Door plate welding spot identification and welding path planning method

A welding path and path planning technology, applied in welding equipment, auxiliary welding equipment, neural learning methods, etc., can solve problems such as poor adaptability and poor real-time performance, and achieve strong adaptability, improve efficiency, and improve efficiency and accuracy. Effect

Inactive Publication Date: 2020-08-18
SOUTH CHINA UNIV OF TECH
View PDF11 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Significantly improve productivity and solve traditional problems such as poor adaptability and poor real-time performance

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

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Door plate welding spot identification and welding path planning method
  • Door plate welding spot identification and welding path planning method
  • Door plate welding spot identification and welding path planning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] A door panel welding spot recognition and welding path planning method, comprising the following steps:

[0039] S1. Use a Gaussian filter to filter an image of a car door panel containing solder joints. The filter formula is:

[0040]

[0041] f s (x,y)=f(x,y)*G(x,y,σ)

[0042] Among them, f(x,y), f s (x, y) respectively represent the gray value of each point in the image before and after filtering, G(x, y, σ) is a two-dimensional Gaussian formula, x, y, σ represent the abscissa, ordinate, standard Difference.

[0043] S2. Perform labeling processing on the image of the automobile door panel to determine the type of solder joints in the image of the automobile door panel, and obtain a labeled data set.

[0044] The distribution of solder joints on the automobile door panel is messy, such as circular, semicircular, oval, etc., so these solder joints need to be labeled. In this embodiment, the labeling tool LabelImg is used to perform the labeling process. The sp...

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

The invention discloses a door plate welding spot identification and welding path planning method. The method comprises the following steps of performing labeling processing on an automobile door plate image to determine the type and the position of a welding spot in the automobile door plate image and obtaining a data set subjected to the labeling processing; establishing a yolo network model, and inputting the data set into the yolo network model for training; inputting a welding spot picture to be detected into a trained yolo network model for detecting to identify the type of each weldingpost and the position coordinates of each welding spot; and performing path planning through a path planning algorithm to obtain a welding path. According to the door plate welding spot identificationand welding path planning method, a deep learning target detection algorithm is applied to an automobile door plate welding production line, so that the efficiency is greatly improved and the weldingtime is shortened quickly.

Description

technical field [0001] The invention relates to the technical field of automobile control processing, in particular to a door panel welding spot recognition and welding path planning method. Background technique [0002] Research on robot path planning began in the 1970s. At present, with the in-depth research of multi-robot systems by scholars at home and abroad, the multi-robot system has made great progress and achievements in theory and practice, and has gradually established a complete simulation system and hardware experiment system. The path planning problem is a core key part in the field of robotics research. Robot motion planning includes three levels of content: path planning, trajectory planning, trajectory tracking or trajectory control. Path planning is to determine the geometric path without time information. Generally, industrial robots contain common path planning such as point-to-point, straight line, arc and spline curve. Robot path planning can be intui...

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 Applications(China)
IPC IPC(8): B23K37/00B23K37/02B25J9/16B25J11/00B25J19/04G06K9/00G06K9/40G06K9/62G06N3/00G06N3/04G06N3/08
CPCB23K37/00G06N3/006G06N3/08B23K37/0247B23K37/0252B25J9/1605B25J9/1664B25J9/1679B25J11/005B25J19/04B25J9/161G06V20/20G06V10/30G06N3/045G06F18/24
Inventor 黎善斌袁志杰
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap