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

A system and method of fiber optic signal recognition

A technology of signal recognition and optical fiber, applied in pattern recognition in signals, character and pattern recognition, instruments, etc., can solve the problems of low efficiency, high consumption of manpower and material resources, etc., and achieve the effect of improving accuracy and correct recognition rate

Pending Publication Date: 2020-10-02
BEIJING INFORMATION SCI & TECH UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If only traditional manual patrols are used to monitor the status of the pipeline, it will consume a lot of manpower and material resources, and the efficiency is low

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 system and method of fiber optic signal recognition
  • A system and method of fiber optic signal recognition
  • A system and method of fiber optic signal recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the attached drawings and specific implementations.

[0020] In the present invention, we conduct research on 5 types of optical fiber vibration data. These five types are excavator excavation, manual excavation, car walking, people walking and environmental noise. The energy and zero-crossing rate two-dimensional space-time graph of their original optical fiber signal are Fourier transformed and frequency shifted.

[0021] Since the original two-dimensional space-time map contains not only the optical fiber vibration signal caused by the event (high-bright area in the figure), but also the background noise component (low-dark area), the entire or partial block sampling of the spectrogram is taken as the event The representative sample of is difficult to distinguish between the bright foreground signal area and the low dark background noise area in the original two-dimensional image.

[0022] The method...

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 optical fiber signal recognition system and method, and relates to an optical fiber sensing signal recognition method based on Fourier transform and CELM. The method comprises the steps: 1) carrying out the Fourier transform of an original sample, and enabling the original sample to serve as a feature sample representing different types of events; 2) adopting a binary classification task decision tree model for the data after feature extraction; and 3) adopting a CELM model to realize each branch node recognition task. Compared with the traditional short-time energy / zero-crossing rate characteristic and extreme learning machine (ELM) algorithm, the Fourier transform and CELM-based optical fiber sensing signal recognition method has the advantage that the classification accuracy of optical fiber vibration data recognition is remarkably improved.

Description

Technical field [0001] The present invention relates to the recognition of optical fiber vibration signals, in particular to the recognition of optical fiber vibration data by using Fourier transform characteristics and CELM algorithm. Background technique [0002] As the global demand for oil and gas increases, safety protection for oil and gas pipelines is becoming more and more important. If only using traditional methods such as manual patrols to monitor the status of the pipeline, a lot of manpower and material resources will be consumed, and the efficiency will be low. As a result, security detection systems for oil and gas pipelines came into being. This system can set a certain number of optical fiber sensors at the boundary of the target area. External pressure and various vibrations will cause the internal force of the optical fiber to change, thereby generating vibration signals. The system identifies and analyzes the vibration signals generated in this process, and ...

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): G06K9/00G06K9/62
CPCG06F2218/04G06F2218/08G06F2218/12G06F18/214G06F18/24323
Inventor 苗军常艺茹周建亭乔元华邹柏贤
Owner BEIJING INFORMATION SCI & TECH UNIV