A bedrock buried hill oil reservoir rock type identification method based on machine learning

A technology of rock type and machine learning, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem of incompatibility between cost and accuracy

Pending Publication Date: 2019-06-25
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned problem that the existing methods for identifying rock types in oil reservoirs cannot balance both cost and accuracy, the present invention provides a method for ident

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 bedrock buried hill oil reservoir rock type identification method based on machine learning
  • A bedrock buried hill oil reservoir rock type identification method based on machine learning
  • A bedrock buried hill oil reservoir rock type identification method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0030] Taking a bedrock buried hill oil reservoir as an example, refer to the attached figure 1 ,Specific steps are as follows:

[0031] S01: Based on the core data of key wells in a buried hill reservoir (the key wells are coring wells, exploratory wells and evaluation wells for ECS special logging, the same below), it is judged that the pore types of key wells are mainly broken intergranular pores, mineral Dissolution pores, intercrystalline pores; fractures are mainly structural fractures, dissolution fractures and mineral cleavage fractures. Rock structural cracks and broken intergranular pores are filled by proto-rock fine debris, argillaceous matter, carbonate, quartz, iron and chlorite, and the lithology is granite, syenite and quartz monzonite.

[0032] S02: According to the core geological description and oil-bearing grade, drill core samples of oil-bearing intervals in key wells, use electron beams generated by mineral electron probes to act on rock samples, generat...

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 bedrock buried hill oil reservoir rock type identification method based on machine learning in order to solve the problem that an existing oil reservoir rock type identification method cannot give consideration to both cost and accuracy, and the method comprises the following steps: carrying out rock core geology description on a key well of a target block; Analyzing thetypes and contents of oxides and rock-making minerals of the main oil-containing rock; Establishing a three-dimensional lithology discrimination chart of the main oxide content and the rock type through a KNN algorithm; Obtaining an element content curve continuously distributed along the shaft in the target layer of the key well by applying an oxide closed model interpretation technology; Establishing a comprehensive histogram of conventional logging, mineral content and rock type of the key well of the target block; Establishing an elemental oxide content prediction model, and predicting theelemental content of the development well which is not cored and is not subjected to ECS capture logging; And substituting into the established three-dimensional lithology discrimination chart of therock type to realize automatic identification and division of the rock type. The identification method is low in cost and high in accuracy.

Description

technical field [0001] The invention belongs to the field of rock type identification methods for oil reservoirs, in particular to a machine learning-based rock type identification method for bedrock buried hill oil reservoirs. Background technique [0002] In recent years, with the continuous increase of people's demand for oil, conventional oil reservoirs can no longer meet the needs of people's life and industrial production. Subtle oil reservoirs have become one of the important directions of oil and gas exploration, and buried hill oil reservoirs are just one of them. An important concealed oil reservoir. Affected by sedimentary discontinuity, formation uplift, denudation, etc., bedrock buried hill reservoir rocks are characterized by many types of rocks, complex lithology, and large changes in distribution rules. The bedrock buried hill reservoir lithology controls the development degree of fractures and vugs in the reservoir, and then controls the distribution, seepa...

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): G06K9/62G06T17/05
Inventor 孙致学姜宝胜葛成红都巾文何楚翘姜传胤刘垒杨旭刚朱旭晨许业鹏秦浩
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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