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

Magnetotelluric two-dimensional inversion method for optimizing neural network based on genetic algorithm

A magnetotelluric and genetic algorithm technology, applied in the field of geophysical exploration, can solve the problems of insufficient inversion speed and accuracy, poor adaptability, etc. Effect

Inactive Publication Date: 2020-05-12
贵州大方煤业有限公司
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a two-dimensional magnetotelluric inversion method based on a genetic algorithm optimized neural network to overcome the problems of insufficient inversion speed and precision and poor adaptability in the prior art

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
  • Magnetotelluric two-dimensional inversion method for optimizing neural network based on genetic algorithm
  • Magnetotelluric two-dimensional inversion method for optimizing neural network based on genetic algorithm
  • Magnetotelluric two-dimensional inversion method for optimizing neural network based on genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0023] Embodiment: a kind of magnetotelluric two-dimensional inversion method based on genetic algorithm optimization neural network comprises the following steps:

[0024] Step A. According to the magnetotelluric two-dimensional forward modeling model and the apparent resistivity data, initialize the neural network structure, and optimize the initial weight and threshold of the network through the genetic algorithm:

[0025] The initial setting of the network structure refers to: the number M of the collected apparent resistivity is used as the number of nodes in the input layer, and the number S of grids in the inversion area of ​​the two-dimensional model is used as the number of output nodes. Double hidden layers are used, and the nodes are respectively h 1 、H 2 ; Specifically, in the process of magnetotelluric inversion, this method is aimed at two-dimensional underground media, and the forward modeling process adopts finite element algorithm, the grid size is 30×31, the...

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 magnetotelluric two-dimensional inversion method for optimizing a neural network based on a genetic algorithm. The method comprises the following steps of: firstly, establishing a BP neural network basic framework for a magnetotelluric two-dimensional geoelectric model for learning training, wherein the network input is the apparent resistivity parameter of a known geoelectric model, and the output is the geoelectric model parameter; optimizing a neural network learning and training process by utilizing a genetic algorithm, and calculating optimal solutions of networkconnection weights and thresholds of various geoelectric models; and finally, performing inversion test on the unknown model by using the optimal connection weight and the threshold, the network inputbeing the apparent resistivity parameter of the unknown geoelectric model, and the output being the parameter of the geoelectric model. The magnetotelluric detection nonlinear inversion method can effectively improve magnetotelluric detection nonlinear inversion precision and speed, and is high in adaptability.

Description

Technical field: [0001] The invention belongs to the field of geophysical exploration, and in particular relates to a two-dimensional magnetotelluric inversion method based on genetic algorithm optimization neural network. Background technique: [0002] The magnetotelluric sounding method has been widely used in the fields of oil and gas exploration, mineral survey, exploration and geological engineering, and the inversion of its data has also been greatly developed. The classic inversion method has a great dependence on the initial model and needs to calculate the sensitivity matrix. The emergence of some new global optimization inversion methods provides a new approach for magnetotelluric inversion, and their common feature is that they are less dependent on the initial model and do not need to calculate the sensitivity matrix. [0003] Because various inversion methods have their own characteristics in principle, one method is not necessarily better than another method, ...

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): G06F30/20G06N3/04G06N3/08G06N3/12
CPCG06N3/084G06N3/086G06N3/126G06N3/044G06N3/045
Inventor 莫连红周炜光张光明陶斌朱嘉伟张超李公朝田玉祖王才彬庄万军
Owner 贵州大方煤业有限公司
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