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

Method for establishing oil deposit development effect prediction model

A technology for reservoir development and prediction model, applied in the field of oil and gas exploration and development, which can solve the problems of insufficient data volume, short time, and inability to truly and effectively describe the core laws of training samples.

Active Publication Date: 2017-10-10
CHINA PETROLEUM & CHEM CORP +1
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the number of training samples is too small, it is impossible to truly and effectively describe the core laws of the training samples
At present, the field test of single well gas injection in fractured-cavity reservoirs is short and the number of wells is small, which is far from the amount of data required by the traditional BP network

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
  • Method for establishing oil deposit development effect prediction model
  • Method for establishing oil deposit development effect prediction model
  • Method for establishing oil deposit development effect prediction model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 A flow chart of building a reservoir development effect prediction model provided by this embodiment is shown.

[0046] Such as figure 1 As shown, the method provided in this embodiment first uses known reservoir development data to perform K-fold cross-training on the initial neural network in step S101 to obtain K sets of network parameters corresponding to K sets of verification data.

[0047] specifically, figure 2 A flow chart of K-fold cross-training of the initial neural network by using known reservoir development data in step S101 in this embodiment is shown.

[0048] From figure 2It can be seen from the figure that when K-fold cross-training is performed on the initial neural network, the known reservoir development data is firstly divided into K groups in step S201, thereby obtaining K groups of data. In this embodiment, the natural number K is preferably configured as 4. Of course, in other embodiments of the present invention, according to a...

Embodiment 2

[0065] image 3 A flow chart of building a reservoir development effect prediction model provided by this embodiment is shown.

[0066] Such as image 3 As shown, the method provided in this embodiment first divides the known reservoir development data into K groups in step S301, thereby obtaining K groups of data. In this embodiment, the natural number K is preferably configured as 4. Of course, in other embodiments of the present invention, according to actual needs, K can also be configured as other reasonable natural numbers (such as reasonable values ​​in [5, 10], etc.), and the present invention is not limited thereto.

[0067] In step S302, the network parameters of the initial neural network are set to random numbers, and the initial error data is set to infinity, and in step S303, the outer loop flag i is set to 0, and the inner loop flag k is set to 1.

[0068] In step S304, the average network parameter of the i-th round is used as the initial value of the neural...

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 method for establishing an oil deposit development effect prediction model. The method includes the following steps: 1. Using known oil deposit development data to conduct K-fold cross training on an initial neural network, obtaining k sets of network parameters; 2. Based on the k sets of network parameters and the K sets of validation data, computing k sets of error data corresponding to the k set of validation data; 3. Based on the k sets of error data, computing the weight of each set of network parameter, and based on the weight, conducting weighted average on the k sets of network parameters, obtaining an average network parameter, based on the average network parameter, determining an optimized neural network so as to establishing an oil deposit development effect prediction model. Compared with traditional BP neural network algorithm, the method herein can repeatedly use samples, and the limited sample data can be sufficiently used, and achieves training and estimation from different angles.

Description

technical field [0001] The invention relates to the technical field of oil and gas exploration and development, in particular to a method for constructing an oil reservoir development effect prediction model. Background technique [0002] Aiming at the current situation that the methods of improving the development effect such as single well water injection to replace oil are gradually ineffective in fractured-cavity reservoirs entering the middle and late stages of development, the mine field carried out a test of single well gas injection to improve the development effect, and achieved certain results. So far, there is no method that can quantitatively predict the development effect of single well gas injection in fractured-vuggy reservoirs. As a result, it is impossible to provide a more accurate reference basis for selecting which oil wells to perform gas injection. [0003] BP neural network is a multi-layer feed-forward network trained by the error back propagation al...

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): G06Q10/04G06N3/08
CPCG06N3/088G06Q10/04
Inventor 张慧刘中春吕心瑞朱桂良郑松青程倩
Owner CHINA PETROLEUM & CHEM CORP
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com