Quality inspection method, device and storage medium based on laser welding

A quality inspection method and laser welding technology, applied in laser welding equipment, welding equipment, neural learning methods, etc., can solve the problems of reducing product accuracy, welding abnormality, and low probability of occurrence, and achieve the effect of improving efficiency and accuracy

Active Publication Date: 2022-04-08
WUYI UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the process of laser welding, welding abnormalities will also occur, which generally include: abnormalities within the distribution and abnormalities outside the distribution; among them, abnormalities within the distribution are common abnormalities, which are relatively easy to distinguish, while abnormalities outside the distribution are due to The probability of occurrence is relatively small, and it is difficult to distinguish, which easily reduces the accuracy of welding quality inspection of products

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
  • Quality inspection method, device and storage medium based on laser welding
  • Quality inspection method, device and storage medium based on laser welding
  • Quality inspection method, device and storage medium based on laser welding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0035] Such as figure 1 As shown, a quality detection method based on laser welding according to an embodiment of the present invention includes:

[0036] Step S100: Collect welding training information within a standard time period; the welding training information includes: normal information, abnormal information within the distribution, and abnormal information outside the distribution;

[0037] Step S200: Divide the abnormality information in the distribution into: the abnormality training information in the distribution and the abnormality detection information in the distribution;

[0038] Step S300: Perform quality classification marking processing on the normal information and abnormal training information within the distribution to obtain marked welding information;

[0039] Step S400: Construct an initial neural network, train the initia...

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 quality inspection method based on laser welding, comprising the following steps: collecting welding training information within a standard time period; dividing abnormal information in distribution into: abnormal training information in distribution and abnormal detection information in distribution; Carry out the marking process of quality classification with the abnormal training information in the distribution to obtain the marked welding information; construct the initial neural network, and train the initial neural network through the marked welding information to obtain a standard neural network; through the abnormal detection information in the distribution and The out-of-distribution abnormal information detects the standard neural network, extracts the standard neural network whose accuracy rate is greater than the accurate threshold, and obtains the target neural network; obtains the welding target information within the target time period, and inputs it into the target neural network for classification processing, and obtains the welding target neural network. The quality type of the target information. The invention can detect and classify the welding quality of products, and improves the efficiency and accuracy of quality detection.

Description

technical field [0001] The invention relates to the field of welding technology, in particular to a quality detection method, device and storage medium based on laser welding. Background technique [0002] Laser welding is an advanced welding process. With its advantages of high energy density, high welding speed, small heat-affected zone of weld seam, small deformation, and high mechanical properties of joints, it occupies an irreplaceable position in various fields of the industry. [0003] However, in the process of laser welding, welding abnormalities will also occur, which generally include: abnormalities within the distribution and abnormalities outside the distribution; among them, abnormalities within the distribution are common abnormalities, which are relatively easy to distinguish, while abnormalities outside the distribution are due to The probability of occurrence is relatively small, and it is difficult to distinguish, which easily reduces the accuracy of produ...

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): B23K26/21B23K26/70G06K9/62G06N3/04G06N3/08
CPCB23K26/21B23K26/702G06N3/08G06N3/045G06F18/2415
Inventor 黄永深李伟科彭健烽邓辅秦冯华
Owner WUYI UNIV
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