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

Hard rock tension-shear fracture identification method and device based on voiceprint depth features

A technology of deep features and recognition methods, applied in neural learning methods, character and pattern recognition, speech analysis, etc., can solve the problems of small data sets, over-fitting, and learning, to improve adaptability and efficiency, and improve Efficiency, reduced complexity effects

Active Publication Date: 2022-05-10
GUANGXI UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the data set is small, it is difficult for the deep learning model to learn enough information from it, resulting in model training failure or overfitting

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
  • Hard rock tension-shear fracture identification method and device based on voiceprint depth features
  • Hard rock tension-shear fracture identification method and device based on voiceprint depth features
  • Hard rock tension-shear fracture identification method and device based on voiceprint depth features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0113] In this implementation case, the monitored karst mountainous area has the average lithology of tension-compression-shear falling hard rock, the two sides of the hard rock are the first and second main control structural planes, and the size of the hard rock is 100,000 m 3 , with a height of 30m, such as figure 2 shown. The conventional physical parameters of hard rock to be monitored are shown in Table 1.

[0114] Table 1 Hard rock mechanical parameters

[0115]

[0116] In this patent, a hard rock tensile-shear fracture identification method based on sound features, such as figure 1 Shown, its specific embodiment comprises the following steps:

[0117] In step S1, the rock sample on the hard rock is selected for processing, and a tensile fracture test and a shear fracture test are performed to obtain a typical tensile fracture Wigner-Ville voiceprint and a shear fracture Wigner-Ville voiceprint,

[0118] Step S1-1: Select representative rock samples on hard roc...

Embodiment example 2

[0139] In order to further implement the method in the present invention, the implementation of the second aspect of this patent application proposes a method and device for automatic identification of hard rock tension-shear fractures based on acoustic features, such as Figure 4 , 5 , as shown in 6, where Figure 4 It is a device block diagram of the implementation method of the present invention, Figure 5 It is a device unit diagram of the implementation method of the present invention, Figure 6 The site layout drawing for the engineering example of the device, including:

[0140] The tension-shear sampling module Z1 is used to mine the rock samples for the tension fracture test, and to carry out the tension test, to obtain the sound signal of the tension fracture, and to mine the rock samples for the shear test, and to carry out the shear test, and to obtain the shear signal. Acoustic signal when cutting. It includes a tension-shear sampling module Z1 including: a te...

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 method and device for identifying tensile-shear fractures of hard rock based on voiceprint depth characteristics, which mainly solves the problem of difficulty in identifying tensile-shear fractures of hard rocks on site. Including Step S1: Obtain the sound signals of tension fracture and shear fracture of hard rock, and draw the corresponding Wigner-Ville soundprint; Step S2: Use the pre-trained deep neural network to extract two types of soundprints of tension and shear fracture The depth feature of the graph; step S3: using the depth features of the two types of cracking signal voiceprints of tension and shearing as training samples to train IVM; step S4: monitoring the cracking sound signal of hard rock, and obtaining the voiceprint of the corresponding cracking sound; Step S5: Use the same pre-trained network to extract the voiceprint depth features to be predicted, and determine the type of hard rock fracture according to the IVM classification results; Step S6: Add the predicted samples with good IVM classification results to the training set as training samples , to predict the sound obtained after monitoring.

Description

technical field [0001] The invention belongs to the technical field of disaster prevention and control in geotechnical engineering, and relates to a method and device for identifying tensile-shear fractures of hard rock based on voiceprint depth characteristics. Background technique [0002] More than two-thirds of my country's land area is mountainous, which is extremely vulnerable to natural disasters caused by dangerous rocks in mountainous areas. Due to the suddenness and rapidity of dangerous rock disasters, there is still a huge room for improvement in the timely warning of dangerous rock disasters. [0003] Existing studies have shown that the macro-failure of hard rocks develops gradually from tiny brittle fractures. Deepening the research on brittle fractures is of great significance for revealing the macro-failure mechanism of hard rocks. Therefore, how to monitor the fracture behavior of hard rocks is an important research hotspots. [0004] The brittle fracture...

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 Patents(China)
IPC IPC(8): G06K9/62G06V10/764G06V10/40G06V10/82G06N3/04G06N3/08G10L17/02G10L17/04G10L17/18G10L17/26
CPCG06N3/08G10L17/02G10L17/04G10L17/18G10L17/26G06N3/045G06F18/2411G06F18/256
Inventor 苏国韶黄杰蒋剑青许华杰张研罗丹旎粟明杰蓝兰
Owner GUANGXI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com