焊接
软件
计算机视觉
人工智能
机器视觉
计算机科学
自动化
机器人焊接
步进电机
像素
分割
MATLAB语言
机器人
工程类
机械工程
材料科学
操作系统
纳米技术
程序设计语言
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI