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

Novel oil and gas prediction method fusing artificial neural network and geostatistics

An artificial neural network and geostatistics technology, which is applied in the field of oil and gas prediction integrating artificial neural network and geostatistics, and can solve problems such as inability to implement

Pending Publication Date: 2021-11-02
CHINA PETROLEUM & CHEM CORP +1
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this technology only predicts the location of the well point, and of course only uses logging data. It is impossible to perform three-dimensional space prediction in a location without drilling

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
  • Novel oil and gas prediction method fusing artificial neural network and geostatistics
  • Novel oil and gas prediction method fusing artificial neural network and geostatistics
  • Novel oil and gas prediction method fusing artificial neural network and geostatistics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to make the above and other objects, features and advantages of the present invention more comprehensible, the preferred embodiments are listed below and shown in the accompanying drawings in detail as follows.

[0021] Such as figure 1 as shown, figure 1 It is a flow chart of the new method of oil and gas prediction combining artificial neural network and geostatistics of the present invention.

[0022] In step 101, the seismic attributes related to the physical properties of the reservoir are extracted around the well, and the arithmetic mean value is calculated after time-depth conversion in a certain interval, and the same process of calculating the arithmetic mean value is performed on the logging data. This can highlight the geological features of the entire interval. The process goes to step 102.

[0023] In step 102, use the Kendal l (in statistics, one of the three famous correlation coefficients named after Maurice Kendal l) grade correlation coeff...

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 provides a novel oil and gas prediction method fusing an artificial neural network and geostatistics. The novel oil and gas prediction method fusing the artificial neural network and geostatistics comprises the following steps: 1 averaging layers of earthquake and logging data; 2 carrying out Kendall correlation analysis on the seismic data and the logging data; 3 training the artificial neural network at the well point; 4 combining seismic logging and geological statistics to obtain three-dimensional distribution of reservoir physical property parameters; 5 training a second artificial neural network at the well point; and 6 performing oil and gas three-dimensional prediction. According to the novel oil and gas prediction method fusing the artificial neural network and geostatistics, an artificial neural network method and a geostatistics method are combined, a large amount of data from different disciplines can be processed in a highly nonlinear mode, various data information can be fused, and respective advantages of an artificial intelligence technology and a geostatistics technology are fully played.

Description

technical field [0001] The invention relates to the technical field of seismic data processing and interpretation, in particular to a new oil and gas prediction method integrating artificial neural network and geostatistics. Background technique [0002] In the field of petroleum exploration and development, there are many methods to integrate data from different disciplines and predict oil and gas by building a detailed reservoir model. Divided by subject type, data can be divided into geological data, drilling and logging data, oil and gas production data, and seismic data. Seismic data is a vital source of information no matter in the exploration stage or in the development stage, because earthquake The data not only has the ability to cover a large area in three dimensions, but also has a relatively dense grid density. In order to predict and analyze the distribution of reservoir parameters in favorable regions, a reliable relationship between reservoir physical propert...

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): G01V1/28G01V1/30G01V1/40G06N3/04G06N3/08G06F17/18
CPCG01V1/282G01V1/306G01V1/40G06N3/08G06F17/18G01V2210/6652G06N3/045
Inventor 程远锋张云银韩宏伟慎国强钮学民王希萍孙金磊
Owner CHINA PETROLEUM & CHEM CORP