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

Braided River Training Image Generation Method

A training image, braided river technology, applied in image data processing, instrumentation, computing and other directions, can solve the problems of inability to accurately obtain training image acquisition methods, large differences in circulation, complex three-dimensional training images, etc. Accurate establishment and reasonable combination of rock facies

Active Publication Date: 2021-08-06
YANGTZE UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Two-dimensional training images are easy to obtain through geological analysis, but three-dimensional training images are more complicated, and its development has experienced manual drawing, computer-based random simulation, flume experiments, outcrop anatomy, etc.
[0003] Braided river is one of the sedimentary types of rivers. Due to the double influence of spin cycle and heterocycle, the deposited sandstone has the characteristics of horizontal quasi-continuous slices, vertical multi-thin layers, and large differences in flowability. Traditional methods cannot accurately obtain its training image acquisition method, therefore, there is an urgent need to obtain a method that can effectively obtain braided river training images

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
  • Braided River Training Image Generation Method
  • Braided River Training Image Generation Method
  • Braided River Training Image Generation Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] This embodiment involves the establishment of multiple models. First, an attributeless model with a grid density of 294×249×24 is established. The number of original grids is 1,756,944. 0.5m.

[0051] Step 1: In the embodiment, starting from core data, combined with modern outcrop data research and sedimentology theory, under the background of braided river sediments, there are four facies in this area: channel, channel, depression, swamp, and bank sand. Deposition patterns such as figure 2 , except for depressions and swamps, they are all facies with high sand content, which are all defined as sand bodies here, and the content of overflowing sand in sand bodies is extremely low, which has little effect on the combination mode of training images, so it can be ignored , only analyze the channel and channel facies in the sand body; it can be determined that the geological characteristics of the sedimentary sand body in the study area are closely combined and continuous ...

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 method for generating a training image of a braided river. The method comprises the steps of (1) establishing a geological knowledge base and obtaining a quantitative geological model; (2) establishing a sand thickness map; (3) using the sand thickness map as a basis to obtain a quantitative geological model As constraints, generate braided river training images. The method of the invention solves the problem of automatic acquisition of training images of overlaid braided rivers. It is based on existing experience and knowledge, combined with statistical parameter constraints of the research area, so that the training images are more consistent with the actual work area.

Description

technical field [0001] The invention relates to the technical field of oil and gas exploration and development, in particular to a method for generating braided river training images. Background technique [0002] Reservoir modeling is the reproduction of geological patterns of subsurface reservoirs. Considering the reservoir modeling process, it is essentially a process of reconstructing the characteristic depositional model of the underground reservoir. If various geological models are regarded as the constituent units of an image, reservoir prediction is also the process of image reconstruction. Based on this idea, at the meeting held by the Stanford Reservoir Prediction Center in 2003, Arpat proposed the Simpat (Simulation with pattern) multi-point geostatistical random geological model, that is, by identifying different geological models and using the similarity judgment method, when modeling reproduce these geological patterns. Since the geological model is processe...

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): G06T17/05G06T17/20
CPCG06T17/05G06T17/20
Inventor 谢鹏飞尹艳树程立华王国亭陈梅韩星
Owner YANGTZE UNIVERSITY
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