Unlock instant, AI-driven research and patent intelligence for your innovation.

Partial image processing based butt type welding seam recognition method

A recognition method and partial image technology, applied in character and pattern recognition, computer parts, instruments, etc., to achieve the effect of improving the speed of weld recognition

Inactive Publication Date: 2008-07-30
SHANGHAI JIAOTONG UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has the advantage of strong adaptability, but also has the disadvantage that the initial position of the weld needs to be given in advance

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] In order to better explain the technical solutions of the present invention, further detailed descriptions are given below with reference to the embodiments.

[0016] 1. Set the parameters required in the welding seam recognition calculation process: specify the position and size of the image area, the width threshold of the weld seam, and the weld seam search termination threshold. In general, the specified image area is set as a rectangular window in the middle of the image, the side length is one-third of the side length of the entire image, the width threshold of the weld is set to d1 = 8 pixels, and the weld search termination threshold is d2 = 4 pixels. Then use a CCD camera under natural light to capture an image including the entire weld. When shooting, it is required that the edge of the weld must pass through the designated image area in the center of the image.

[0017] 2. Extract all edge points within the specified image area. Perform median filtering on...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

This invention relates to calibration type weld beam identification method based on local image process, which comprises the following steps: using CCD cameral under natural light to catch total weld beam image through pre-set image area; then processing image filter, fringe test and weld beam identification in the designed area to get two local weld fringe; finally starting from local weld fringe two ends to overlap and research remaining part of the rectangle window connected with the weld beam to get whole fringe.

Description

technical field [0001] The invention relates to a butt-type welding seam identification method based on local image processing, which can be widely used in robot welding and the like. It belongs to the field of advanced manufacturing and automation. Background technique [0002] Intelligent robot welding has become the main development direction of welding automation. The welding robots currently used in the industry mainly work in the teaching and reproducing work mode. Before welding new workpieces, a large amount of manpower is required to teach the welding seam, which is especially obvious in small batch production. On the other hand, robots based on the teaching work mode cannot perceive changes in workpiece size, clamping position, etc., and when these factors change, the welding quality will decrease. Therefore, it is of great significance to automatically identify the edge of the weld by means of visual sensing, which can improve production efficiency and welding q...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
Inventor 石繁槐林涛陈善本
Owner SHANGHAI JIAOTONG UNIV