Shanchun Wei

Binocular vision system for both weld pool and root gap in robot welding process

Purpose – The purpose of this paper is to develop a kind of low cost measuring system based on binocular vision sensor to detect both the weld pool geometry and root gap simultaneously for robot welding process.Design/methodology/approach – Two normal charge coupled device cameras are used for capturing clear images from two directions; one of them is used to measure the root gap and another one is used to measure the geometric parameters of the weld pool. Efforts are made from both hardware and software aspects to decrease the strong interferences in pulsed gas tungsten arc welding process, so that clear and steady images can be obtained. The grey level distribution characteristics of root gap edge and weld pool edge in images are analyzed and utilized for developing the image processing algorithms.Findings – A solid foundation for seam tracking and penetration control of robot welding process can be established based on the binocular vision sensor.Practical implications – The results show that the algor...

Three‐dimensional weld seam tracking for robotic welding by composite sensing technology

Purpose – This paper aims to develop a method to achieve automatic robotic welding and seam tracking so that three‐dimensional weld seam could be tracked without teaching and good welding formation could be accomplished.Design/methodology/approach – Adaptive image processing method was used for various types of weld seam. Also the relationship between welding height and arc signal was calibrated. Through the decomposition and synthesis, three‐dimensional space type weld seam could be extracted and tracked well. The workpiece without teaching was finally tracked precisely and in a timely way with use of the fuzzy controller.Findings – Composite sensing technology including arc and visual sensing had obvious advantages. Image processing method could be used for tracking plane weld seam efficiently while arc sensing could characterize welding height. Through the coupled controlling algorithm, arc sensing and visual sensing could be fused effectively.Research limitations/implications – How to couple informati...

Autonomous guidance of initial welding position with “single camera and double positions” method

Purpose – Recognition and guidance of initial welding position (IWP) is one of the most important steps of automatic welding process, also a key technology of autonomous welding process. The purpose of this paper is to advance an improved Harris Algorithm and grey scale scanning method (GSCM) to raise the precision of image processing.Design/methodology/approach – Through the configuration of “single camera and double positions,” a new set of image processing algorithms is adopted to extract feature points by using the pattern of rough location and subtle extraction, so as to restructure three‐dimensional information to guide robot move to IWP in the practical welding environment.Findings – Experiments showed that mean square errors (MSEs) in X, Y, Z‐directions for both flat butt joint and flat flange are 0.4491, 0.8178, 1.4797, and 0.5398, 0.4861, 1.1071 mm, respectively.Research limitations/implications – It has a limitation in providing guidance for only one step, and would be more accurate if fraction...

Autonomous Seam Acquisition and Tracking for Robotic Welding Based on Passive Vision

A method of autonomous seam acquisition and tracking for arc welding robot is proposed. The seam information is real-timely obtained by one CCD camera in front of the anterior seam, while the host computer is in charge of image processing and edge features extracting. Thus the deviation between the projection of the tungsten electrode and the central line of welding seam can be obtained. Simultaneously tracking trajectory is optimized by Kalman filter and revised to eliminate the deviation defined so as to track the weld seam. The method can also be used to finish seam acquisition and tracking in the whole welding process autonomously even if the robot is never taught. The results validate feasibility of the method and imply the improvement of autonomy and intelligence for robot welding.

A Self-calibration Algorithm with Chaos Particle Swarm Optimization for Autonomous Visual Guidance of Welding Robot

Camera calibration is the process of finding the true parameters of a camera. In this article, we study the application of improved particle swarm optimization (PSO) algorithm in camera calibration. Then proposes a new algorithm CPSO, combining PSO with chaos optimization algorithm, to optimize camera’s intrinsic parameters based on absolute conics. Finally we carry out experiments to test its performance. Re-projection errors show that the method used in this paper is flexible and feasible, and the re-projection error is small enough to meet the accuracy demand of welding guidance.