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

A Distributed Optical Fiber Sensor Vibration Signal Classification Method and Recognition Classification System

A distributed optical fiber and vibration signal technology, applied in the field of signal detection, can solve the problems of low classification accuracy of optical fiber sensing intrusion signal identification and classification, and achieve the effect of solving low classification accuracy, improved identification accuracy, and strong universality

Active Publication Date: 2022-07-15
HOHAI UNIV CHANGZHOU
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems, the present invention proposes a method and system for identifying optical fiber sensing vibration signals, which realizes feature extraction of optical fiber sensing signals, accurate identification and classification, and solves the technology of low accuracy in identification and classification of optical fiber sensing intrusion signals question

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
  • A Distributed Optical Fiber Sensor Vibration Signal Classification Method and Recognition Classification System
  • A Distributed Optical Fiber Sensor Vibration Signal Classification Method and Recognition Classification System
  • A Distributed Optical Fiber Sensor Vibration Signal Classification Method and Recognition Classification System

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The technical solutions of the present invention will be further elaborated below according to the accompanying drawings and in conjunction with the embodiments.

[0038] figure 1 It is a schematic flowchart of a method for identifying vibration signals of optical fiber sensors according to an embodiment of the present invention, and a method for classifying vibration signals of distributed optical fiber sensors, including the following steps:

[0039] S1: The optical fiber cable detects the signal generated by the external vibration. The sampling rate and parameter settings of the equipment are adjusted according to the specific position of the optical cable. The collected signals include non-intrusion signals and intrusion signals, as well as the interference of environmental noise.

[0040] S2: Pre-process the collected signal, and determine the appropriate framing window function according to the actual sampling rate and the number of points of the collected discret...

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 vibration signal classification method of a distributed optical fiber sensor and an identification and classification system. The method is as follows: first, an optical fiber sensing system is used to obtain a vibration signal acting on an optical cable; the optical fiber vibration signal is preprocessed; Short-term energy and short-term zero-crossing rate; set dual thresholds for short-term energy and short-term zero-crossing rate, if the threshold is exceeded, the valid data segment is extracted and judged as a disturbance event; the time-frequency domain of the optical fiber vibration signal is plotted. Spectrogram; extract the Mel frequency cepstral coefficient of the optical fiber vibration signal; establish a deep learning recognition model based on the Mel frequency cepstral coefficient of the disturbance event signal and the time-frequency domain spectrogram; based on the spectrogram and the Mel frequency in the time-frequency domain of the vibration signal The two features of the cepstral coefficient are matched with the deep learning recognition model to determine the type of optical fiber vibration signal. The invention realizes feature extraction of optical fiber sensing signals, accurate identification and classification, and solves the technical problem of low identification and classification accuracy of optical fiber sensing intrusion signals.

Description

technical field [0001] The invention belongs to the technical field of signal detection, and in particular relates to a vibration signal classification method and identification classification system of a distributed optical fiber sensor. Background technique [0002] Distributed optical fiber sensing disturbance detection technology has increasingly become the mainstream technology of intrusion behavior security monitoring due to its strong anti-electromagnetic interference ability, high sensitivity, large dynamic range, easy to quickly capture and high-precision monitoring of dynamic change information and other technical advantages. For example, in oil pipelines, the distributed optical fiber disturbance monitoring system is used to replace manual patrols to detect oil stealing, oil leakage, and pipeline damage in time, and intelligently manage pipelines to ensure pipeline safety. In the field of security, due to the concealment and anti-electromagnetic properties of opti...

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): G01H9/00
CPCG01H9/004
Inventor 许海燕单洪颖谢迎娟张卓
Owner HOHAI UNIV CHANGZHOU
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