Automatic extraction and identification of narrow butt joint based on ANFIS before GMAW

To improve the automation level of the welding robots, the automatic extraction and identification of the weld seam is the pre-requisite of the intelligent welding robots. During the real industrial environment, the welding environment often has the characteristics of weak texture, poor contrast, reflections from metallic surfaces, and imperfections on the work piece. These characteristics will seriously affect the accurate extraction of weld seam. To realize the automatic path planning of welding robots, a new method of automatic extraction and identification of narrow butt joint under weak contrast is realized to serve the 3D path teaching of welding robots. To achieve accurate extraction of narrow butt joint under weak contrast, this paper designs a new seam extraction operator to achieve accurate and fast extraction of weld seam with various shapes and sizes. And the shape feature of weld seam is used to construct feature vector. Finally, to get optimal classification performance, the adaptive network-based fuzzy inference system (ANFIS) is adopted in this paper to finish identification of narrow butt joints. The experimental results show that the proposed algorithm could quickly and accurately realize the extraction and identification of the narrow butt joints under weak contrast.

[1]  Yanling Xu,et al.  The acquisition and processing of real-time information for height tracking of robotic GTAW process by arc sensor , 2013 .

[2]  Kang-Yul Bae,et al.  A study on development of inductive sensor for automatic weld seam tracking , 2006 .

[3]  Carlos Frederico de Oliveira Graeff,et al.  An open-source equipment for thin film fabrication by electrodeposition, dip coating, and SILAR , 2016, The International Journal of Advanced Manufacturing Technology.

[4]  Konstantinos-Dionysios Bouzakis,et al.  Off-line programming of an industrial robot for manufacturing , 2005 .

[5]  Marizan Sulaiman,et al.  Autonomous detection and identification of weld seam path shape position , 2017 .

[6]  Gu Fang,et al.  Autonomous weld seam identification and localisation using eye-in-hand stereo vision for robotic arc welding , 2013 .

[7]  Ju Jia Zou,et al.  Experiments on Automatic Seam Detection for a MIG Welding Robot , 2011, AICI.

[8]  Haichao Li,et al.  Online welding path detection in automatic tube-to-tubesheet welding using passive vision , 2017 .

[9]  Ziqin Chen,et al.  Detection of weld pool width using infrared imaging during high-power fiber laser welding of type 304 austenitic stainless steel , 2014 .

[10]  Min Tan,et al.  Automatic recognition system of welding seam type based on SVM method , 2017, The International Journal of Advanced Manufacturing Technology.

[11]  Patrick M. Pilarski,et al.  Intelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learning , 2016 .

[12]  Jagdev Singh,et al.  Artificial intelligent modeling to predict tensile strength of inertia friction-welded pipe joints , 2013 .

[13]  Wen Wan,et al.  Autonomous seam acquisition and tracking system for multi-pass welding based on vision sensor , 2013 .

[14]  Li Wang,et al.  A Vision-Aided 3D Path Teaching Method before Narrow Butt Joint Welding , 2017, Sensors.

[15]  Ismael Lopez-Juarez,et al.  Robotic GMAW online learning: issues and experiments , 2016 .

[16]  Dilip Kumar Pratihar,et al.  Expert systems in manufacturing processes using soft computing , 2015, The International Journal of Advanced Manufacturing Technology.

[17]  Drago Bračun,et al.  Stereo vision based measuring system for online welding path inspection , 2015 .

[18]  De Xu,et al.  Visual seam tracking system for butt weld of thin plate , 2010 .

[19]  Yu Huang,et al.  A seam-tracking laser welding platform with 3D and 2D visual information fusion vision sensor system , 2013 .

[20]  Kai Wang,et al.  Weld deviation detection based on wide dynamic range vision sensor in MAG welding process , 2016 .

[21]  Daniel J. Huggett,et al.  Prediction of friction stir weld quality without and with signal features , 2017, The International Journal of Advanced Manufacturing Technology.

[22]  Yanling Xu,et al.  Computer vision technology for seam tracking in robotic GTAW and GMAW , 2015 .

[23]  Marizan Sulaiman,et al.  An experiment of detection and localization in tooth saw shape for butt joint using KUKA welding robot , 2018 .

[24]  Lin Wu,et al.  Bead geometry prediction for robotic GMAW-based rapid manufacturing through a neural network and a second-order regression analysis , 2012, Journal of Intelligent Manufacturing.

[25]  S. Liang,et al.  Force modeling of Inconel 718 laser-assisted end milling under recrystallization effects , 2017 .

[26]  Tao Lin,et al.  Recognition of Macroscopic Seam for Complex Robotic Welding Environment , 2007 .

[27]  Shivanandan Shashidhar Indimath,et al.  Online ultrasonic technique for assessment of mash seam welds of thin steel sheets in a continuous galvanizing line , 2017 .

[28]  Xuewu Wang,et al.  Three-dimensional vision-based sensing of GTAW: a review , 2014 .

[29]  Lei Yang,et al.  A welding quality detection method for arc welding robot based on 3D reconstruction with SFS algorithm , 2018 .

[30]  T. Jayakumar,et al.  Intelligent modeling for estimating weld bead width and depth of penetration from infra-red thermal images of the weld pool , 2015, J. Intell. Manuf..