Gravity field density inversion method based on quasi-radial basis function neural network

A neural network and density inversion technology, applied in the measurement of gravitational fields, measurement devices, instruments, etc., can solve the problems of inability to improve the vertical resolution of gravity inversion, ill-posed gravity inversion, etc., and achieve improved vertical resolution. and reliability, interpretability clear and well-defined effects

Active Publication Date: 2018-09-04
CHINA PETROLEUM & CHEM CORP +1
View PDF1 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The object of the present invention proposes a gravity field density inversion method based on a pseudo-radial basis function neural network, which can solve the problems that the gravity inversion of the existing inversion method is ill-posed and cannot improve the vertical resolution of the gravity inversion

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
  • Gravity field density inversion method based on quasi-radial basis function neural network
  • Gravity field density inversion method based on quasi-radial basis function neural network
  • Gravity field density inversion method based on quasi-radial basis function neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] The gravity field density inversion method based on the pseudo-radial basis function neural network adopts the following steps:

[0050] 1. Establish a gravity observation system

[0051] The coordinates of the two-dimensional observation system are (X, Z), X is the horizontal coordinate, Z is the elevation of the observation point; the coordinates of the three-dimensional observation system are (X, Y, Z), X and Y are the horizontal coordinates perpendicular to each other, Z is the elevation of the observation point; the observation system can be a plane observation system, that is, Z is a constant, or a curved surface observation system, and the observation points can be distributed at equal intervals or randomly distributed at unequal intervals;

[0052] 2. Establish a grid model

[0053] Divide the inversion target area into grids, the 2D inversion grids are rectangular, the 3D inversion grids are upright hexahedrons, and the grid data format is divided into (X 1 ,...

Embodiment 2

[0077] The present invention will be further described below in conjunction with specific examples.

[0078] The three-dimensional combined model is used to test the inversion effect of the method. The subdivision range of the underground half space is x direction: 0-9240 meters, y direction: 0-9240 meters, z direction: 0: 3040 meters, and each direction is divided into 10 grid, set two geological bodies, the density of geological body 1 is 1.0g / cm 3 , the distribution grid is x direction: 4~6, y direction: 3~5, z direction 2~4, the density of geological body 2 is 3.0g / cm 3 , the distribution grid is x direction: 4~6, y direction: 4~6, z direction 5~7, observation system range x direction: 0~10000 meters, y direction 0~1000 meters, observation point height is 0 meters, The distance between observation points in each direction is 500 meters, and there are 400 observation points in total. The model and simulated observation data are as follows: image 3 and Figure 4 shown. ...

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 gravity field density inversion method based on a quasi-radial basis function neural network. The method comprises a step of establishing a gravity observation system, a stepof establishing a gridded model, a step of establishing a gravity forward kernel function matrix, a step of establishing a radial basis function neural network, a step of training the neural network,and a step of outputting an inversion result. According to the method, a model space is compressed by using a radial basis function, and the dimensionality reduction of inversion parameters is achieved under the premise of ensuring complex model representation ability. A pseudo-neural network structure is proposed, the training of a sample tag is not needed, the difficulty of establishing a training data set is avoided, and a gravity field density inversion algorithm is achieved based on the pseudo-neural network structure. The vertical resolution and reliability of an inversion result are improved, the method has strong anti-noise ability, and the application field of a gravity inversion method is extended.

Description

technical field [0001] The invention belongs to the field of geophysical inversion, and specifically refers to a gravity inversion method, in particular to a method for inverting an underground target density model based on a quasi-radial basis function neural network using gravity field data. Background technique [0002] Gravity prospecting is widely used in regional geological surveys, basin framework studies, and deep and large fault reconnaissance because of its fast data collection and low price. It restricts its application in high-precision exploration fields, such as oil and gas exploration. The root cause of the above problems lies in the ill-posed nature of the inverse gravity problem. First, the density of gravity data collection is low and the amount of data is small, while high-resolution inversion requires high-density subdivision of the underground half-space, making the number of unknown parameters in the inversion far greater than the number of data, resul...

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): G01V7/06
CPCG01V7/06
Inventor 相鹏刘佳陈学国王金铎于会臻谭绍泉王有涛张建华杨国杰王月蕾
Owner CHINA PETROLEUM & CHEM CORP
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap