Image recognition of molten pool based on non-negative matrix factorization

被引：0
|
作者：
Pei Y. [1 ]
Wang K. [2 ]
机构：
[1] Guiyang Big Data Industry Group Co., Ltd., Guiyang
[2] School of Materials Science and Engineering, Nanjing University of Science and Technology, Nanjing
来源：
Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2023年 / 29卷 / 03期
关键词：
gas metal arc welding; image recognition; non-negative matrix factorization; welding defect; welding pool;
D O I：
10.13196/j.cims.2023.03.022
中图分类号：
学科分类号：
摘要：
To explore the technology of visual sensing intelligent identification of welding defects, the continuous images of welding pool in Gas Metal Arc Welding (GMAW) were acquired by Charge Coupled Device (CCD) to research the behavior of the welding pool as well as the corresponding welding defects. The nonnegative matrix factorization algorithm was used for feature extraction of the welding pool images. The recognition value of tested image in feature matrix was calculated by least square method. The automatic identification method of welding defects was given. The results showed that the welding quality was related to the stability of the weld pool. Specifically, the unstable weld pool was characterized by profile fluctuation, welding slag dispersion and so on. The decrease of molten pool stability was accompanied by the decrease of welding quality, which leaded to appear the weld defects. The feature matrix of weld pool image based on nonnegative matrix factorization algorithm could describe the original images in general (such as weld pool profile) and in part-base (such as weld slag profile), which had physical interpret-ability and could be used to identify welding defects. © 2023 CIMS. All rights reserved.
引用
收藏
页码：930 / 937
页数：7
相关论文
共 20 条
  • [1] KONG M, CHEN S B., Al alloy weld pool control of welding robot with passive vision[J], Sensor Review, 29, 1, pp. 28-37, (2009)
  • [2] GAO F, WANG K H, ZHAN L L, Et al., Classification of MAG weld pool image based on moment invariants and fisher [J], China Wedling, 20, 4, pp. 51-56, (2011)
  • [3] YAN, WANG Yizhong, WANG Zhongren, Et al., Embedded vision tracking control system for automous mobile welding robot [J], Computer Integrated Manufacturing Systems, 26, 11, pp. 3049-3056, (2020)
  • [4] LUO Xiang, WANG Zongyi, Vision system for open arc welding based on multi-exposure, Transactions of the China Welding Institution, 36, 9, pp. 91-94, (2015)
  • [5] LIANG Zhimin, ZHAO Shuangshuang, ZHANG Meimel, Et al., Vision sensing of weld pool for P-GMAW by an infrared transmitting filter[J], Transactions of the China Welding Institution, 35, 2, pp. 33-36, (2014)
  • [6] FANG Jimi, WANG Kehong, HUANG Yong, Et al., Research on image fusion method of visible and near infrared weld pool [J], Transactions of the China Welding Institution, 40, 5, pp. 18-23, (2019)
  • [7] ZHANG Z F, CHEN H B, XU Y L, Et al., Multisensor-based real-time quality monitoring by means of feature extraction, selection and modeling for Al alloy in arc welding[J], Mechanical Systems and Signal Processing, 60, pp. 151-165, (2015)
  • [8] ZHANG Yugang, MA Guohong, CUI Yong, Et al., Multi-focus welding pool image fusion based on wavelet transform of double arc welding of magnesium alloy[j], Journal of Shanghai Jiaotong University, 49, 3, pp. 398-401, (2015)
  • [9] HUANG Seji, XU Yanlmg, YANG Xuejun, Et al., ROI weld feature extraction algorithm of real-time tracking[j], Journal of Shanghai Jiaotong University, 50, 12, pp. 1877-1880, (2016)
  • [10] FABRICE B, STEPHEN M, STEWART W., Process control of laser conduction welding by thermal imaging measurement with a color camera[j], Applied Optics, 44, 32, pp. 6841-6848, (2005)
12