GMAW Penetration State Prediction Based on Visual Sensing

doi:10.3901/JME.2019.17.041

Abstract

Abstract: Real-time acquisition of the penetration information is one of the key links in the automation of backing welding. Predicting the penetration state through the shape feature parameters of weld pool can provide a reference for the effective extraction of penetration information. Since the welder estimates the penetration state in real time by observing the shape features of weld pool, a GMAW test system with binocular vision sensors is established. Backing welding tests are carried out under different welding currents and welding speeds, and the front and back images of weld pool are collected synchronously during the welding process. Based on the characteristics of weld pool images, combined with the mature image processing algorithms, the two-dimensional and three-dimensional shape feature parameters of weld pool surface and the back-bead width information are extracted, which are taken as the training samples. The feature parameters of weld pool surface are taken as the input and the back-bead width is taken as the output. The BP algorithm is used to train the neural network, and the penetration state prediction model is set up to analyse the mapping relationship between the shape feature parameters of weld pool surface and the back-bead width. The weight coefficient of each shape feature parameter to the back-bead width is calculated by the Garson algorithm. The penetration state prediction model is verified by the backing GMAW tests. The test results show that the BP neural network model can predict the penetration state of the weld effectively.

Key words: backing GMAW, vision sensor of weld pool, penetration state, neural network model

CLC Number:

TG409

HUANG Junfen, XUE Long, HUANG Jiqiang, ZOU Yong, MA Ke, JIAO Xiangdong. GMAW Penetration State Prediction Based on Visual Sensing[J]. Journal of Mechanical Engineering, 2019, 55(17): 41-47.

References

[1] XUE Long,ZOU Yong,HUANG Jiqiang,et al. Constant speed control for complex cross-section welding using robot based on angle[J]. Chinese Journal of Mechanical Engineering,2014,27(2):260-268.
[2] XUE Long,WU Jinming,HUANG Junfen,et al. Welding polarity effects on weld spatters and bead geometry of hyperbaric dry GMAW[J]. Chinese Journal of Mechanical Engineering,2016,29(2):351-356.
[3] ZOU Yong,JIANG Lipei,LI Yunhua,et al. Welding deviation detection algorithm based on extremum of molten pool image[J]. Chinese Journal of Mechanical Engineering,2016,29(1):74-83.
[4] Comas T F,DIAO Chenglei,DING Jialuo,et al. A passive imaging system for geometry measurement for the plasma arc welding process[J]. IEEE Transactions on Industrial Electronics,2017,64(9):7201-7209.
[5] 张刚,石玗,李春凯,等. 钨极惰性气体保护焊熔池三维自由表面特征参数的激光视觉测量. 上海交通大学学报,2015,49(3):301-305. ZHANG Gang,SHI Yu,LI Chunkai,et al. Measurement of characteristic parameters of three dimensional weld pool surface in Tungsten Inert Gas arc welding based on laser-vision[J]. Journal of Shanghai Jiaotong University,2015,49(3):301-305.
[6] 陈善本,曹建明,徐晨明,等. 脉冲熔化极气体保护焊熔池的视觉传感与实时控制[J]. 焊接学报,2002,23(4):17-20. CHEN Shanben,CAO Jianming,XU Chenming,et al. Visual sensing and real -time control of weld pool dynamics in pulsed GMAW[J]. Transactions of the China Welding Institution,2002,23(4):17-20.
[7] 武传松,刘祖明,陈姬. 受控脉冲穿孔等离子弧焊接小孔动态行为的检测[J]. 机械工程学报,2013,49(18):114-118. WU Chuansong,LIU Zuming,CHEN Ji. Measurement of dynamic keyhole behaviors in controlled-pulse plasma arc welding[J]. Journal of Mechanical Engineering,2013,49(18):114-118.
[8] ZHANG Weijie,WANG Xuewu,ZHANG Yuming. Analytical real-time measurement of a three-dimensional weld pool surface[J]. Measurement Science and Technology,2013,24(11):5011-5028.
[9] LIU,Yukang,ZHANG,Yuming. Model-based predictive control of weld penetration in Gas Tungsten Arc Welding[J]. IEEE Transactions on Control Systems Technology,2014,22(3):955-966.
[10] MNICH C,AL-BAYAT F,DEBRUNNER C,et al. In situ weld pool measurement using stereovision[C]//2004 Japan-USA Symposium on Flexible Automation,July 19-21,2004,Denver,Colorado,USA. New York:ASME,2004:19-21.
[11] 陈华斌,樊重建,林涛,等. 基于前馈补偿的五通连接器机器人GTAW熔透控制[J]. 上海交通大学学报,2009,43(1):71-74. CHEN Huabin,FAN Chongjian,LIN Tao,et al. Penetration control of robotic gtaw for five-port connector based on feedforward compensation[J]. Journal of Shanghai Jiaotong University,2009,43(1):71-74.
[12] 高向东,林俊,萧振林,等. 电弧焊熔透ICA-BP神经网络识别模型[J]. 焊接学报,2016,37(5):33-36. GAO Xiangdong,LIN Jun,XIAO Zhenlin,et al. Recognition model of arc welding penetration using ICA-BP neural network[J]. Transactions of the China Welding Institution,2016,37(5):33-36.