Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Joint pre-stack elastic inversion parameter and deep network target inversion technology

A deep network, elastic impedance inversion technology, applied in the field of target inversion, can solve the problems of increasing cumulative error, result inaccuracy, and reducing accuracy, so as to improve the degree of representation, enhance the reliability and authenticity, and improve the The effect of accuracy

Active Publication Date: 2021-11-05
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF16 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing target inversion technology obtains the parameters required for target fitting, such as P / S wave velocity and density through seismic data inversion, and then obtains the target parameters through fitting, which will inevitably increase the cumulative error in the calculation process, resulting in inaccurate results. The target parameters obtained by fitting are an approximate solution, and the accuracy is relatively low, and the accuracy of re-fitting through calculation will be greatly reduced; therefore, we propose a joint pre-stack elastic inversion parameter and deep network target inversion technology

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
  • Joint pre-stack elastic inversion parameter and deep network target inversion technology
  • Joint pre-stack elastic inversion parameter and deep network target inversion technology
  • Joint pre-stack elastic inversion parameter and deep network target inversion technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] refer to figure 1 , this embodiment discloses a joint pre-stack elastic inversion parameter and a deep network target inversion technology. The specific steps of the target inversion technology are as follows:

[0038] S1. Calculate the well data to obtain the pre-stack elastic impedance inversion parameters;

[0039] Specifically, the pre-stack elastic impedance inversion parameters include compressional wave velocity, shear wave velocity and density.

[0040] S2. Carry out an angle division on the side channel pre-stack seismic data, and obtain the pre-stack parameters of the division angle;

[0041] Specifically, the pre-stack parameters for dividing angles include large-angle data, medium-angle data, and small-angle data.

[0042] S3. Taking the well bypass data corresponding to each time point on the well bypass as input, and the well bypass target data at this time point as output constraints;

[0043] S4, establishing a training network;

[0044] In addition,...

Embodiment 2

[0049] refer to figure 2 , this embodiment discloses joint pre-stack elastic inversion parameters and deep network target inversion technology; this embodiment mainly describes the deep neural network algorithm except for the same steps as embodiment 1;

[0050] In this embodiment, the deep neural network algorithm (DNN) is used to establish the relationship between the label data set and the training data set to form a prediction network, which uses neural network technology, which is also called a perceptron, and has an input layer, The output layer and a hidden layer. The input feature vector reaches the output layer through the hidden layer transformation, and the classification result is obtained in the output layer. DNN can be understood as a neural network with many hidden layers;

[0051] It needs to be further explained that the deep neural network algorithm can be divided according to the position of different layers, and its internal neural network layers can be di...

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 joint pre-stack elastic inversion parameter and deep network target inversion technology, and relates to the technical field of target inversion. The target inversion technology comprises the following specific steps of: obtaining pre-stack elastic impedance inversion parameters; obtaining pre-stack parameters of a division angle; taking well bypass data as input and target data as output constraint; establishing a training network; obtaining a mapping network through training, and directly carrying out mapping calculation on all-region data; and inputting all-region data parameters, and directly obtaining a target data body through the mapping network. According to the method, seismic target parameters can be better predicted, the prediction accuracy and efficiency are improved, data internal information is deeply mined through the deep network, the characterization degree of the information is improved, accumulative errors and approximate errors existing in the process of solving target data through fitting are solved, and the credibility and authenticity of the algorithm are enhanced directly through parameters and different angle data obtained through pre-stack inversion.

Description

technical field [0001] The invention relates to the technical field of target inversion, in particular to the joint pre-stack elastic inversion parameter and deep network target inversion technology. Background technique [0002] In shale gas engineering sweet spot prediction (or in the current exploration sweet spot prediction) there are many times, we can obtain a curve that matches the actual parameters through fitting calculation from well data, such as in-situ stress curve, formation pressure curve, brittleness curve, etc. The curve is often obtained through various elastic parameters on the well, including parameters such as compressional and shear wave velocity and density; the well is a single-point prediction, and the prediction from point to surface requires the processing of seismic data. Wave velocity, density and other parameters required for target fitting, and then obtaining the target parameters through fitting will inevitably increase the cumulative error in...

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): G01V1/36G01V1/30G06N3/06
CPCG01V1/362G01V1/307G06N3/061
Inventor 蒋旭东曹俊兴王兴建祖绍环蔡紫薇
Owner CHENGDU UNIVERSITY OF TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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