Penetration estimation is a prerequisite of the automation of backing welding based on vision sensing technology. However, the arc interference in welding process leads to the difficulties of extracting the weld pool characteristic information, which brings great challenges to the penetration estimation. At present, most researches focus on the extraction of weld pool geometry parameters, and the visual sensing systems are complex in structure and complicated in the image processing algorithms. The research of penetration estimation based on weld pool geometry parameters is still in the exploratory stage. The purpose of this paper is to research the relationship between the weld pool geometry parameters and the penetration during backing welding and to estimate penetration using the weld pool geometry parameters. A passive vision sensing test system for gas metal arc (GMA) backing welding was established. An image processing algorithm was developed to extract the weld pool geometry parameters, namely, the area, maximum width and length, half-length, length-width ratio and advancing contact angle (simplified as AWP, MWWP, MLWP, HLWP, LWR and ACA, respectively). The corresponding relationships between the weld pool geometry parameters and the penetration state were explored by analysing their changes with the welding current and speed. The distribution of the weld pool geometry parameters corresponding to penetration was determined. When the AWP of the weld pool is within a certain range and the values of LWR and ACA are close to their maximum and minimum respectively, the penetration is in good condition. A mathematical model with the weld pool geometry parameters as independent variables and the back-bead width (the indicator of the penetration state) as a dependent variable was established based on multivariable linear regression analysis, and relevant statistical tests were carried out. Multivariable linear regression equations for the weld pool geometry parameters and the back-bead width were deduced according to the variations in the current and speed, and the equations can be used to estimate the penetration of backing welding. The study provides a solution to penetration estimation of GMA backing welding based on automatic vision sensing.
Penetration estimation is a prerequisite of the automation of backing welding based on vision sensing technology. However, the arc interference in welding process leads to the difficulties of extracting the weld pool characteristic information, which brings great challenges to the penetration estimation. At present, most researches focus on the extraction of weld pool geometry parameters, and the visual sensing systems are complex in structure and complicated in the image processing algorithms. The research of penetration estimation based on weld pool geometry parameters is still in the exploratory stage. The purpose of this paper is to research the relationship between the weld pool geometry parameters and the penetration during backing welding and to estimate penetration using the weld pool geometry parameters. A passive vision sensing test system for gas metal arc (GMA) backing welding was established. An image processing algorithm was developed to extract the weld pool geometry parameters, namely, the area, maximum width and length, half-length, length-width ratio and advancing contact angle (simplified as AWP, MWWP, MLWP, HLWP, LWR and ACA, respectively). The corresponding relationships between the weld pool geometry parameters and the penetration state were explored by analysing their changes with the welding current and speed. The distribution of the weld pool geometry parameters corresponding to penetration was determined. When the AWP of the weld pool is within a certain range and the values of LWR and ACA are close to their maximum and minimum respectively, the penetration is in good condition. A mathematical model with the weld pool geometry parameters as independent variables and the back-bead width (the indicator of the penetration state) as a dependent variable was established based on multivariable linear regression analysis, and relevant statistical tests were carried out. Multivariable linear regression equations for the weld pool geometry parameters and the back-bead width were deduced according to the variations in the current and speed, and the equations can be used to estimate the penetration of backing welding. The study provides a solution to penetration estimation of GMA backing welding based on automatic vision sensing.
[1] Y Lei, X B Yuan, X N Sun. Application situation and prospect of automatic welding technology faced on pressure vessel. Pressure Vessel Technology, 2004, 21(10): 35-40. (in Chinese)
[2] G Q Hou, G F Liao, R Ma, et al. Research on improving the efficiency and welding quality of welding robot for construction machinery structure. Journal of Shanghai Jiao Tong University, 2016, 50(Sup.): 40-43. (in Chinese)
[3] G J Li, C H Wu, B D Xu, et al. Ship curved plate column welding automation. Marine Technology, 2017, (2): 68-72. (in Chinese)
[4] L Xue, J M Wu, J F Huang, et al. Welding polarity effects on weld spatters and bead geometry of hyperbaric dry GMAW. Chinese Journal of Mechanical Engineering, 2016, 29(2): 351-356.
[5] Y Z Rong, R P Liu, Y H Wei. Welding database and expert system for aviation. Aeronautical Manufacturing Technology, 2017, (12): 43-47. (in Chinese)
[6] L Xue, Y Zou, J Q Huang, et al. Constant speed control for complex cross-section welding using robot based on angle. Chinese Journal of Mechanical Engineering, 2014, 27(2): 260-268.
[7] J F Yue, L Y Li, F L Fan, et al. Welding pool adaptive vision detection for arc welding robot gas metal arc welding. Journal of Mechanical Engineering, 2008, 44(4): 206-210. (in Chinese)
[8] Y Zou, L P Jiang, Y H Li, et al. Welding deviation detection algorithm based on extremum of molten pool image. Chinese Journal of Mechanical Engineering, 2016, 29(1): 74-83.
[9] J Q Huang, L Xue, J F Huang, et al. Arc behavior and joints performance of CMT welding process in hyperbaric atmosphere. Acta Metallurgica Sinica, 2016, 52(1): 93-99. (in Chinese)
[10] Y K Liu, Y M Zhang. Supervised learning of human welder behaviors for intelligent robotic welding. IEEE Transactions on Automation Science and Engineering, 2017, 14(3): 1532-1541.
[11] A S Baskoro, R Tandian, Haikal, et al. Automatic tungsten inert gas (TIG) welding using machine vision and neural network on material SS304. Proceedings of International Conference on Advanced Computer Science and Information Systems, East Java, Indonesia, October 15-16, 2016: 427-432.
[12] U Reisgen, P Lozano, S Mann, et al. Process control of gas metal arc welding processes by optical weld pool observation with combined quality models. Proceedings of IEEE International Conference on Automation Science and Engineering, Gothenburg, Sweden, Aug 24-28, 2015: 407-410.
[13] J S Chen, J Chen, Z L Feng, et al. Dynamic evolution of the weld pool reflection during weld penetration development. Proceedings of IEEE International Conference on Advanced Intelligent Mechatronics (AIM), Banff, Alberta, Canada, July 12-15, 2016: 548-553.
[14] T F Comas, C L Diao, J L Ding, et al. A passive imaging system for geometry measurement for the plasma arc welding process. IEEE Transactions on Industrial Electronics, 2017, 64(9): 7201-7209.
[15] R Kovacevic, Y M Zhang. Real-time image processing for monitoring of free weld pool surface. Journal of Manufacturing Science and Engineering, 1997, 119(5): 161-169.
[16] Y K Liu, Y M Zhang. Dynamic control of 3D weld pool surface based on human response model. Proceedings of 19th World Congress of the International Federation of Automatic Control, Cape Town, South Africa, August 24-29, 2014: 10640-10645.
[17] H Song, Y M Zhang. Error analysis of a three-dimensional GTA weld pool surface measurement system. Welding Journal, 2009, 88(7s): 141-148.
[18] W J Zhang, X W Wang, Y M Zhang. Analytical real-time measurement of a three-dimensional weld pool surface. Measurement Science and Technology, 2013, 24(11): 5011-5028.
[19] G Zhang, Y Shi, C K Li, et al. Measurement of characteristic parameters of three dimensional weld pool surface in Tungsten Inert Gas arc welding based on laser-vision. Journal of Shanghai Jiao Tong University, 2015, 49(3): 301-305. (in Chinese)
[20] Y K Liu, W J Zhang, Y M Zhang. Estimation of weld joint penetration under varying GTA pools. Welding Journal, 2013, 92(11): 313s-321s.
[21] Y K Liu, Y M Zhang. Model-based predictive control of weld penetration in Gas Tungsten Arc Welding. IEEE Transactions on Control Systems Technology, 2014, 22(3): 955-966.
[22] F Gao, M L Lu, B L Xu, et al. Multi region segmentation algorithm based on edge preserving for molten pool image. Proceedings of International Conference on Control, Automation and Information Sciences, Ansan, Korea, October 27-29, 2016: 210-214.
[23] C J Fan. Weld pool characters extraction visual sensing and intelligent control during varied gap aluminum alloy pulsed GTAW process. Shanghai: Shanghai Jiao Tong University, 2008. (in Chinese)
[24] H Y Shen, H B Chen, T Lin, et al. Passive visual technology in aluminum alloy welding. Journal of Shanghai Jiao Tong University, 2015, 49(3): 341-343. (in Chinese)
[25] D M Wang, J Q Gao, C S Wu, et al. Vision-based detection of weld pool in short-circuit gas metal arc welding. Transactions of The China Welding Institution, 2008, 29(10): 85-88. (in Chinese)
[26] J Q Gao, C S Wu. Vision-based measuring of weld pool geometry in TIG welding. Acta Metallurgica Sinica, 2000, 36(12): 1284-1288. (in Chinese)
[27] J Liu, Z Fan, S I Olsen, et al. A real-time passive vision system for robotic arc welding. Proceedings of the IEEE International Conference on Automation Science and Engineering, Gothenburg, Sweden, 2015: 389-394.
[28] A M Neill, J P H Steele. Modeling and simulation of three dimensional weld pool reconstruction by stereo vision. Proceedings of IEEE International Conference on Advanced Intelligent Mechatronics (AIM), Banff, Alberta, Canada, July 12-15, 2016: 542-547.
[29] J Wang, W Wang, S Chen. Inspection of welding pool height from shading in pulsed GTAW with wire filler. Industrial Robot: An International Journal, 2009, 36(3): 270-276.
[30] D B Zhao, J Q Yi, S B Chen, et al. Extraction of three-dimensional parameters for weld pool surface in pulsed GTAW with wire filler. Journal of Manufacturing Science and Engineering, 2003, 125(3): 493-503.
[31] L P Li, X Q Yang, F Y Zhang, et al. Research on surface recover of aluminum alloy P-GTAW pool based on SFS. Robotic Welding, Intelligence and Automation, Lecture Notes in Electrical Engineering, 2011, 88: 307-314.
