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

A particle image velocimetry method based on convolutional neural network

A technology of convolutional neural network and particle image speed measurement, which is applied in the field of particle image speed measurement based on convolutional neural network, can solve the problems of increasing the calculation amount of correlation analysis method, and achieve the effect of reducing calculation time, high precision and improving calculation efficiency

Active Publication Date: 2021-04-09
ZHEJIANG UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These operations greatly increase the computational load of the correlation analysis method

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 particle image velocimetry method based on convolutional neural network
  • A particle image velocimetry method based on convolutional neural network
  • A particle image velocimetry method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0036] The invention provides a particle image velocity measurement method based on a convolutional neural network, which is characterized in that the method uses a supervised deep learning convolutional neural network (Convolutional Neural Network, CNN) to extract and analyze the velocity field from a two-dimensional fluid particle image . figure 1 For the realization flowchart of the inventive method, it comprises the following steps:

[0037] Step 1: Generate PIV dataset;

[0038] The PIV training data set refers to a large number of artificially generated particle images and corresponding velocity field labels, which are used for the training of convolutional neural networks. Each data item used for training in the data set contains two consecutive frames of particle images f 1 ,f 2 and a velocity vector field ω.

[0039] In ...

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 particle image velocity measurement method based on a convolutional neural network, which uses a supervised learning method to solve the problem of extracting a velocity field from a two-dimensional fluid particle image. The method includes steps of generating PIV data sets, building a neural network model, reading particle images, preprocessing, network operation, and postprocessing. Among them, there are two ways of PIV data: one is to generate a particle map with a known velocity field, and the other is to generate a velocity field from an existing experimental particle map. The network model is a convolutional neural network, and the PIV convolutional neural network model is obtained through training parameters. The input is two images, and the output is the velocity vector field of each pixel on the image. By applying the invention, a high-resolution and high-precision velocity field can be obtained from a particle image, and at the same time, the computing efficiency of the velocity measurement of the particle image can be improved.

Description

technical field [0001] The present invention relates to a velocity field extraction method using deep learning technology to realize particle image velocimetry, in particular to a particle image velocimetry (PIV for short) method based on a convolutional neural network. Background technique [0002] PIV is a modern laser velocity measurement technology, which is mainly used to measure the velocity of fluid motion, and plays a vital role in the study of fluid dynamics theory and experiments. PIV obtains the global velocity field of the fluid by adding fluorescent tracer particles into the measured medium, and then using the motion of the tracer particles in the flow field. Among them, how to obtain the velocity field from the particle image is the key to the particle image velocimetry technology. [0003] The traditional particle image velocimetry technology adopts the correlation analysis method. The correlation analysis method selects a window from the first frame image, ...

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): G01P5/22G06N3/04
CPCG01P5/22G06N3/045
Inventor 许超蔡声泽高琪周世超
Owner ZHEJIANG 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