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

High-water-cut-period oil reservoir oil well yield prediction method based on machine learning

A prediction method and technology of high water-cut period, applied in nuclear methods, surveying, earthwork drilling, etc., can solve the problems of many factors, large amount of calculation, complicated steps, etc. Effect

Pending Publication Date: 2022-06-03
CHINA PETROLEUM & CHEM CORP +1
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] There are many factors to consider in this method, the actual calculation amount is large, and the steps are relatively complicated

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
  • High-water-cut-period oil reservoir oil well yield prediction method based on machine learning
  • High-water-cut-period oil reservoir oil well yield prediction method based on machine learning
  • High-water-cut-period oil reservoir oil well yield prediction method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Example 1 A method for predicting oil well production in high water-cut oil reservoirs based on machine learning

[0044] The method includes:

[0045] Step 1. Judge the target reservoir and select the appropriate block:

[0046] The method of judging the target oil reservoir is: judging the correlation between the water injection well and the oil production well in the target oil reservoir, select the injection production well with high correlation, draw the production curve of the production well and the water injection curve of the water injection well, and judge the water injection well according to the two curves. Whether there is a co-increase and co-decrease between the water injection amount and the production of the oil production well, if so, the oil reservoir is a suitable oil reservoir.

[0047] Step 2. Detect the data stability of the water injection curve of the water injection well and the production curve of the oil production well respectively. If the ...

Embodiment 2

[0062] Example 2 A method for predicting oil well production in high water-cut oil reservoirs based on machine learning

[0063] Taking oil and water wells in an actual block in China as an example, the method for predicting oil well production in high water-cut oil reservoirs based on machine learning specifically includes:

[0064] A time series curve is drawn for the production data of oil and water wells in this block. The production date of oil and water wells in this block is from March 1969 to December 2018. Draw the co-correlation matrix of water injection wells and oil production wells in this block, such as figure 1 As shown, the brighter the color block, the higher the correlation of production curves between injection and production wells, and the darker the color block, the lower. It can be seen that there is a good correlation between some injection and production wells in this block, and the production curve of Xi 46-6-1 oil production well and the water inject...

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 the technical field of oil field development, in particular to a high-water-cut-period oil reservoir oil well yield prediction method based on machine learning. According to the method, through a vector autoregression algorithm, the oil production of an oil well and the injection rate of a water injection well are jointly used as influence factors in the yield prediction process, a time sequence model is constructed by utilizing liquid quantity change curves of the water injection well and the oil production well, and the time step length of a fitted curve is determined through selection of a lag order; the oil well yield prediction method based on the machine learning algorithm is formed by iteratively calculating the oil well yield under different time steps in the future, and a new thought is provided for oil well yield prediction. The method is simple in model, few in considered variables, easy to calculate and operate, high in accuracy and beneficial to popularization and application.

Description

technical field [0001] The invention relates to the technical field of oilfield development, in particular to a method for predicting oil well production in a high water-cut stage oil reservoir based on machine learning. Background technique [0002] As oil fields enter the stage of high water cut development, a large amount of reservoir static data and development dynamic data provide an important data basis for predicting reservoir development effects through machine learning algorithms. At present, machine learning models are applied in different fields of petroleum exploration and development, such as decision tree method, support vector machine method, neural network method, etc. They determine the relationship between input and output parameters through machine learning algorithms, resulting in the results of the test data set. The factors that affect the accuracy of the prediction model mainly include the size and quality of the data set, the selection of data featur...

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): E21B43/20E21B47/00G06F17/16G06N20/10
CPCE21B43/20E21B47/00G06F17/16G06N20/10Y02A10/40
Inventor 郭奇孙业恒黄迎松李伟忠吕远刘华夏
Owner CHINA PETROLEUM & CHEM CORP
Features
  • Generate Ideas
  • 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