Welding seam groove recognition of steel structure on construction site based on machine vision

被引：2

作者：

Cheng J. ^{[1
,2
]}

Jin H. ^{[1
,2
]}

Zheng Z. ^{[1
,2
]}

Jiang L. ^{[1
,2
]}

Luo Q. ^{[3
]}

Dong K. ^{[3
]}

Zhou J. ^{[4
]}

Chen X. ^{[4
]}

机构：

[1] School of Civil Engineering, Southeast University, Nanjing

[2] Jiangsu Provincial Key Laboratory of Engineering Mechanics, Southeast University, Nanjing

[3] China Construction Science and Industry Jiangsu Corporation Ltd., Nanjing

[4] China Construction Steel Structure Jiangsu Corporation Ltd., Taizhou

来源：

Dongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Southeast University (Natural Science Edition) | 2023年 / 53卷 / 01期

关键词：

error analysis; image processing; intelligent construction; machine vision; welding seam recognition;

D O I：

10.3969/j.issn.1001-0505.2023.01.011

中图分类号：

学科分类号：

摘要：

A recognition method for weld groove of steel structure on construction site was proposed based on the linear structured light visual sensing technology. Taking the steel structure of a super high-rise building in Nanjing as the engineering background, an image acquisition device suitable for the construction site was firstly designed and developed, and the region of interest of the structured light line was intercepted from the acquired image through the recognition algorithm. Then, a local threshold segmentation method based on the group teaching optimization algorithm-Otsu method (GTO-Otsu) was presented to realize the effective segmentation of structured light lines and background. The linear structural elements were correspondingly constructed to repair the broken area of structured light lines. Finally, the centerline of the structured light line and the coordinates of the feature points were extracted by comparing the grayscale sum of adjacent pixels and the first-order difference value. A pixel conversion method was established to complete the conversion of pixel coordinates of feature points and realize the measurement of groove geometry. The image processing and identification results of three groups of construction site steel structure weld grooves show the accuracy and applicability of the proposed method. © 2023 Southeast University. All rights reserved.

引用

页码：86 / 93

页数：7

共 12 条

[1]

Fan J F, Jing F S, Fang Z J, Et al., Automatic recognition system of welding seam type based on SVM method [J], The International Journal of Advanced Manufacturing Technology, 92, pp. 989-999, (2017)

[2]

Sengee N, Sengee A, Choi H K., Image contrast enhancement using bi-histogram equalization with neighborhood metrics [J], IEEE Transactions on Consumer Electronics, 56, 4, pp. 2727-2734, (2010)

[3]

Guo L, Zhang H., Discontinuous fold line welding seam recognition and mobile robot tracking system in narrow space, Journal of Mechanical Engineering, 55, 17, pp. 8-13, (2019)

[4]

Yang L, Li E, Long T, Et al., A high-speed seam extraction method based on the novel structured-light sensor for arc welding robot. A review, IEEE Sensors Journal, 18, 21, pp. 8631-8641, (2018)

[5]

Zhao J, Zhao J, Zhang L., Image processing and feature extraction for structured light images of welded seam [J], Journal of XV an Jiaotong University, 47, 1, pp. 114-119, (2013)

[6]

Zhang S K, Wu Q X, Lin Z Y., Detection and segmentation of structured light stripe in weld image [J], Acta Optica Sinica, 41, 5, pp. 88-96, (2021)

[7]

Huang S J, Xu Y L, Yang X I, Et al., ROI weld feature extraction algorithm of real-time tracking [J], Journal of Shanghai Jiao Tong University, 50, 12, pp. 1877-1880, (2016)

[8]

Wang W C, Gao X D, Ding X D., Study on welding seam recognition methods based on visual sensing [J], Hot Working Technology, 47, 1, pp. 195-198, (2018)

[9]

Huang H, Li Q W, Fan X J., Adaptive local threshold image segmentation algorithm [J], Optoelectronic Technology, 31, 1, pp. 10-13, (2011)

[10]

Zhang Y, Jin Z., Group teaching optimization algorithm: A novel metaheuristic method for solving global optimization problems, Expert Systems with Applications, 148, (2020)

← 1 2 →