Application and trends of point cloud in intelligent welding: State of the art review

Abstract

Point cloud is an important data format for expressing 3D scenes. With the development of digitalization and intelligence in welding, the application of point cloud in welding is gradually increasing. This paper provides a comprehensive overview of the application of point clouds in intelligent welding, divided into pre-welding stage, in-welding stage, and post-welding stage according to the welding sequence. A detailed analysis was conducted on the pre-welding stage of intelligent welding operations, including the point cloud construction of the workpiece, weld seam detection in the point cloud, path and posture planning, automatic programming, and weld seam positioning. The in-welding stage was divided into welding pool monitoring, weld seam tracking and adjustment, and a comparative analysis was conducted on point cloud processing algorithms and control methods. The post-welding stage is divided into weld seam identification, defect detection, and quality detection, which are analyzed and discussed separately. This paper introduces the application of point clouds in the previous stages, and compares in detail the selection of sensors, application scenarios, point cloud processing algorithms, and processing effects. Furthermore, in-depth analysis was conducted on the effects and limitations achieved in various application scenarios. Finally, this paper provides an outlook on future work, summarizes the relevant applications of machine learning in welding point cloud processing, and analyzes future development trends.