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

Friction stir welding quality evaluation method, device and system based on clustering algorithm

A technology of friction stir welding and clustering algorithm, applied in welding equipment, non-electric welding equipment, metal processing equipment, etc., can solve the problems of lack of real-time and efficient monitoring methods, high cycle cost, etc., to shorten the evaluation time and the number of required nodes, The effect of high accuracy and high efficiency

Inactive Publication Date: 2021-04-13
CRRC CHANGCHUN RAILWAY VEHICLES CO LTD
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the current lack of real-time and efficient monitoring methods for the quality of friction stir welding joints and the high cycle cost of using post-weld destructive evaluation, the present invention provides a method, device and system for evaluating the quality of friction stir welding based on clustering algorithms

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
  • Friction stir welding quality evaluation method, device and system based on clustering algorithm
  • Friction stir welding quality evaluation method, device and system based on clustering algorithm
  • Friction stir welding quality evaluation method, device and system based on clustering algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0028] In one of the examples, as figure 1 As shown, the present invention provides a kind of friction stir welding quality evaluation method based on clustering algorithm, and this method comprises the following steps:

[0029] Step 1 (S100): Establish a welding quality evaluation model of friction stir welding equipment based on a clustering algorithm, wherein the clustering algorithm can be adopted but not limited to a self-organized incremental learning neural network or a K-means algorithm, etc., wherein the K-means algorithm can be Reduce the number of cluster centers to further improve the evaluation efficiency. With the continuous development of industrial big data technology, through the accumulation of a large amount of welding experience data, the use of self-organized incremental learning neural networ...

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 relates to a friction stir welding quality evaluation method, device and system based on a clustering algorithm. The friction stir welding quality evaluation method comprises the steps that a welding quality evaluation model of friction stir welding equipment is established based on the clustering algorithm; original data of friction stir welding parameters are obtained, the original data are input into the welding quality evaluation model for analysis and training to form a data clustering center, and a trained welding quality evaluation model is obtained; and current data of the friction stir welding parameters during welding of the friction stir welding equipment are collected, the current data are input into the trained welding quality evaluation model, the current data are classified by the trained welding quality evaluation model according to the data clustering center closest to the current data, and a friction stir welding quality evaluation result is output. The real-time online evaluation of the process quality of a friction stir welding joint is successfully realized on the premise of not influencing the friction stir welding process and not damaging a real product, the efficiency is high, and the accuracy is high.

Description

technical field [0001] The invention relates to the technical field of friction stir welding, in particular to a method, device and system for evaluating the quality of friction stir welding based on a clustering algorithm. Background technique [0002] The friction stir welding process involves many welding parameters and factors, and the influence of each factor is coupled with each other, resulting in a complicated relationship between each factor and welding quality. It belongs to a multi-factor strongly coupled nonlinear time-varying system, and will It has an impact on the quality of the final friction stir welded joint. At present, in the production of friction stir welding, it is necessary to judge the quality through the combination of non-destructive testing and destructive testing. The testing cycle and cost are relatively high, and the delay in testing is not conducive to timely traceability. The detection of process parameters and environmental parameters gives...

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): B23K20/12B23K20/26
CPCB23K20/123B23K20/1235B23K20/1245B23K20/26
Inventor 何广忠闫占奇朱梅奇张学广陆冠含
Owner CRRC CHANGCHUN RAILWAY VEHICLES CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com