A weld line detection robot based on structure light for automatic NDT

被引：24

作者：

Dong, Zhaoxuan ^{[1
]}

Mai, Zhiheng ^{[1
]}

Yin, Shiqi ^{[1
]}

Wang, Jie ^{[1
]}

Yuan, Jie ^{[1
]}

Fei, Yuenong ^{[1
]}

机构：

[1] Shenzhen Univ, Shenzhen, Peoples R China

来源：

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY | 2020年 / 111卷 / 7-8期

关键词：

Structured light sensor; Weld line detection; MobileNet-SSD; VISION SENSOR; TRACKING; SYSTEM;

D O I：

10.1007/s00170-020-05964-w

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In automatic non-destructive testing (NDT), weld bead tracking is usually performed outside. However, irregular weld boundaries, unconstrained illumination, and rough metal surfaces can cause noise, which increases the difficulty of seam tracking. In this paper, a method of parallel structured light (PSL) sensing based on deep learning and information fusion is proposed to detect weld lines. First, a camera is used to capture the laser stripe image projected by the PSL on the weld bead. Then, a MobileNet-SSD deep learning model is trained to extract the regions of interest (ROIs) to de-noise the laser stripe image. Finally, the weld line is obtained by fusing information from multiple weld boundaries.

引用

页码：1831 / 1845

页数：15

共 27 条

[11]

Li LY, 2007, LECT NOTES CONTR INF, V362, P319

[12] Urban mapping using DMSP/OLS stable night-time light: a review [J].