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

Acoustic emission signal feature extraction method, acoustic emission signal recognition method and device, acoustic emission signal feature extraction device and storage medium

An acoustic emission signal and feature extraction technology, which is applied to mining equipment, earth cube drilling, mining equipment, etc., can solve the problems of difficult to guarantee recognition accuracy and poor feature effect, achieve good feature effect, timely recognition, and improve recognition accuracy Effect

Pending Publication Date: 2021-08-06
GUANGXI ZHONGJIN LINGNAN MINING CO LTD +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a mine acoustic emission signal feature extraction method, recognition method, device and storage medium to solve the problem that the existing mine acoustic wave feature extraction method has poor feature extraction effect and makes it difficult to guarantee the recognition accuracy

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
  • Acoustic emission signal feature extraction method, acoustic emission signal recognition method and device, acoustic emission signal feature extraction device and storage medium
  • Acoustic emission signal feature extraction method, acoustic emission signal recognition method and device, acoustic emission signal feature extraction device and storage medium
  • Acoustic emission signal feature extraction method, acoustic emission signal recognition method and device, acoustic emission signal feature extraction device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0100] Such as figure 1 As shown, the present embodiment provides a mine acoustic emission signal feature extraction method, including:

[0101] S1: Acquire mine acoustic emission signals.

[0102] S2: Perform CEEMD decomposition (complementary ensemble empirical mode decomposition) on the mine acoustic emission signal to obtain a plurality of corresponding first IMF components. Specifically include:

[0103] Add a pair of opposite positive and negative Gaussian white noise n to the mine AE signal X(t) i (t) and -n i (t), get a new sequence:

[0104] x i + (t)=X(t)+a i no i (t)

[0105] x i - (t)=X(t)-a i no i (t)

[0106] In the formula: a i is the amplitude of the white noise, i=1, 2, 3,..., M, where M is the logarithm of the added white noise, generally 20-60.

[0107] Carry out EMD decomposition to above-mentioned new sequence respectively, illustrate with the obtained first-order IMF component as example, the first-order IMF component obtained respectively...

Embodiment 2

[0153] The present embodiment provides a mine acoustic emission signal identification method, comprising:

[0154] Adopt the mine acoustic emission signal feature extraction method as described in embodiment 1 to extract the feature vector of the mine acoustic emission signal that acquires in real time;

[0155] Input the extracted feature vector into the preset mine acoustic emission signal classification model to obtain the category of the mine acoustic emission signal.

[0156] The feature extraction process can not only effectively eliminate the false component and noise component, but also retain the sensitive features of the signal, and the extracted feature effect is good; the feature vector obtained by using this feature extraction method is applied to the classification and recognition of mine acoustic emission signals, with high accuracy. The calculation cost is low, which can solve the problem that the extracted features are not effective and the recognition accurac...

Embodiment 3

[0186] This embodiment provides a mine acoustic emission signal feature extraction device, including:

[0187] The signal acquisition module is used to acquire mine acoustic emission signals;

[0188] The first decomposition module is used to perform CEEMD decomposition on the mine acoustic emission signal to obtain a plurality of corresponding first IMF components;

[0189] The screening module is used for a plurality of first IMF components, wherein the first IMF component whose correlation coefficient with the mine acoustic emission signal is greater than or equal to the correlation coefficient threshold value is retained, and the first IMF component whose correlation coefficient is less than the correlation coefficient threshold value is removed; simultaneously Wherein the first IMF component whose permutation entropy is less than or equal to the permutation entropy threshold is retained, and the first IMF component whose permutation entropy is greater than the permutation...

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 an acoustic emission signal feature extraction method, an acoustic emission signal recognition method, an acoustic emission signal feature extraction device and a storage medium. The feature extraction method comprises the following steps of acquiring a mine acoustic emission signal; performing CEEMD decomposition on the mine acoustic emission signal to obtain a plurality of corresponding first IMF components; for the plurality of first IMF components, removing pseudo components and noise components in the plurality of first IMF components based on correlation coefficients and permutation entropies; reconstructing the remaining first IMF component to obtain a reconstructed signal; performing EMD decomposition on the reconstructed signal to obtain a plurality of second IMF components; and selecting preset t second IMF components from the plurality of second IMF components and calculating permutation entropies of the second IMF components under a preset scale to form a feature vector. In the feature extraction process, the false components and the noise components can be effectively eliminated, and sensitive features can be reserved; and the method improves the classification recognition precision of the subsequent mine acoustic emission signals, can correctly and timely recognize the surrounding rock acoustic emission signals, and provides a basis for the accurate early warning of an acoustic emission monitoring system.

Description

technical field [0001] The invention relates to the field of ground pressure monitoring in mining engineering, in particular to a mine acoustic emission signal feature extraction method, identification method, device and storage medium. Background technique [0002] With the development and utilization of underground mineral resources, underground mines are faced with a complex ground pressure environment. Problems such as roof collapse, goaf roof collapse, and rockburst are prominent, causing great safety hazards to underground operators and mechanical equipment. Acoustic emission monitoring, as one of the main ground pressure monitoring methods, has been widely used in underground mines and other fields at home and abroad. Acoustic emission signal source identification is an important part of ground pressure monitoring and early warning. Correct and timely identification of acoustic emission sources is an important basis for ground pressure monitoring safety and early warn...

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): E21F17/18E21F17/00
CPCE21F17/18E21F17/00
Inventor 李小元刘晖谢学斌刘涛张世东苏振华支伟曹胜祥潘立景陆维唐运坚
Owner GUANGXI ZHONGJIN LINGNAN MINING CO LTD
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