Whole well pattern water injection development optimization method based on deep learning and graph theory

A technology of deep learning and optimization methods, applied in neural learning methods, mining fluids, earthwork drilling and production, etc., can solve problems such as difficult to expand the swept volume, difficult to obtain better development results, unstable water injection schemes, etc.

Active Publication Date: 2021-01-29
HOHAI UNIV
View PDF22 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the face of complex geological conditions such as medium-high permeability reservoirs with severe planar heterogeneity and low-permeability fractured reservoirs, it is difficult to expand the swept volume due to fast wate...

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
  • Whole well pattern water injection development optimization method based on deep learning and graph theory
  • Whole well pattern water injection development optimization method based on deep learning and graph theory
  • Whole well pattern water injection development optimization method based on deep learning and graph theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments. The drawings in the embodiments are used for further understanding of the present invention, and are used together with the description to explain the present invention, and do not constitute a limitation to the protection scope of the present invention.

[0028] The present invention described in the present invention proposes a method for optimizing water injection development of a full well pattern based on deep learning and graph theory. The specific method is as follows:

[0029] (1) Reference figure 2 and Figure 5 , to obtain the geometric information of the full injection-production target well pattern, and construct a deep convolutional neural network structure; specifically including:

[0030] According to the characteristics of the full injection-production well pattern in the long period, the construction includes...

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 whole well pattern water injection development optimization method based on deep learning and a graph theory. The whole well pattern water injection development optimizationmethod specifically comprises the steps of (1) obtaining the geometric information of a whole injection-production target well pattern, and constructing a deep convolutional neural network structure;(2) dividing by taking a single five-point injection-production well pattern as a basic unit according to a position relationship between a water injection well and a production well of the whole injection-production well pattern, and converging a directed graph by taking five-point dots of the basic unit; (3) acquiring historical production data of the target well pattern, selecting 60% of the historical production data as a training set, and taking the remaining 40% as a verification set; and (4) performing iterative training verification on the convolutional neural network structure by using historical production data, and establishing a convolutional neural network model applied to whole well pattern water injection development optimization. The influence of the water injection amounton the oil production amount can be obtained in continuous model training, and meanwhile, the optimal water injection amount range is obtained, so that a scientific basis is provided for adjusting water injection parameters of a water injection well and effectively improving the oil production efficiency of an oil production well.

Description

technical field [0001] The invention relates to the technical field of oil and gas exploration and development, in particular to an optimization method for water injection development of a full well pattern based on deep learning and graph theory. Background technique [0002] The use of water injection wells to inject water into the oil layer to supplement and maintain the pressure of the oil layer is called water injection. Injecting water into the reservoir can effectively maintain the pressure of the reservoir, increase the oil recovery rate and recovery rate of the reservoir, and is an important means of oil and gas exploration and development. The prediction of oil well production change law in the process of water flooding development is the core content of reservoir engineering research, and it is also an important basis for formulating and adjusting development plans. [0003] After the oil field is put into development, with the increase of production time, the en...

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): E21B43/20E21B43/30E21B49/00G06N3/08G06N3/04
CPCE21B43/20E21B43/30E21B49/00G06N3/08G06N3/04
Inventor 张宏兵严立志韩飞龙尚作萍芮剑文
Owner HOHAI 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