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

A kind of welding seam forming quality monitoring method

A technology of forming quality and training methods, applied in welding equipment, biological neural network models, instruments, etc., can solve the problems of human subjectivity and hysteresis, and achieve the effect of easy computer implementation, simple learning rules, and easy on-site use

Active Publication Date: 2020-05-19
HUAZHONG UNIV OF SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The traditional post-weld observation method to evaluate the weld formation is subjective and hysteresis

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
  • A kind of welding seam forming quality monitoring method
  • A kind of welding seam forming quality monitoring method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] Three typical situations measured: the fusion width is qualified, the penetration depth / reinforcement is unqualified, the penetration depth is qualified, the fusion width / reinforcement is unqualified, the reinforcement is qualified, and the fusion width / depth is unqualified. There are 36 groups of data in total. In this case, 12 groups of data are used as training input data, and the output is defined as (1,0,0), (0,1,0), (0,0,1) respectively.

[0041] According to the kolomogorov theorem: in a three-layer network, the number p of neurons in the hidden layer and the number n of neurons in the input layer satisfy the approximate relationship of p=2n+1. Since n=4, it can be concluded that p=9, The number of neurons in the output layer is m=3, the transfer functions of the hidden layer and the output layer are tansig and purelin respectively, and the trainlm method is used for training.

[0042] Train the forward cascaded BP neural network on the matlab platform, and after...

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 belongs to the field of welding machining, and discloses a welding line forming quality monitoring method. The method comprises the following steps that a, initial data are obtained by collecting welding parameters and welding line forming situations; b, an initial BP neural network model is constructed and subjected to training, and a final BP neural network model is obtained; c, the relational expression among the welding parameters, feature parameters and the welding line forming situations is constructed to serve as a predicting display model; and d, real-time welding parameters during welding line forming are collected and input into the predicting display model, and the needed real-time welding line forming situation is obtained. Through the welding line forming qualitymonitoring method, through real-time measurement of welding current, voltage, speed and the wire stretching amount, the welding line forming situation is objectively evaluated in real time, and imaging display is conducted. Accordingly, the subsequent technology can be guided in time, the quality is improved, losses are reduced, and danger is avoided.

Description

technical field [0001] The invention belongs to the field of welding processing, and more specifically relates to a method for monitoring the quality of weld formation. Background technique [0002] The welding process is a nonlinear, strongly coupled, time-varying multi-variable complex system, which describes the geometric variables of the weld forming quality, such as welding penetration, weld width, weld reinforcement and other direct welding parameters, which are determined by welding voltage, current, welding It is determined by indirect welding parameters such as speed and wire drawing amount. In the welding process, through the measurement of indirect welding parameters, it is required to obtain the evaluation of the quality of weld formation. This requires the establishment of a relationship model between indirect welding parameters and direct welding parameters. [0003] Artificial neural network is a model established by simulating human brain neurons and their ...

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): G05B13/04G06N3/02B23K31/12
CPCB23K31/125
Inventor 胡友民胡秀琨黄帅桑凯旋
Owner HUAZHONG UNIV OF SCI & TECH
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