Bi-LSTM-based magnetotelluric signal denoising method and system

A magnetotelluric and signal technology, applied in the field of magnetotelluric signal de-noising based on Bi-LSTM, can solve the problem of noise overprocessing, achieve high-precision noise prediction, realize self-adaptation, and improve the effect of signal-to-noise separation efficiency

Active Publication Date: 2021-11-23
HUNAN NORMAL UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, how to accurately predict the complex noise profile in the measured data, effectively complete the separation and removal of noise, and solve the problem of noise overprocessing in the prior art is an urgent need for consideration in the present invention.

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
  • Bi-LSTM-based magnetotelluric signal denoising method and system
  • Bi-LSTM-based magnetotelluric signal denoising method and system
  • Bi-LSTM-based magnetotelluric signal denoising method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] The method for denoising magnetotelluric signals based on Bi-LSTM provided in this embodiment is essentially a method for denoising magnetotelluric signals based on NPSO-Bi-LSTM. Such asfigure 1 As shown, the shown method includes the following steps:

[0089] Step 1: Take the amplitude of the time series of the magnetotelluric signal as the characteristic parameter, and construct a large number of noise contour signals that conform to the characteristics of the actual magnetotelluric weak signal and strong interference, and add the two to obtain the noisy signal;

[0090] In order to better characterize the time-domain waveform characteristics of the magnetotelluric measured data, the noise contour signals containing typical square waves, triangle waves and pulses were respectively constructed. The length of each analog signal was 80000, and the amplitude was 10 -5 to 10 5 between;

[0091] Construct the pure interference signal as the clean signal. The length of th...

Embodiment 2

[0118] A magnetotelluric signal denoising system based on the NPSO-Bi-LSTM magnetotelluric signal denoising method provided based on the above-mentioned embodiment 1, including: a sample library building module, an NPSO parameter optimization module, a Bi-LSTM model building module, and a prediction Modules, refactoring modules.

[0119] Among them, the sample library construction module is used to construct the noise sample library and the pure signal sample library of the magnetotelluric signal.

[0120] NPSO parameter optimization module: It is used to find the optimal data segment division length and network parameters within a reasonable range, and select the optimal parameter combination to improve the prediction accuracy of the Bi-LSTM network.

[0121] Bi-LSTM model building block: used to define the input and output of the bidirectional long-term short-term memory neural network, and use the magnetotelluric noise-containing signal and its noise contour signal to train...

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 Bi-LSTM-based magnetotelluric signal denoising method and system, the method comprises the steps: constructing a large number of noise contours conforming to magnetotelluric weak signals and containing strong interference characteristics, and adding the noise contours to obtain noisy signals; dividing the noisy signals into a corresponding training set and a test set according to a proportion, defining input and output corresponding to the network, preferably selecting related parameters of an optimal bidirectional long-short-term memory neural network by using NPSO, and then sending the training set into the neural network for training to obtain a prediction model; predicting the actually measured magnetotelluric data by using the prediction model to obtain the noise contour; and finally, subtracting the predicted noise contour from the actually measured magnetotelluric data to obtain useful magnetotelluric signals. According to the method, the noise contours can be effectively and accurately predicted, so that the noise in the noisy signals is eliminated, and more useful magnetotelluric signals are reserved.

Description

technical field [0001] The invention belongs to the technical field of magnetotelluric signal processing, in particular to a method and system for denoising magnetotelluric signals based on Bi-LSTM. Background technique [0002] With the rapid development of social economy, my country's dependence on foreign energy and metal mineral resources is increasing year by year. The shortage of mineral resources and insufficient proven reserves of energy reserves have become major bottlenecks restricting the development of the national economy. Magnetotelluric (MT) is a geophysical exploration method proposed by Soviet scholar Tikhon and French scholar Cagiard in the early 1950s to study the electrical structure of the earth by using natural alternating electromagnetic fields. MT plays an important role in geophysical exploration because of its large exploration depth, low exploration cost, convenient construction, and mature data processing and interpretation technology. Many geop...

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
IPC IPC(8): G01V3/38
CPCG01V3/38
Inventor 李晋汪嘉琳刘业成苏贵刘姗姗马翻红彭意群张贤
Owner HUNAN NORMAL UNIVERSITY
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