SVM-based information fusion for weld deviation extraction and weld groove state identification in rotating arc narrow gap MAG welding

详细信息    查看全文

• 作者：Wenhang Li (1) (2)
  Kai Gao (1)
  Jing Wu (3)
  Ting Hu (1)
  Jiayou Wang (1)
  
• 关键词：SVM ; Vision sensing ; Arc sensing ; Intelligent modeling ; Information fusion
• 刊名：The International Journal of Advanced Manufacturing Technology
• 出版年：2014
• 出版时间：October 2014
• 年：2014
• 卷：74
• 期：9-12
• 页码：1355-1364
• 全文大小：1,483 KB
• 参考文献：1. Wang JY, Ren YS, Yang F, Guo HB (2007) Novel rotation arc system for narrow gap MAG welding. Sci Technol Weld Join 12(6):505鈥?07 CrossRef
  2. Min D, Xin-hua T, Feng-gui L, Shun Y (2011) Welding of quenched and tempered steels with high-spin arc narrow gap MAG system. Int J Adv Manuf Technol 55(5鈥?):527鈥?33 CrossRef
  3. Kim GH, Na SJ (2001) A study of an arc sensor model for gas metal arc welding with rotating arc Part 2: simulation of an arc sensor in mechanically rotating gas metal arc welding. Proc Inst Mech Eng B J Eng Manuf 215(9):1281鈥?288 CrossRef
  4. Xu Y, Zhong J, Ding M, Chen H, Chen S The acquisition and processing of real-time information for height tracking of robotic GTAW process by arc sensor. Int J Adv Manuf Technol 65(5鈥?):1031鈥?043
  5. Moon HS, Kim YB, Beattie RJ (2006) Multi sensor data fusion for improving performance and reliability of fully automatic welding system. Int J Adv Manuf Technol 28(3):286鈥?93 CrossRef
  6. Wang H, Chen Y (2006) Sensor data fusion using rough set for mobile robots system. In: Proceedings of the 2nd IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA 2006, Beijing, 2007. 2nd IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications, MESA
  7. Chen B, Wang J, Chen S (2010) Prediction of pulsed GTAW penetration status based on BP neural network and DS evidence theory information fusion. Int J Adv Manuf Technol 48(1鈥?):83鈥?4 CrossRef
  8. Moon H-S, Kim YB, Beattie RJ (2006) Multi sensor data fusion for improving performance and reliability of fully automatic welding system. Int J Adv Manuf Technol 28(3鈥?):286鈥?93 CrossRef
  9. Bae KY, Lee TH, Ahn KC (2002) An optical sensing system for seam tracking and weld pool control in gas metal arc welding of steel pipe. J Mater Process Technol 120(1):458鈥?65 CrossRef
  10. Ma H, Wei S, Sheng Z, Lin T, Chen S (2010) Robot welding seam tracking method based on passive vision for thin plate closed-gap butt welding. Int J Adv Manuf Technol 48(9鈥?2):945鈥?53 CrossRef
  11. Vapnik VN (2000) The nature of statistical learning theory. Springer-Verlag New York Inc
  12. Chiu S-H, Lu C-P (2006) On-line unusual tension recognition system on twister using smooth support vector machine classifier. Int J Adv Manuf Technol 30(1鈥?):92鈥?7 CrossRef
  13. Ramesh R, Mannan MA, Poo AN (2002) Support vector machines model for classification of thermal error in machine tools. Int J Adv Manuf Technol 20(2):114鈥?20 CrossRef
  14. Ghosh A, Majumdar SK (2011) Modeling blast furnace productivity using support vector machines. Int J Adv Manuf Technol 52(9鈥?2):989鈥?003 CrossRef
  15. Li WH, Sun DD, Yang F, Wang JY (2011) Modeling method for narrow gap MAG welding seam tracking based on rough sets. Mater Sci Technol 19(6):48鈥?2
  16. Zhao C, Zhang H, Zhang X, Zhang R, Luan F, Liu M, Hu Z, Fan B (2006) Prediction of milk/plasma drug concentration (M/P) ratio using support vector machine (SVM) method. Pharm Res 23(1):41鈥?8 CrossRef
  17. Fei Z, Tiyip T (2011) A method of soil salinization information extraction with SVM classification based on ICA and texture features. Agric Sci Technol 15(7):1046鈥?049, 1074
  
• 作者单位：Wenhang Li (1) (2)
  Kai Gao (1)
  Jing Wu (3)
  Ting Hu (1)
  Jiayou Wang (1)
  
  1. School of Materials Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang, 212003, China
  2. Jiangsu Modern Shipbuilding Technology Co., Ltd., Zhenjiang, 212003, China
  3. Department of Mechanical Engineering, Aerospace and Biomedical Engineering, The University of Tennessee, Knoxville, TN, 37996-2210, USA
  
• ISSN：1433-3015

文摘

As a high-efficiency welding method, rotating arc narrow gap MAG welding (RANGMW) is accurate with its seam tracking to make enough groove sidewall penetration at both sides. The accuracy of traditional arc sensing-based methods is impacted by the bottom shape of the welding groove, especially when the shape is irregular. To overcome this shortage, an arc sensing-vision sensing synchronous data acquisition system was developed. More specially, the vision sensing method used passive vision and worked in infrared region to extract the welding character by an automatic image processing algorithm. Furthermore, by fusing the arc sensing and vision sensing information, a statistical learning model, support vector machine (SVM), was built to predict the groove state. The method was validated by tenfold cross-validation and also compared with back propagation (BP) neural network model. The results showed that our model met the demand of welding application and outperformed BP neural network, thus can help for the further application of welding quality control.