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

A Neural Network-Based Method for Extracting Slow Diffusion and Multiple Parameters from Ground-to-Space Electromagnetic Data

A neural network, multi-parameter technology, applied in the field of electromagnetic exploration, to achieve the effect that is conducive to refinement

Active Publication Date: 2021-10-22
JILIN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies of existing electromagnetic data parameter extraction methods, and provide a multi-parameter extraction method for ground-air electromagnetic data based on a slow diffusion fractional order model based on actual underground complex media

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
  • A Neural Network-Based Method for Extracting Slow Diffusion and Multiple Parameters from Ground-to-Space Electromagnetic Data
  • A Neural Network-Based Method for Extracting Slow Diffusion and Multiple Parameters from Ground-to-Space Electromagnetic Data
  • A Neural Network-Based Method for Extracting Slow Diffusion and Multiple Parameters from Ground-to-Space Electromagnetic Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] combine figure 1 As shown, a neural network-based multi-parameter extraction method for slow diffusion of ground-to-air electromagnetic data, including:

[0027] 1) According to the complex characteristics of the actual underground medium and the electromagnetic slow diffusion phenomenon, the slow diffusion parameters are introduced, and the slow diffusion fractional order model is established;

[0028] Define the conductivity expression of slow diffusion fractional order model as σ(ω)=σ 0 +mσ 0 (iω) -β , where ω is the angular frequency, σ 0 is the DC conductivity, m is the weight coefficient, and β is the spatially uniform roughness parameter.

[0029] 2) Construct the electromagnetic field fractional diffusion equation and the fractional Helmholtz equation, and derive the electromagnetic response formula of the conductive source. Based on the fractional finite difference algorithm, realize the three-dimensional numerical simulation of the electrical source-air el...

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 relates to a method for extracting slow diffusion and multi-parameters of ground-air electromagnetic data based on a neural network. The slow diffusion fractional model is established according to the electromagnetic slow diffusion phenomenon; the fractional conductivity expression is substituted into the Maxwell equation to construct an electromagnetic field fractional diffusion equation, Derive the ground-air electromagnetic response formula of the conductive source; based on the acquired geological data of the survey area, build a slow-diffusion fractional model with different slow-diffusion parameters and electrical conductivity, and calculate the ground-air electromagnetic response to form a sample data set; optimize the selection of neural network The network structure parameters and training functions are used to establish a neural network; after preprocessing the measured ground-air electromagnetic data, the neural network is used to extract the multi-parameter information of the underground medium; finally, the multi-parameter results are imaged. The purpose of the invention is to construct a slow diffusion fractional order model to realize high-precision multi-parameter extraction of ground-to-air electromagnetic slow diffusion data. Compared with the traditional conductivity imaging method, the multi-parameter imaging results are closer to the actual underground medium.

Description

technical field [0001] The invention relates to a method for extracting parameters in the field of geophysical exploration, and is especially suitable for an electromagnetic exploration method that conforms to the complex characteristics of actual underground media and the phenomenon of electromagnetic slow diffusion. Background technique [0002] In the field of geophysical exploration, the actual underground medium is affected by differential compaction and metamorphism during its deposition or diagenesis, which makes the formation have characteristics such as nonlinear and porous media. With the fine detection of instruments, the phenomenon of electromagnetic slow diffusion was gradually observed. In view of the slow diffusion phenomenon and the actual complex geological structure, the subsurface medium model is redefined for refined detection, so it is particularly important to obtain multi-parameter information such as rock conductivity and slow diffusion parameters 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 Patents(China)
IPC IPC(8): G01V3/38G06N3/04
CPCG01V3/38G06N3/04
Inventor 吴琼嵇艳鞠邱仕林林君黎东升关珊珊栾卉王远
Owner JILIN UNIV