Affiliation:
1. Nanjing University of Aeronautics and Astronautics
2. Industrial Technology Research Institute
Abstract
He sensing of the weld pool and controlling of torch at the center of the groove are important problems in back welding of GMAW (Gas Metal Arc Welding) for pipeline, furthermore, the gap of the groove perhaps is varied, which needs an intelligent control strategy to obtain the high welding quality. Fuzzy neural network control method based on BP algorithm is proposed in this paper, from the module of image processing, the corresponding gap location and width can be obtained. Then determine corresponding swing width and speed when weld gap is varied by the network fuzzy inference and calculating Euclidean distance for GMAW variable gap backing welding process. Experiment results show that the designed control method can improve the welding quality compared with traditional fixed swing and the traditional auto swing.
Publisher
Trans Tech Publications, Ltd.
Reference5 articles.
1. Satoshi Yamane, Yasuyoshi Kaneko, Noriguki Kitahara. Neural network and fuzzy control of welding robot [A]. Manufacturing Systems Development and Applications Department Conference Records-IAS Annual Meeting [C], NJ, USA: IEEE, 1993, 2175-2180.
2. henHuaBin. The Development of Robotic GTA Welding Quality Control System for Five Port Connector on the Launch Vehicle Propulsion System [D]. (2009).
3. LiuShuGuang, WeiJunMin ZhuZhiChao. Fuzzy control technology, [M]. Beijing: China Textile & Apparel Press. 2001. 6.
4. LiRenBing, LiYiHua CaiYanPin etc, Support vector machine for rejecting identification of regional solutions based on the Euclidean distance. [J]. Journal of computer applications, 2010, 30(2).
5. K. Ohshima, Y. Kaneko, Y. Kohashi, T. lizaka, S. Yamane, Neuro-Fuzzy Control of Weld Pool in Pulsed MIG Welding, 140th Technical Committee of Welding Process of J.W.S. (1992).
Cited by
4 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