Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Weld defect real-time detection method and system based on 3D point cloud

A real-time detection and defect technology, which is applied in optical testing defects/defects, image data processing, instruments, etc., to avoid weld scrap, enhance real-time performance and high accuracy

Active Publication Date: 2022-04-15
苏芯物联技术(南京)有限公司
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: Aiming at the problems existing in the prior art, the present invention provides a real-time detection method and system for weld defects based on 3D point cloud, which can effectively identify the weld surface without building complex machine learning or neural network models Whether there is a defect greatly saves computing resources. At the same time, under a certain camera frame rate, fast and accurate real-time detection can be achieved, so that defects can be found as early as possible in actual production, reducing losses, avoiding weld scrapping, and reducing repair costs. high production value

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
  • Weld defect real-time detection method and system based on 3D point cloud
  • Weld defect real-time detection method and system based on 3D point cloud
  • Weld defect real-time detection method and system based on 3D point cloud

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings, and the technical solution of the present invention will be explained more clearly and completely.

[0036] Such as figure 1 Shown is a real-time detection method for weld defects based on 3D point cloud, including the following steps:

[0037] Step 1. Set the normal weld profile template and distance threshold th based on historical data, preferably th=3;

[0038] Step 1.1, carry out down-sampling process according to the magnification of η, preferably η=0.25 in the embodiment;

[0039] In step 1.2, normalize the down-sampled data to obtain the final template data.

[0040] Step 2. Real-time collection of weld 3D point cloud data;

[0041] 3D point cloud data is formed by scanning the appearance shape of the weld seam in three-dimensional space with the line laser, that is, the longitudinal direction of the weld seam is the Y axis, the cross-sectiona...

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 weld defect real-time detection method and system based on 3D point cloud. The method comprises the following steps: setting a normal weld contour template based on historical data; scanning the cross section of the welding seam through line laser, collecting 3D point cloud data of the welding seam in real time, and recording initial contour data obtained through real-time scanning of the line laser as data; carrying out inflection point detection based on a DBSCAN density clustering algorithm, and determining current weld contour data; and calculating the distance d between the current welding seam contour data and the normal welding seam contour template through a DTW algorithm so as to judge whether defects exist on the surface of the welding seam. According to the method, whether the defects exist on the surface of the weld joint can be effectively distinguished without constructing a complex machine learning or neural network model, calculation resources are greatly saved, meanwhile, rapid and accurate real-time detection is achieved, therefore, the defects are found as early as possible in actual production, losses are reduced, weld joint scrapping is avoided, the repair cost is reduced, and high production value is achieved.

Description

technical field [0001] The invention relates to a method and system for real-time detection of weld defects based on 3D point clouds, belonging to the technical field of intelligent welding. Background technique [0002] The quality inspection during the welding process is very important, which determines whether the weld is qualified and meets the requirements for use. At present, the quality inspection of welds mainly includes: weld appearance shape and surface defect inspection, weld internal defect inspection, weld performance inspection and so on. Among them, the detection of internal defects of welds is mainly realized by non-destructive testing methods such as X-ray and ultrasonic flaw detection. The above methods are mainly used in the detection of welds of pressure vessels and important load-bearing structures. At present, there are perfect and strict quality inspection standards; welds Performance testing includes testing of mechanical properties, corrosion proper...

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): G01N21/88G06T7/00G06T7/521G06V10/762G06K9/62
Inventor 田慧云李波
Owner 苏芯物联技术(南京)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products