Abstract
PurposeThe recognition and positioning of start welding position (SWP) is the first step and one of the key technologies to realize autonomous robot welding. The purpose of this paper is to describe a method developed to accomplish successful autonomous detection and guiding of SWP.Design/methodology/approachThe images of workpieces are snapped by charge coupled device (CCD) cameras in a relative large range without additional light. The recognized methods of SWP are analyzed according to the given definition. A two‐step method named “coarse‐to‐fine” is proposed to recognize the SWP accurately. The first step is to solve the curve functions of seam and workpieces boundaries by fitting. The intersection point is regarded as initial value of SWP. The second step is to establish a small window that takes the initial value of SWP as centre. Then, the SWP is obtained exactly by corner detection in the window. Both the abundant information of original image and the structured information of recognized image are used according to given rules, which takes full advantage of the image information and improves the recognized precision.FindingsThe detected results show that the actual and calculated positions by first step of SWP are identical for regular seam, but different for the irregular curve seam. The exact results can be calculated by the two‐step method in the paper for both regular and irregular seams. The typical planar “S‐shape” and spatial arc curved seams are selected to carry out autonomous guiding of SWP.Originality/valueThe experimental results are given based on the introduction of 3D reconstructed and guided method. The guided precision is less than 1.1 mm, which meets the requirements of practical production. The proposed two‐step method recognizes the SWP rapidly and exactly from coarse to fine.
Subject
Industrial and Manufacturing Engineering,Computer Science Applications,Control and Systems Engineering
Reference18 articles.
1. Chen, S.B., Chen, X.Z. and Li, J.Q. (2005), “The research on acquisition of welding seam space position information for arc welding robot based on vision”, Journal of Intelligent & Robotic Systems, Vol. 43 No. 1, pp. 77‐97.
2. Chen, X.Z., Chen, S.B. and Lin, T. (2007), “Recognition of macroscopic seam for complex robotic welding environment”, Lecture Notes in Control and Information Sciences, Vol. 362, pp. 171‐8.
3. Chen, X.Z., Chen, S.B., Lin, T. and Lei, Y.C. (2006), “Practical method to locate the initial weld position using visual technology”, International Journal of Advanced Manufacturing Technology, Vol. 130 Nos 7/8, pp. 663‐8.
4. Cullison, A. (1995), “Trailer, manufacturer depends on robotic welding to boast production”, Welding Journal, Vol. 74 No. 7, pp. 49‐51.
5. Ge, J., Zhu, Z., He, D. and Chen, L. (2005), “A vision‐based algorithm for seam detection in a PAW process for large‐diameter stainless steel pipes”, International Journal of Advanced Manufacturing Technology, Vol. 26 Nos 9/10, pp. 1006‐11.
Cited by
47 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献