Fault identification method based on Unet + + convolutional neural network

A convolutional neural network and fault identification technology, applied in the field of seismic interpretation, achieves high resolution, good noise resistance, and improved identification accuracy

Inactive Publication Date: 2019-11-29
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF1 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there are two problems in fault identification. First, how to identify faults more quickly, accurately, efficiently and intelligently when interpreting complex geological structures; second, how to improve the noise resistance and continuity of fault identification. and resolution

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
  • Fault identification method based on Unet + + convolutional neural network
  • Fault identification method based on Unet + + convolutional neural network
  • Fault identification method based on Unet + + convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] For the convenience of those skilled in the art to understand the technical contents of the present invention, the following technical terms are now explained:

[0034] 1. Convolutional neural network

[0035] CNN can be roughly divided into input layer, hidden layer (including convolution layer, pooling layer and fully connected layer) and output layer. The convolution kernel that can extract different features is the main component of the convolution layer. Each convolution kernel has a fixed-size receptive field. In the receptive field, the volume between the convolution kernel and the input data (the previous layer) is calculated. It can learn the local features of the image. A pooling layer (Pooling Layer) is added between the convolutional layers to downsample, that is, to reduce the size of the features by a certain ratio and perform feature selection and information filtering on the output feature map to reduce the number of model parameters. At the end of 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 fault identification method based on a Unet + + convolutional neural network, and is applied to the field of seismic interpretation. Aiming at the problems of low identification efficiency, poor precision, poor noise immunity and the like in fault identification at present, the method comprises the following steps: constructing a seismic amplitude image and a marked faultlabel as a training set of a network; training a Unet + + convolutional neural network according to the constructed training set, and performing fault identification on actual seismic data by using the trained Unet + + convolutional neural network. The method can achieve the quick and precise fault recognition, is high in recognition result resolution, and is good in noise immunity.

Description

technical field [0001] The invention belongs to the field of seismic interpretation, in particular to a geological fault interpretation technology. Background technique [0002] Accurate identification and description of faults is the key to oil and gas development and exploration. However, the research on fault identification is very difficult, because the origin of faults is affected by various geological conditions, their generation is uncertain, and their distribution is uneven. Before oil and gas development, researchers should construct geological fault models by interpreting seismic data, judge oil and gas reserves based on the constructed geological fault models and other data, and formulate corresponding development plans. The quality of fault interpretation is directly related to subsequent mining planning and production, so fault interpretation is a key research content in oil and gas exploration and production. [0003] Convolutional neural network (CNN) is one...

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): G06K9/62G06N3/04G06N3/08G06T7/11
CPCG06T7/11G06N3/084G06T2207/20132G06N3/045G06F18/214
Inventor 姚兴苗蔡宇飞胡光岷
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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