Paper
5 November 2020 A method for measuring the width of welding seam based on machine vision
Author Affiliations +
Proceedings Volume 11568, AOPC 2020: Optics Ultra Precision Manufacturing and Testing; 1156816 (2020) https://doi.org/10.1117/12.2579886
Event: Applied Optics and Photonics China (AOPC 2020), 2020, Beijing, China
Abstract
Aiming at the problems of low measurement efficiency and large measurement error when manually measuring the width of the welding seam using the welding seam ruler, a method for measuring the width of the weld seam based on machine vision was proposed in this paper. Firstly, the hardware of the measuring device was designed. The hardware included a measurement platform, an image acquisition and control module, a computer. One motor guide, one stepper motor, an industrial camera and a lighting source were installed on the measurement platform. Secondly, based on Matlab + OpenCV, the measurement software was developed. The software included five functions: controlling the stepper motor and the lighting source, receiving weld seam images, preprocessing the images, segmenting images, correcting images and calculating the width of the weld seam. The image segmentation was implemented by GrabCut algorithm, which could extract the weld area very well. The calculation of the weld width was based on the imaging size and resolution of the industrial camera and the pixels positions on the upper and lower edges of the weld area. Finally, a measurement experiment was carried out on the width of the weld. According to the measurement results, the measurement accuracy of the width of the welding seam reached to 0.1 mm and the measurement speed reached to 30.7 mm / s. The results showed that measuring the width of the welding seam based on machine vision could replace manual measurement and be applied to industrial automation.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wei Jin and Hai-bin Sun "A method for measuring the width of welding seam based on machine vision", Proc. SPIE 11568, AOPC 2020: Optics Ultra Precision Manufacturing and Testing, 1156816 (5 November 2020); https://doi.org/10.1117/12.2579886
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Machine vision

Cameras

Image acquisition

Light emitting diodes

Software development

Connectors

Back to Top