高级检索

基于红外视觉的熔化极气体保护焊外观缺陷识别

夏卫生, 龚福建, 杨荣国, 万柴志, 杨云珍

夏卫生, 龚福建, 杨荣国, 万柴志, 杨云珍. 基于红外视觉的熔化极气体保护焊外观缺陷识别[J]. 焊接学报, 2020, 41(3): 69-73. DOI: 10.12073/j.hjxb.20190928001
引用本文: 夏卫生, 龚福建, 杨荣国, 万柴志, 杨云珍. 基于红外视觉的熔化极气体保护焊外观缺陷识别[J]. 焊接学报, 2020, 41(3): 69-73. DOI: 10.12073/j.hjxb.20190928001
XIA Weisheng, GONG Fujian, YANG Rongguo, WAN Chaizhi, YANG Yunzhen. Apparent defect recognition of gas metal arc welding based on infrared vision[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(3): 69-73. DOI: 10.12073/j.hjxb.20190928001
Citation: XIA Weisheng, GONG Fujian, YANG Rongguo, WAN Chaizhi, YANG Yunzhen. Apparent defect recognition of gas metal arc welding based on infrared vision[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2020, 41(3): 69-73. DOI: 10.12073/j.hjxb.20190928001

基于红外视觉的熔化极气体保护焊外观缺陷识别

基金项目: 航天科学技术基金项目(2019-HT-HZ);武汉市应用基础研究计划项目(2017010201010125).
详细信息
    作者简介:

    夏卫生,1979年出生,博士,副教授;主要从事焊接与增材制造智能控制、先进连接与电子封装技术、智能制造与机器人系统等科研和教学工作;发表论文50余篇;Email:xiawsh@hust.edu.cn

    通讯作者:

    杨云珍,讲师;Email:yangyunzhen@whut.edu.cn.

  • 中图分类号: TG 441

Apparent defect recognition of gas metal arc welding based on infrared vision

  • 摘要: 焊接过程可视化监控与成形缺陷智能识别是实现焊接智能制造的重要途径之一. 采用红外CCD在线采样熔化极气体保护焊(gas metal arc welding,GMAW)熔池红外图像,结合改进滤波算法和图像增强算法对图像进行预处理,通过热电偶进行温度标定,建立红外图像中灰度值与温度值的对应关系,进而获取焊接熔池的温度分布信息,然后采用改进边缘提取算法提取熔池的特征参数,据此建立焊接外观缺陷的特征识别算法. 结果表明,所设计的算法对焊接形状缺陷、烧穿及未熔透等在线识别具有良好的实用性和准确性.
    Abstract: The visual monitoring of welding process and welding defect identification are vital to the intelligent control of welding processes. In this paper, a mid-wave infrared CCD was used to acquire the infrared images of the welding pool on-line during the welding process. The images captured are preprocessed by the improved filtering algorithm and image enhancement algorithm. To obtain the temperature distribution information of the welding pool, the relationship between the gray value in infrared image and the temperature is established based on temperature calibration of the used thermocouple. The improved edge extraction algorithm is used to extract the characteristic parameters of the welding pool. Then the identification algorithm of welding defect is developed. The results of verified experiments show that the proposed algorithm has good practicability and accuracy in the on-line identification of welding shape, burn-through and unmelted defects.
  • 图  1   红外图像采集系统示意图

    Figure  1.   Infrared image acquisition system

    图  2   热电偶测量熔池温度示意图

    Figure  2.   Temperature measurement by thermocouples

    图  3   熔池温度测量点示意图

    Figure  3.   20 points selected for temperature measurement

    图  4   实测温度与像素灰度值间玻尔兹曼函数拟合结果

    Figure  4.   Boltzmann fitting consequent of temperature and grayscale value

    图  5   原始红外图像及滤波处理结果对比

    Figure  5.   Comparisons between the raw and the filtered infrared images. (a) simplified digital image; (b) original image; (c) ordinary mean filtering; (d) improved mean filtering

    图  6   三种插值算法增强后的图像对比

    Figure  6.   Comparisons of infrared images after three interpolation algorithms

    图  7   红外图像的熔池特征参数

    Figure  7.   Characteristic parameters of welding pool

    图  8   焊缝形状缺陷图像及其对应红外图像

    Figure  8.   Defects of weld shape and its corresponding infrared images. (a) weld field diagram; (b) infrared map of region A; (c) infrared map of region B

    图  9   烧穿及未熔透缺陷及焊缝熔池红外图像

    Figure  9.   Burn-through defect, lack of penetration and its corresponding infrared images. (a) early period of overheating; (b) continued overheating; (c) late stage of overheating; (d) after burn through; (e) not fully melted; (f) normal; (g) actual appearance of the weld

    表  1   红外传感器参数

    Table  1   Parameters of the IR sensor

    FPA分辨率像素尺寸(μm × μm)响应波长l/μm积分时间t/µs最大帧数f/Hz通讯接口
    80 × 80130 × 1301 ~ 5100 ~ 1 0001 000USB 2.0
    下载: 导出CSV
  • [1]

    Zhu Yanjun, Wu Zhisheng, Li Ke, et al. Welding deviation detection method based on weld pool image contour features[J]. China Welding, 2019, 28(2): 35 − 44.

    [2]

    Xu Y, Fang G, Lü N, et al. Computer vision technology for seam tracking in robotic GTAW and GMAW[J]. Robotics & Computer Integrated Manufacturing, 2015, 32: 25 − 36.

    [3]

    Xu Y, Lü N, Fang G,et al. Sensing technology for intelligentized robotic welding in arc welding processes[M]. Cham: Springer International Publishing, 2015.

    [4] 方吉米, 王克鸿, 黄勇. 高速GMAW驼峰焊道形成过程熔池图像识别[J]. 焊接学报, 2019, 40(2): 42 − 46.

    Fang Jimi, Wang Kehong, Huang Yong. Weld pool image recognition of humping formation process in high speed GMAW[J]. Transactions of the China Welding Institution, 2019, 40(2): 42 − 46.

    [5]

    Wang Kehong, Tang Xincheng, Yu Jian, et al. Method of visional detecting MAG weld pool information[J]. Transactions of Nonferrous Metals Society of China, 2005, 15(S3): 369 − 374.

    [6] 于英飞, 朱志明, 孙博文,等. 焊接电弧图像的边缘检测及其批处理算法[J]. 焊接学报, 2018, 39(11): 17 − 21.

    Yu Yingfei, Zhu Zhiming, Sun Bowen, et al. Edge detection and batch algorithm for welding arc images[J]. Transactions of the China Welding Institution, 2018, 39(11): 17 − 21.

    [7]

    Hu C, Chen X Z. A review and preliminary experiment on application of infrared thermography in welding[M]. Cham: Springer International Publishing, 2015.

    [8]

    Lu X Q, Liu W M, Wu Y X. Review of sensors and its applications in the welding robot[M]. Cham: Springer International Publishing, 2015.

    [9]

    Kumar R, Somkuva V. A review on analysis, monitoring and detection of weld defect products[J]. International Journal of Engineering & Technical Research, 2015, V4(11): 664 − 667.

    [10] 曹宏岩, 陈章希, 胡超, 等. 基于红外温度场的焊接质量在线检测方法简介[J]. 上海交通大学学报, 2016, 50(7): 66 − 70.

    Cao Hongyan, Chen Zhangxi, Hu Chao, et al. A brief introduction to the on-line measurement method of welding quality based on infrared temperature field[J]. Journal of Shanghai Jiaotong university, 2016, 50(7): 66 − 70.

    [11]

    Huang R S, Liu L M, Song G. Infrared temperature measurement and interference analysis of magnesium alloys in hybrid laser-TIG welding process[J]. Materials Science & Engineering, 2007, 447(1-2): 239 − 243.

    [12] 闻倩艺, 何建萍, 王昂洋, 等. 焊接熔池图像视觉传感技术的研究现状及发展趋势[J]. 热加工工艺, 2016(22): 7 − 10.

    Wen Qianyi, He Jianping, Wang Angyang, et al. Research status and development trend of visual sensing technology for welding pool image[J]. Journal of Thermal Processing Technology, 2016(22): 7 − 10.

    [13] 谢志孟, 高向东. 基于Canny算子的焊缝图像边缘提取技术[J]. 焊接学报, 2006, 27(1): 29 − 32.

    Xie Zhimeng, Gao Xiangdong. Edge extraction of weld image based on canny operator[J]. Transactions of the China Welding Institution, 2006, 27(1): 29 − 32.

    [14] 罗勇, 张华. 基于Canny边缘检测算子和去除小物体算法的熔池图像处理[J]. 焊接学报, 2005(5): 17 − 20.

    Luo Yong, Zhang Hua. Image processing of molten pool based on Canny edge detection operator and small object removal algorithm[J]. Transactions of the China Welding Institution, 2005(5): 17 − 20.

    [15]

    Ogawa Y. High speed imaging technique. Part1: high speed imaging of arc welding phenomena[J]. Science & Technology of Welding & Joining, 2011, 16(1): 33 − 43.

  • 期刊类型引用(1)

    1. 孟美情,韩俭,朱瀚钊,梁哲滔,蔡养川,张欣,田银宝. 基于多丝电弧增材制造研究现状. 材料工程. 2025(05): 46-62 . 百度学术

    其他类型引用(1)

图(9)  /  表(1)
计量
  • 文章访问数:  546
  • HTML全文浏览量:  46
  • PDF下载量:  46
  • 被引次数: 2
出版历程
  • 收稿日期:  2019-09-27
  • 网络出版日期:  2020-07-12
  • 刊出日期:  2020-02-29

目录

    /

    返回文章
    返回