welding. However, the adaptability and robustness of most image processing algorithms are deficient during welding practice. To address this problem, an adaptive feature extraction algorithm based on laser vision sensor is proposed. According to laser stripe images, typical welding seams are classified into continuous and discontinuous welding seams. A Faster R-CNN model is trained to identify welding seam type and locate laser stripe ROI automatically. Before welding, initial welding point is determined through point cloud processing to realize welding guidance. During seam tracking process, the seam edges are achieved by a two-step extraction algorithm, and the laser stripe is detected by Steger algorithm. Based on the characteristics of two kinds of welding seams, the corresponding seam center extraction algorithms are designed. And a prior model is proposed to ensure the stability of the algorithms. Test results prove that the algorithm has good adaptability for multiple typical welding seams and can maintain satisfying robustness and precision even under complex working conditions. (C) 2019 Elsevier B.V. All rights reserved.