A method for predicting molten pool state in perforated plasma arc welding based on deep learning algorithm

A deep learning, plasma arc technology, applied in plasma welding equipment, welding equipment, computers, etc., can solve the problem of low generalization ability of training models, reduce data processing time and memory running space, improve efficiency, and facilitate collection Effect

Active Publication Date: 2022-04-01
SHANDONG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a method for predicting the state of the perforated plasma arc welding molten pool based on a deep learning algorithm, which solves the problem of low generalization ability of the training model

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 method for predicting molten pool state in perforated plasma arc welding based on deep learning algorithm
  • A method for predicting molten pool state in perforated plasma arc welding based on deep learning algorithm
  • A method for predicting molten pool state in perforated plasma arc welding based on deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] A method for predicting the molten pool state of perforated plasma arc welding based on a deep learning algorithm, including a training process and a testing process, the steps are as follows:

[0042] 1. Build an experimental platform; the experimental platform includes workpieces to be welded, such asfigure 1 , 2 As shown, a welding torch and a CCD camera are installed on one side of the workpiece to be welded. The CCD camera is used to collect the information of the front molten pool. A lot of molten pool information such as reflected arc light, pinhole information, and shape of molten pool metal. Because the distance between the plasma arc welding torch and the welding material is too close, it is not conducive to the installation of the CCD camera. The CCD camera is installed in the vertical direction of the welding direction and forms a certain angle with the horizontal direction. On the other side of the workpiece to be welded, directly below the welding torch, ...

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 perforated plasma arc welding molten pool state prediction method based on a deep learning algorithm, which belongs to the technical field of perforated plasma arc welding. An experimental platform is built, a CCD camera is set to collect molten pool images, a photosensitive sensor is set to collect photosensitive information, and a pulse current is selected. Perform welding, collect image information and perforation information, perform feature matching on the acquired image and photosensitive information, and establish a deep learning model. The front molten pool image is used as the input of the network, and the perforation status information is used as the output for training, and then the deep learning model is verified. , carry out secondary development of the verified model, and deploy it to the computer; through real-time acquisition of images as input, the perforation state is obtained, and then the obtained perforation state is used as a basis to modify the welding parameters to control the welding process, expanding the database of training data, The accuracy of molten pool state prediction is improved, and the generalization ability and robustness of the trained model are improved.

Description

technical field [0001] The invention relates to a perforation plasma arc welding molten pool state prediction method based on a deep learning algorithm, which greatly improves the accuracy of penetration prediction, and belongs to the technical field of perforation plasma arc welding. Background technique [0002] Because it can weld medium and thick plates, and single-sided welding and double-sided forming, perforated plasma arc welding occupies a pivotal position in modern manufacturing. However, the pinhole behavior seriously affects the welding process stability, penetration and joint quality. The prediction and control of pinhole behavior is imperative for the development of automated and efficient welding methods. [0003] In recent years, with artificial intelligence setting off a new round of industrial revolution on a global scale, the outstanding performance of deep learning algorithms in image feature extraction and mathematical modeling has brought new possibili...

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): G06F11/30G06T1/40B23K10/02
CPCB23K10/02
Inventor 贾传宝李云张金衡周卫鲁周方正于长海
Owner SHANDONG 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap