Check patentability & draft patents in minutes with Patsnap Eureka AI!

Lithology identification method based on reservoir element target invariant feature description

A technology for lithology identification and feature description, applied in the field of lithology identification, it can solve the problem that the original spatial amplitude feature of the logging curve does not have inter-well invariance, and achieve the effect of improving the accuracy and reliability and enhancing the generalization ability.

Active Publication Date: 2021-07-16
NORTHEAST GASOLINEEUM UNIV
View PDF13 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve the problem that the original spatial amplitude characteristics of existing logging curves do not have inter-well invariance

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
  • Lithology identification method based on reservoir element target invariant feature description
  • Lithology identification method based on reservoir element target invariant feature description
  • Lithology identification method based on reservoir element target invariant feature description

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] Combine below figure 1 Illustrate this embodiment, the lithology identification method described in this embodiment based on the invariant feature description of reservoir element target, it comprises the following steps:

[0092] Step S1: Obtain the reservoir correlation feature by taking the correlation measure of adjacent points in the vertical direction for each depth sampling vector and take the difference of the measurement distance of the correlation feature to obtain the corresponding correlation difference feature, so as to realize the correlation between multiple logging curves. Correlation invariant feature extraction;

[0093] Step S2: By performing lateral singular value decomposition on the neighborhood vector set of each deep sampling vector, the extraction of tensor features of the multi-curve reservoir structure and the vertical local binary pattern (LBP, Local Binary Patterns) for each curve are performed. ) Texture feature extraction to realize the f...

Embodiment 2

[0100] The further limitation of the lithology identification method based on the invariant feature description of the reservoir element target described in the first embodiment,

[0101] The method for extracting relevant invariant features in step 1 is:

[0102] Traditional well logging features do not fully consider the lateral correlation and related transformation information of multiple logging curves at the same depth, and this kind of information just has the invariance ability of reservoir description between wells.

[0103] However, specifically, for a data set composed of multiple curves of a certain well, since each depth sampling vector is composed of multiple values ​​from different curves, it is possible to take the longitudinal value of the depth sampling vector of the logging curve Reservoir correlation characteristics can be obtained by measuring the correlation of adjacent points above. Among them, the correlation features mentioned in this patent mainly in...

Embodiment 3

[0106] The further limitation of the lithology identification method based on the invariant feature description of the reservoir element target described in the first embodiment,

[0107] The method for extracting the structure invariant feature in step 2 is:

[0108] Structural invariant features refer to features that detect or describe local structures that remain invariant to geometric transformations. The basic idea is to extract the essential attributes of local structures for description. Specifically, the structure-invariant information involved in this patent mainly includes texture feature descriptions such as structure tensors and local binary patterns.

[0109] For a well logging curve set, for a certain depth sampling vector S i , let N(S i ) represents the depth sampling vector S i is the local neighborhood of the center (the neighborhood radius is generally set to about 0.5 meters). Then the extraction of structural tensor features can be realized by analyzing...

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 provides a lithology identification method, and particularly relates to a lithology identification method based on invariant feature description of a reservoir element target. According to the method, logging curve invariant features are extracted and described, automatic layering of element targets is achieved, meanwhile, the invariant features of the element targets are embedded into a lithology identification machine learning model, lithology prediction is finally achieved in unknown well machine model application, while local reservoir personality is reserved, the generalization ability of reservoir description is greatly enhanced, the bottleneck problem that cross-well generalization ability restricts introduction of a machine learning method when lithology identification is carried out by using a logging curve at present is solved, and the reservoir description precision and reliability are also improved.

Description

technical field [0001] The invention proposes a lithology identification method, in particular to a lithology identification method based on the invariant feature description of reservoir element targets. Background technique [0002] As most of the mature oilfields in my country have entered the mid-to-late stage of development, the exploration and development of unconventional oil and gas resources has become the most important way for the current mature oilfields to achieve stable production, increase production and prolong production life. Whether it is the exploration and development of unconventional oil and gas resources in old oil fields, or the accurate prediction and development of new oil and gas resources, it is an unavoidable problem faced by major oil field companies in my country today. [0003] Geophysical logging data is one of the most important information sources for obtaining description information of oil and gas reservoir resources. Since the stratifi...

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): G16C20/70G16C20/30G06N20/20G06Q10/04G06Q50/02
CPCG16C20/70G16C20/30G06N20/20G06Q10/04G06Q50/02Y02A10/40
Inventor 曹志民阳璨吴云韩建全星慧付天舒
Owner NORTHEAST GASOLINEEUM UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com