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

Multi-attribute seismic information fusion fracture prediction method based on neural network

A crack prediction and seismic information technology, applied in seismic signal processing, seismology, geophysical measurement, etc., can solve the problems of low prediction accuracy, low efficiency, strong randomness of weight coefficients, etc., and achieve the effect of improving prediction accuracy.

Active Publication Date: 2017-06-20
CHINA NAT OFFSHORE OIL CORP +1
View PDF8 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of strong randomness of weight coefficients, low efficiency and low prediction accuracy in the existing information fusion technology, the present invention provides a method for fracture prediction based on neural network multi-attribute seismic information fusion to improve work efficiency and information The purpose of fusion fracture prediction volume accuracy

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
  • Multi-attribute seismic information fusion fracture prediction method based on neural network
  • Multi-attribute seismic information fusion fracture prediction method based on neural network
  • Multi-attribute seismic information fusion fracture prediction method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] Example 1: Fracture prediction in Krisna Oilfield, Indonesia

[0072] The work area involved in the Indonesian Krisna Oilfield is relatively small, and has relatively sufficient core and imaging logging data. Through the above-mentioned technical scheme 1, the fracture prediction research of the carbonate rock reservoir in this work area is carried out.

[0073] Through core description and loss analysis, it is believed that there are fractures in the LBR layer of Krisna Oilfield. According to the acquisition of seismic data in the Krisna Oilfield, two methods of azimuth anisotropy and difference in far and near offset attributes are selected to predict fractures, and the fractures with azimuth anisotropy attributes are obtained according to step 2 (pre-stack seismic multi-attribute fracture prediction) Prediction volume and fracture prediction volume with far and near offset attributes) method and process to obtain fracture prediction volumes with corresponding seismi...

Embodiment 2

[0076] Example 2: Prediction of Fractures in Block AG of Missan Oilfield in Iraq

[0077] The work area involved in Iraqi Missan Oilfield is relatively large. Due to the war, core and imaging logging data are relatively scarce. In view of this data situation, we improved the technical plan 1 and adopted the technical plan 2 for the carbonate rock in the work area. Reservoir fracture prediction research.

[0078] Through the core description and production performance analysis, it is believed that there are fractures in the A and B oil groups in the AG block of the Missan Oilfield. According to the acquisition of seismic data in Missan Oilfield, two methods of azimuthal anisotropy and detection based on local structural entropy discontinuity were selected to predict fractures, and the azimuthal anisotropy was obtained according to step 3 (pre-stack seismic multi-attribute fracture prediction) The fracture prediction volume of the attribute and the fracture prediction volume of...

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 multi-attribute seismic information fusion fracture prediction method based on a neural network. The method comprises the steps of (1) single well fracture development strength curved fitting, (2) prestack seismic multi-attribute fracture prediction and the obtainment of a fracture prediction body of an azimuthal anisotropy attribute and a fracture prediction body of a far and near offset distance attribute, (3) the time-depth conversion of a seismic attribute fracture prediction body and the obtainment of a depth domain fracture prediction body, (4) depth domain fracture prediction body coarsening, and (5) prestack seismic attribute fracture information fusion based on a BP neural network. According to the method, a BP neural network algorithm is fused into the process of multiple seismic attribute facture prediction information fusion, a scientific and objective fusion fracture prediction body is obtained, seismic data and single well data are combined, the single well constraint of a seismic attribute body is carried out, and the prediction accuracy is improved further.

Description

technical field [0001] The invention relates to the exploration and development of fractured carbonate rock oil and gas reservoirs, in particular to a fracture prediction method based on BP neural network fusion of multi-attribute seismic information. Background technique [0002] Currently developed carbonate reservoir fracture prediction technologies include: shear wave splitting, P-S converted wave, multi-component seismic, multi-azimuth VSP, longitudinal wave AVAZ, etc. One of the most effective methods is the shear wave splitting technique. However, the cost of shear wave acquisition and processing is extremely high, and the oil field investment risk is high, so it cannot become a common technology. However, multi-component seismic, multi-azimuth VSP, and P-S converted wave technologies have good results, but either the exploration costs are high, or they are unconventional seismic acquisition projects, which are difficult to be widely used in China at this stage. At ...

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): G01V1/30
CPCG01V1/30G01V2210/512
Inventor 史长林万盾魏莉但玲玲李德鹏张剑吴蔚
Owner CHINA NAT OFFSHORE OIL 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