Porous medium super dimensional reconstruction method based on learning

A technology of porous media and three-dimensional images, applied in image data processing, instrumentation, calculation, etc., can solve the problems of long reconstruction time of multi-point geostatistical algorithms, differences in statistical features, and inaccurate morphological features of reference images.

Active Publication Date: 2016-09-21
SICHUAN UNIV
View PDF8 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Usually, these algorithms have different degrees of defects: the reconstruction results of the simulated annealing algorithm are not accurate enough to describe the morphological ch...

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
  • Porous medium super dimensional reconstruction method based on learning
  • Porous medium super dimensional reconstruction method based on learning
  • Porous medium super dimensional reconstruction method based on learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] In order to make the learning-based porous medium hyperdimensional reconstruction method of the present invention easier to understand and close to real applications, the following selects 128 original CT image sequences as the training set and uses the sampling strategy at intervals to establish a dictionary. According to the established dictionary The image is reconstructed by layer-by-layer reconstruction, the neighborhood matching strategy of pixel values ​​in the reconstruction process, and the operation process of a series of processes such as pixel value filling by block matching on the basis of the reconstruction results are described as a whole.

[0050] The specific operation steps are as follows:

[0051] (1) Select 128 original CT image sequences of real rock samples as the training set. The CT sequences and their three-dimensional structures are as follows: figure 1 shown. The selected CT image sequence should be complete, so that the established dictionar...

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 porous medium super dimensional reconstruction method based on learning. Based on a three-dimensional modeling problem of a porous medium two-dimensional image, a learning method in super resolution reconstruction is introduced in porous medium three-dimensional reconstruction by the porous medium super dimensional reconstruction method, and a dictionary from a single image to a three-dimensional structure is established, and then a super dimensional concept is proposed. The porous medium super dimensional reconstruction method is characterized in that an original CT image sequence is selected, and is used as a training set; the super dimensional reconstruction method is used to establish the dictionary from every two-dimensional image layer of the original three-dimensional CT sequence to the three-dimensional structure of the corresponding positions of five CT image layers including the above mentioned layer by using the super dimensional reconstruction method. Based on the original reference image, a matched three-dimensional structure is searched in the established training set, and the super dimensional reconstruction is realized. A good explanation is provided for a real porous medium microstructure by the reconstructed three-dimensional microstructure, which can be used for the researching of the porous medium microstructure electrical characteristics and the porous flow characteristic, and has the practical value.

Description

technical field [0001] The invention relates to a three-dimensional modeling method based on two-dimensional images, in particular to a learning-based hyperdimensional reconstruction method of porous media, belonging to the technical field of three-dimensional image reconstruction. Background technique [0002] Many industrial applications involve the problems of porous media, such as the development of low and ultra-low permeability oil and gas fields, the utilization of groundwater, the exploitation of gas beds, and the preparation of metal materials, etc. Accurate three-dimensional reconstruction of porous media, and on this basis extract the pore network in the media, and animate the flow of fluid in the media pores, which can not only help people to quickly and conveniently determine the relevant physical parameters of porous media through computer experiments, but also for It is also very helpful to study the influence of the spatial structure of porous media on pore f...

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): G06T3/40
CPCG06T3/4053
Inventor 滕奇志何小海李洋李征骥王正勇吴晓红
Owner SICHUAN 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