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

PIV flow field recovery method based on deep transfer learning

A technology of transfer learning and recovery methods, applied in CAD numerical modeling, design optimization/simulation, etc., can solve the problems of filling flow fields, increasing the cost, difficulty and accuracy, and high cost of data fitting methods

Active Publication Date: 2020-05-19
XI AN JIAOTONG UNIV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method of data fitting to supplement missing data is highly dependent on a large amount of training data, and the high cost and long-term PIV test technology will undoubtedly increase the cost, difficulty and accuracy of this data fitting method
For some situations where the complete flow field cannot be obtained through experimental measurement techniques, it is even more impossible to use this technique to fill in the missing flow field

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
  • PIV flow field recovery method based on deep transfer learning
  • PIV flow field recovery method based on deep transfer learning
  • PIV flow field recovery method based on deep transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention will be further elaborated below in combination with a specific example according to the content of the invention. The following is an application of the present invention, but it is not limited thereto, and implementers can change the parameters according to specific problems and actual application conditions.

[0056] Such as figure 1 As shown, a kind of PIV flow field recovery method based on deep migration learning provided by the present invention comprises the following steps:

[0057]The first step is to obtain the data of the fluid dynamics model

[0058] The data to be collected includes physical model data and corresponding flow field data under various working conditions. Among them, the physical model data represent the distribution of the water domain and solid domain of the experimental object, including the position information of the structured grid nodes and model structure information The global flow field data is the global...

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 PIV flow field recovery method based on deep transfer learning, and the method combines a small part of experiment data with a large part of numerical fitting data, and completes the recovery process from local experiment flow field data to global experiment flow field data. The method has the advantages that when the PIV technology is used for measuring the flow field, good global flow field distribution can be obtained only through reconstruction according to the experimental result of the local flow field, the application range of the PIV technology is expanded, and the use technical threshold of the PIV is reduced; compared with a traditional data processing method, the method has the advantages that deep migration learning is adopted, the accuracy of PIV flowfield reconstruction is further improved by means of a large amount of numerical fitting data, and although the training time is long, the calculation speed of the trained migration network is far higher than that of the traditional data processing method.

Description

technical field [0001] The invention belongs to the technical field of experimental measurement, and in particular relates to a PIV flow field recovery method based on deep transfer learning. Background technique [0002] At present, the experiment solves the problem of flow heat transfer, and mostly uses infrared measurement and control technology, PIV technology and other methods to obtain various flow field information in the experimental section. Among them, the full name of PIV is Particle Imaging Velocity Field Instrument. As a transient flow field test instrument, it mainly includes CCD camera, particle generator, data processing system and other equipment. PIV technology is a widely used speed measurement method today. Compared with the hot-wire anemometer HWFA, laser speed measurement technology LDA, phase Doppler technology PDA, etc. that appeared successively in the early days, PIV technology combines the advantages of single-point measurement and display measurem...

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
IPC IPC(8): G06F30/20G06F111/10
Inventor 谢永慧李云珠张荻张蕾
Owner XI AN JIAOTONG UNIV
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