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

TBM rock breaking seismic source seismic wave field feature recovery method and system based on deep learning

A deep learning and seismic wave field technology, applied in the field of geophysical exploration, can solve the problems of incompatibility of seismic data time and deep neural network parameter weights, shared attributes, large differences in the meaning of input data features, etc., to improve feature extraction capabilities, The effect of improving accuracy

Active Publication Date: 2021-01-15
SHANDONG UNIV +1
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The volume of data required for TRON feature recovery training is significantly larger than that of conventional deep learning problems, and there are also large differences in the meaning of features represented by input data.
At the same time, there is an incompatibility between the time and space variation characteristics of seismic data and the weight sharing properties of deep neural network parameters
[0007] (2) The transition problem of recovering wave field characteristics from simulated data to data
The ultimate goal of the wave field feature restoration method is the actual landing and application in the TBM tunnel excavation site, but there are a lot of random environmental noise and irregular mechanical noise in the actual engineering application on site, and the complexity of the actual data is much higher than that of the simulated data. It is not enough to retrain the network parameters of the wave field recovery from the numerical simulation data

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
  • TBM rock breaking seismic source seismic wave field feature recovery method and system based on deep learning
  • TBM rock breaking seismic source seismic wave field feature recovery method and system based on deep learning
  • TBM rock breaking seismic source seismic wave field feature recovery method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Such as figure 1 As shown, this embodiment provides a method for recovering the seismic wave field characteristics of the TBM rock-breaking seismic source based on deep learning, including:

[0045]Step 1: Obtain the original signal and pilot signal of the rock-breaking source, and obtain the numerical simulation data of the TBM rock-breaking source.

[0046] This example mainly simulates the underground geological situation where there are single-layer interface, double-layer interface, karst cave and / or double-layer interface and karst cave in front of the tunnel face, as shown in Figure 5(a), Figure 5(b), and Figure 5( c) as shown.

[0047] The size of the model in this embodiment is 290m*90m, the grid spacing Δx=Δy=1m, and 20 grids of PML absorption boundaries are set around the model. The layout of seismic sources and geophones is shown in Figure 6(a) and (b). In the rock-breaking seismic source observation system and the pulse seismic source observation system, ...

Embodiment 2

[0079] This embodiment provides a +deep learning-based TBM rock-breaking seismic source seismic wave field feature recovery system, including:

[0080] (1) A signal acquisition module, which is used to acquire the original signal and pilot signal of the rock-breaking seismic source, and obtain the numerical simulation data of the TBM rock-breaking seismic source.

[0081] This example mainly simulates the underground geological situation where there are single-layer interface, double-layer interface, karst cave and / or double-layer interface and karst cave in front of the tunnel face, as shown in Figure 5(a), Figure 5(b), and Figure 5( c) as shown.

[0082] The size of the model in this embodiment is 290m*90m, the grid spacing Δx=Δy=1m, and 20 grids of PML absorption boundaries are set around the model. The layout of seismic sources and geophones is shown in Fig. 6(a) and Fig. 6(b). In the rock-breaking seismic source observation system and the pulse seismic source observation...

Embodiment 3

[0114] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in the method for recovering the seismic wave field characteristics of the TBM rock-breaking source based on deep learning as described above are implemented.

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 belongs to the field of geophysical exploration, and provides a TBM rock breaking seismic source seismic wave field feature recovery method and system based on deep learning. The deep learning-based TBM rock-breaking seismic source seismic wave field feature recovery method comprises the steps of obtaining a rock-breaking seismic source original signal and a pilot signal, and obtaining TBM rock-breaking seismic source numerical simulation data; converting the TBM rock breaking seismic source numerical simulation data into a pulse seismic source seismic record subjected to wave field feature recovery through a wave field feature recovery network based on deep learning, wherein the wave field feature recovery network based on deep learning comprises a preprocessing layer and adeep neural network layer; using the pre-processing layer for carrying out convolution on the rock breaking seismic source original signal and the pilot signal channel by channel and carrying out segmentation superposition on convolution output; enabling the output of the preprocessing layer, the time information constraint matrix and the event information constraint matrix to form three-channel data, and then inputting the three-channel data to the deep neural network layer.

Description

technical field [0001] The invention belongs to the field of geophysical exploration, and in particular relates to a method and system for recovering the seismic wave field characteristics of a TBM rock-breaking seismic source based on deep learning. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] The advanced detection method of rock-breaking seismic source is a prediction method that uses the rock-breaking vibration generated by the tunnel boring machine (TBM) as the seismic source to detect the abnormal body ahead. This method can simultaneously detect and quickly obtain data processing results during the TBM excavation process, so it is very suitable for the needs of TBM rapid excavation. Due to the time-continuous and uncontrollable characteristics of the rock-breaking vibration wave field, it is difficult to directly identify the ef...

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): G06F30/27G06F17/16G06F17/18G06N3/04G06N3/08G01V1/28G01V1/30G06F111/10G06F119/10
CPCG06F30/27G06F17/16G06F17/18G06N3/08G01V1/282G01V1/307G06F2111/10G06F2119/10G06N3/045
Inventor 许新骥王清扬蒋鹏高雪池岳景杭周鹏飞马川义杨森林
Owner SHANDONG UNIV
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