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

Road noise suppression method and system based on artificial intelligence deep neural network

A technology of deep neural network and noise suppression, applied in biological neural network models, neural architectures, instruments, etc., can solve the problem of less research on non-random noise deep learning methods, and achieve good suppression and denoising effects

Active Publication Date: 2019-07-12
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the field of image processing, denoising technology based on deep learning has been widely studied; because the discriminant method can directly learn complex models of different noises from long-term accumulated seismic data denoising samples, research in the field of seismic data denoising has also begun to be extensive. However, most of the current research is still focused on the suppression method of additive random noise. For example, Si et al (2018) proposed a random noise suppression method for seismic data based on convolutional neural network technology. less research

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
  • Road noise suppression method and system based on artificial intelligence deep neural network
  • Road noise suppression method and system based on artificial intelligence deep neural network
  • Road noise suppression method and system based on artificial intelligence deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] like figure 1 As shown, the road noise suppression method based on artificial intelligence deep neural network provided in this embodiment includes:

[0077] Step 101: Obtain sample data; the sample data includes noisy seismic data and noise distribution data; the noisy seismic data is seismic data containing road noise; the noise distribution data is the noisy seismic data minus Data obtained from noisy seismic data.

[0078] Step 102: Perform harmonic noise removal, data block and regularization processing on the sample data.

[0079] Step 103: Use artificial intelligence deep learning convolutional neural network to learn the processed sample data to obtain a noise distribution model; the noise distribution model is a relationship model between the processed noisy seismic data and the processed noise distribution data.

[0080] Step 104: Obtain the current seismic data with noise, and perform harmonic noise removal, data block and regularization processing on the c...

Embodiment 2

[0099] In order to achieve targeted, direct and better suppression of road noise in seismic acquisition data, this embodiment proposes a road noise suppression method based on artificial intelligence technology, including the step of learning a road noise model using convolutional neural network technology. The complete method implementation is divided into two steps:

[0100] First, the road noise model is learned from the sample data of the historical road noise in the seismic exploration work area (such as figure 2 ), the sample data includes noisy seismic data and noise distribution data, or noisy seismic data and denoised seismic data, and the noise distribution data is obtained by subtracting the denoised seismic data from the noisy seismic data.

[0101] Then, the highway noise model obtained through sample learning can be used to process the noisy seismic data that needs to be processed to obtain the final denoised seismic data (such as image 3 ), which is also used...

Embodiment 3

[0152] like Figure 11 As shown, a road noise suppression system based on artificial intelligence deep neural network, including:

[0153] The sample data acquisition module 100 is used to acquire sample data; the sample data includes noisy seismic data and noise distribution data; the noisy seismic data is seismic data containing road noise; the noise distribution data is the noise-containing seismic data Data obtained by subtracting denoised seismic data from seismic data;

[0154] A sample data processing module 200, configured to perform harmonic noise removal, data block and regularization processing on the sample data;

[0155] The noise distribution model acquisition module 300 is used to learn the processed sample data by using artificial intelligence deep learning convolutional neural network to obtain a noise distribution model; the noise distribution model is the processed noisy seismic data and the processed noise Relational models for distributed data;

[0156]...

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 highway noise suppression method and system based on an artificial intelligence deep neural network, and relates to the technical field of petroleum geophysical exploration seismic data processing. The method mainly comprises the following steps: processing noisy seismic data and noise distribution data in sample data; learning the processed sample data by adopting an artificial intelligence deep learning convolutional neural network to obtain a noise distribution model; inputting the processed current noise-containing seismic data into a noise distribution model to obtain a noise distribution data estimation value; calculating a noise mask and a suppression scale according to the noise distribution data estimation value; and suppressing highway noise in the current noisy seismic data according to the noise mask and the suppression scale. According to the method, the artificial intelligence deep learning convolutional neural network is adopted, the distribution model of the highway noise is directly learned from the sample data, and the purpose of directly and better suppressing the highway noise in the seismic data is achieved.

Description

technical field [0001] The invention relates to the technical field of petroleum geophysical exploration seismic data processing, in particular to a road noise suppression method and system based on an artificial intelligence deep neural network. Background technique [0002] Seismic exploration mainly includes three steps: seismic data acquisition, seismic data processing and seismic interpretation. Seismic data processing is to decompile the collected seismic data, static correction, pre-stack noise suppression, deconvolution, velocity analysis, residual static correction, Conventional processing such as post-stack migration or pre-stack migration imaging processing finally provides post-stack or pre-stack result data that can be used in the seismic interpretation step. Pre-stack noise suppression is the suppression of various noises in seismic data, which is a basic and critical step in the seismic data processing process. A better noise suppression method can provide sei...

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): G06F17/50G06N3/04G01V1/36
CPCG01V1/36G06F30/20G06N3/045Y02T90/00
Inventor 朱兆林曹丹平
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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