Unlock instant, AI-driven research and patent intelligence for your innovation.

Microseismic P-wave identification method and system based on depth convolution neural network

A convolutional neural network and neural network technology, applied in the field of microseismic monitoring, can solve the problems of low signal-to-noise ratio of microseismic signals, affect the accuracy of automatic picking, and take a long time, so as to improve efficiency and accuracy, and promote application and promotion Effect

Inactive Publication Date: 2018-12-21
YANGTZE UNIVERSITY
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the low signal-to-noise ratio of microseismic signals, these single methods often have poor recognition results, and even misjudgments and misjudgments, which undoubtedly seriously affect the accuracy of automatic picking.
Although the accuracy of artificially identifying the first arrival of microseismic is high, it takes a long time and cannot meet the needs of real-time processing of microseismic

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
  • Microseismic P-wave identification method and system based on depth convolution neural network
  • Microseismic P-wave identification method and system based on depth convolution neural network
  • Microseismic P-wave identification method and system based on depth convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in further detail below in conjunction with accompanying drawing, the present invention provides a kind of microseismic P wave recognition method based on deep convolutional neural network, described method comprises the following steps, as figure 1 Shown:

[0035] S1. Use microseismic forward modeling signals with different main frequencies and different signal-to-noise ratios and actual microseismic records to make data sets for training convolutional neural networks, and divide the data sets into two categories in the form of effective P waves and noise;

[0036] S2. Using the convolutional neural network to train the data set;

[0037] S3, using the Relu activation function to increase the response of the signal;

[0038] S4. The signal is identified by the label type corresponding to the One-hot code converted by the Softmax function, and the signal is divided into a P wave and a noise signal.

[0039] Among them, such as ...

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 micro-seismic P-wave identification method and system based on a depth convolution neural network, which completes the training of the depth convolution neural network by establishing a training set comprising an effective signal and noise of the micro-seismic, and then identifies the micro-seismic P-wave through the trained network, and the method improves the efficiencyand the precision of the effective signal identification.

Description

technical field [0001] The invention relates to the technical field of microseismic monitoring, in particular to a microseismic P-wave identification method and system based on a deep convolutional neural network. Background technique [0002] Microseismic monitoring technology is a geophysical technology that monitors subsurface conditions by observing and analyzing tiny seismic events generated by fracturing, which is of great significance to stable and high production in oilfield development. The effective signal energy of microseismic data is weak, the signal-to-noise ratio is low, and even completely submerged in the noise. Although there are many conventional seismic data processing methods, if they are directly applied to microseismic data, they often cannot obtain satisfactory results, which will directly affect the quality and accuracy of microseismic monitoring. Therefore, finding a suitable method to identify weak effective signals in microseismic data is the key...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/00G06F18/214
Inventor 盛冠群谢凯唐新功郑祖兵文方青汤婧裔飞
Owner YANGTZE UNIVERSITY