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

LBM computational domain planning method based on image recognition

An image recognition and computational domain technology, applied in computing, computer components, character and pattern recognition, etc., can solve the problems of limiting the complexity of LBM model, representation, and boundary complexity.

Pending Publication Date: 2021-03-05
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the programming process, the division of computational domains, wall boundaries, and inlet and outlet boundaries all require limited mathematical expressions to achieve. However, for many practical conditions, including pore flow, lattice growth, and microchannel flow in actual experiments, etc. , its boundaries are usually complex and difficult to represent with simple mathematical expressions, which limits the complexity of the LBM model to a certain extent

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
  • LBM computational domain planning method based on image recognition
  • LBM computational domain planning method based on image recognition
  • LBM computational domain planning method based on image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0015] 1) Image preprocessing implementation process:

[0016] First, crop the experimental image or engineering image so that it can be divided into multiple areas (at least three areas) in a closed manner, perform corresponding grayscale processing, select an appropriate threshold for binarization, and convert the binarized The image matrix is ​​converted into a double-precision matrix to facilitate later processing. Use the regionprop function to identify the image area, extract the pixelist attribute in the returned structure, and return the index coordinates of the segmented area and its pixels.

[0017] 2) Realization process of marked area:

[0018] On the basis of the image of the divided area, continuously display the image and use the mouse tool to mark the pixel point, record the coordinates of the pixel point, and assign and mark all the ...

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 an LBM computational domain planning method based on image recognition, which surpasses the limitation that a mathematical expression required by a traditional specified computational domain expresses a computational domain and boundary conditions, and can divide the computational domain into an integer matrix containing predefined label information based on any closed image (engineering image or actual experimental image). According to the method, after a closed image is input, a plurality of regions are automatically divided through a series of preprocessing, pixel points in the regions can be selected, a drainage basin and a wall surface region are planned according to a predefined integer label, pixel points near the edge of the image are selected to automatically identify a boundary entrance and exit, and planning is also carried out according to a predefined integer. Finally, a matrix with various predefined integer information is output, and different regions and entrances and exits are distinguished by different integers, so that corresponding boundary conditions can be defined according to the predefined integers when the LBM method is used.

Description

technical field [0001] The MATLAB-based image recognition method of the present invention surpasses the limitation of the calculation field of the Lattice Boltzmann method (LBM) represented by traditional mathematical expressions, and can divide the calculation area into an integer matrix based on any closed image. The invention belongs to the field of computational fluid dynamics. Background technique [0002] The Lattice Boltzmann Method (Lattice Boltzmann Method) is a new computational fluid dynamics (CFD) method that was born in the past 30 years. The huge amount of calculation brought by the equation has made great progress in multiphase flow, heat transfer phase transition, magnetic fluid and lattice growth. It is an important computational fluid dynamics method. [0003] With the development of LBM, the models suitable for various force fields, phase transitions and boundary precision are becoming more and more perfect. In the programming process, the division of c...

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): G06K9/40G06K9/20G06K9/34
CPCG06V10/22G06V10/267G06V10/30
Inventor 刘赵淼康子宵任彦霖逄燕
Owner BEIJING UNIV OF 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