Unlock instant, AI-driven research and patent intelligence for your innovation.

Reservoir time-shift parameter prediction method and system based on dual network

A reservoir parameter and time-shifting technology, applied in neural learning methods, biological neural network models, measuring devices, etc., can solve problems such as the inability to predict multiple reservoir parameters, and achieve the effect of reducing the amount of training data

Active Publication Date: 2022-02-15
CHINA UNIV OF MINING & TECH (BEIJING)
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to provide a method and system for predicting reservoir time-shift parameters based on dual networks, so as to alleviate the technical problem in the prior art that it is impossible to realize prediction of multiple reservoir parameters at the same time

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
  • Reservoir time-shift parameter prediction method and system based on dual network
  • Reservoir time-shift parameter prediction method and system based on dual network
  • Reservoir time-shift parameter prediction method and system based on dual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] figure 1 It is a flow chart of a method for predicting reservoir time-shift parameters based on a dual network according to an embodiment of the present invention, as shown in figure 1 As shown, the method specifically includes the following steps:

[0025] Step S102, acquire the 3D background seismic data volume and the target well logging curve of the target area; the 3D background seismic data volume includes shot set seismic data, pre-stack angle gather data and post-stack seismic data; the target well logging curve is based on the The target log refers to the log curve measured for the target reservoir parameters.

[0026] Optionally, the target reservoir parameters are parameters that are directly measured or indirectly converted by target logging, such as formation velocity, density, porosity, permeability, fluid saturation, and gas content.

[0027] Step S104, based on the post-stack seismic data, acquire the attributes of the wellbore background seismic data ...

Embodiment 2

[0046] image 3 is a schematic diagram of a dual-network-based reservoir time-shift parameter prediction system provided according to an embodiment of the present invention. Such as image 3 As shown, the system includes: a first acquisition module 10 , a second acquisition module 20 , a first training module 30 , a first prediction module 40 , a second training module 50 and a second prediction module 60 .

[0047] Specifically, the first acquisition module 10 is used to acquire the 3D background seismic data volume and target logging curve of the target area; the 3D background seismic data volume includes shot set seismic data, pre-stack angle gather data and post-stack seismic data; A well curve is a well log measured for a target reservoir parameter based on a target well log on the target area.

[0048] Optionally, the target reservoir parameters are parameters that are directly measured or indirectly converted by target logging, such as formation velocity, density, por...

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 present invention provides a method and system for predicting reservoir time-shift parameters based on a double network, including: obtaining a three-dimensional background seismic data volume and a target well logging curve in a target area; Train the first neural network to obtain the first neural network after training; input the attributes of the three-dimensional background seismic data into the first neural network after training to obtain the prediction result of the three-dimensional background reservoir parameters in the target area; based on the three-dimensional background seismic data Based on the prediction results of volume and three-dimensional background reservoir parameters, the second neural network is trained to obtain the trained second neural network; based on the trained second neural network, the three-dimensional time-lapse reservoir parameters of the target area are predicted. The invention alleviates the technical problem in the prior art that the prediction of multiple reservoir parameters cannot be realized at the same time.

Description

technical field [0001] The invention relates to the technical field of time-lapse seismic exploration, in particular to a method and system for predicting time-lapse parameters of reservoirs based on a double network. Background technique [0002] In the context of clean energy utilization and green mining, it is of great significance to grasp the changes in underground rock structure, stress distribution, and groundwater caused by resource extraction. Formation elasticity, physical parameters, effective stress, resistivity, etc. are effective parameters to characterize the above changes. [0003] Time-lapse seismic exploration is one of the key technologies for reservoir dynamic monitoring, but since only one open-hole logging can be performed in practical applications, it is difficult to directly obtain the logging curves corresponding to the monitoring seismic data after reservoir development, which seriously restricts Prediction accuracy and application effect of time-l...

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 Patents(China)
IPC IPC(8): G01V1/30G06N3/04G06N3/08
CPCG01V1/303G01V1/306G06N3/08G01V2210/6222G01V2210/6224G01V2210/624G01V2210/6244G01V2210/6246G06N3/045
Inventor 李冬彭苏萍郭银玲卢勇旭崔晓芹
Owner CHINA UNIV OF MINING & TECH (BEIJING)