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

BP neural network laser welding seam forming prediction method based on double optimization

A BP neural network and welding seam forming technology, applied in laser welding equipment, welding equipment, metal processing equipment, etc., to achieve the effect of improving computing speed, eliminating information overlap, and high prediction accuracy

Active Publication Date: 2021-12-24
KUSN BAOJIN LASER TAILOR WELDED
View PDF20 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The invention aims to solve the problems existing in the weld seam quality monitoring in the laser welding process, and proposes a BP neural network laser welding seam shape prediction method based on principal component analysis and genetic algorithm double optimization

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
  • BP neural network laser welding seam forming prediction method based on double optimization
  • BP neural network laser welding seam forming prediction method based on double optimization
  • BP neural network laser welding seam forming prediction method based on double optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described below in conjunction with the examples.

[0044] The present invention adopts laser welding molten pool coaxial monitoring system, such as figure 2 As shown, the laser used can be fiber laser, CO 2 Lasers, semiconductor lasers, etc. The motion system used for welding can be mechanical arms, CNC machine tools, CNC guide rails, etc. The cameras used can be CCD cameras, CMOS cameras, etc. The auxiliary light source can be fiber lasers, xenon lamps, etc. The protective gas can be argon gas, helium, helium-argon mixture, etc.

[0045] TA15 titanium alloy is used as the welding base material, and the T-joint form is taken as an example; the size of the T-joint skin sample used is 150mm×50mm×1.5mm, and the rib plate sample size is 150mm×30mm×10mm.

[0046] The specific experimental method is as follows:

[0047] Step 1: Before welding, the surface of the base metal to be welded needs to be cleaned, first using 10% HNO 3 +30%...

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 BP neural network laser welding seam forming prediction method based on double optimization. Welding seam forming is predicted through a BP neural network method with double optimization of principal component analysis and a genetic algorithm. Compared with a traditional BP neural network method for predicting welding seam forming, the method has the following advantages that molten pool characteristic quantity and welding process parameters are adopted as model input at the same time, and a model is higher in welding seam shape prediction precision; the repeatability of model input layer information is reduced by adopting principal component analysis, information overlapping between features is eliminated, the input dimension of a neural network is reduced, and the model operation speed is improved, so that the requirement of real-time monitoring is met; and the genetic algorithm is adopted to improve an initial weight and a threshold value of the model, so that inherent defects of the BP neural network are improved, the model is prevented from being converged to a local optimal value, and a large error of a prediction result is prevented.

Description

technical field [0001] The invention relates to a double optimization-based BP neural network laser welding seam shape prediction method, which belongs to the technical field of material processing engineering. Background technique [0002] With the development of national defense science and technology, the requirements for the structure and process performance of aerospace equipment are more stringent; the upgrading of aerospace equipment has put forward higher requirements for the manufacturing process, service performance, service life, reliability and automation manufacturing level of structural materials. Requirements; skin grid structure is a typical hollow structure design form, this structure can reduce the weight of structural parts very well, and is widely used in the manufacture of lightweight high-strength components; titanium alloy skin grid structure weldments are large There are many weldment paths, and the requirements for weld quality and stability are high...

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): B23K26/70B23K26/21
CPCB23K26/702B23K26/21
Inventor 雷正龙郭亨通
Owner KUSN BAOJIN LASER TAILOR WELDED
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