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

A method and system for suppressing magnetotelluric signal noise based on bp neural network

A BP neural network and magnetotelluric technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problems of low processing and efficiency, and achieve loss reduction, high signal-to-noise separation reliability and data processing efficiency Effect

Active Publication Date: 2022-06-28
HUNAN NORMAL UNIVERSITY
View PDF3 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 provide a kind of noise suppression of magnetotelluric signal based on BP neural network for the technical problems of overprocessing and low efficiency when using traditional time-frequency domain denoising method to suppress large-scale interference in magnetotelluric data method and system

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 method and system for suppressing magnetotelluric signal noise based on bp neural network
  • A method and system for suppressing magnetotelluric signal noise based on bp neural network
  • A method and system for suppressing magnetotelluric signal noise based on bp neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0091] Aiming at how to improve the denoising reliability and efficiency of the magnetotelluric signal, the present invention utilizes the data classification and mapping functions of the BP neural network, and obtains the BP signal-to-noise identification model and the denoising model by training a large amount of sample data similar to the measured magnetotelluric signal. On the one hand, the signal-to-noise identification model reduces the loss of useful information and improves the reliability of the denoising of the measured magnetotelluric signals; and after the BP model is obtained, the identification and denoising of the measured magnetotelluric data consumes less time, and the efficiency is extremely high. big boost. The present invention will be further described below with reference to the embodiments.

[0092] like figure 1 As shown, the present invention provides a method for suppressing noise of magnetotelluric signals based on BP neural network, comprising 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 discloses a method and system for suppressing magnetotelluric signal noise based on BP neural network. The method includes: respectively constructing noise profile samples, pure signal samples, and noisy data samples, and then inputting the noisy data samples and the pure signal samples To the first BP neural network training to obtain BP signal-to-noise identification model. And input the noisy data sample and the noise profile sample into the second BP neural network, and train to obtain the BP denoising model. Finally, evenly segment the measured magnetotelluric data into the BP signal-to-noise identification model, retain the data segment identified as no interference, and input the interference data segment into the BP denoising model to output the noise profile, and subtract the corresponding Noise profile obtains the data after denoising the noise data. Finally, the retained non-interference data and the denoised data are spliced ​​and reconstructed to obtain the denoised magnetotelluric signal.

Description

technical field [0001] The invention belongs to the technical field of magnetotelluric signal processing, and in particular relates to a method and system for suppressing noise of magnetotelluric signals based on a BP neural network. Background technique [0002] In the 1950s, Tikhon and Cagiard proposed the magnetotelluric bathymetry (Magnetotelluric, MT), which is a geophysical exploration method that uses the natural alternating electromagnetic field to study the electrical structure of the earth. Due to the advantages of low cost, simple construction and high resolution, this method has been widely used in mineral exploration and resource exploration. However, natural magnetotelluric signals are weak and wide in frequency, and are easily affected by various noises, which makes it impossible to make correct processing and interpretation. Especially in resource-rich mining areas, the collected MT data is often accompanied by very complex and high-energy noise, and useful ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F2218/10G06F2218/04
Inventor 李晋刘业成马翻红刘姗姗汪嘉琳彭意群张贤苏贵
Owner HUNAN NORMAL UNIVERSITY
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