Real-time power cable monitoring and protection system based on deep learning

A real-time monitoring and deep learning technology, applied in electromagnetic wave transmission systems, transmission systems, electrical components, etc., can solve problems such as optical fiber failures, accidents that cannot be achieved, and complex environments, so as to prevent accidents, save search time, and improve The effect of work efficiency

Active Publication Date: 2019-03-15
JINZHONG POWER SUPPLY COMPANY OF STATE GRID SHANXI ELECTRIC POWER
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The operating environment of the power optical cable varies from overhead to buried, and the environment is relatively complex. The optical fiber inside the power optical cable is more susceptible to failure due to external factors
The traditional power optical cable operation and maintenance work is regular inspection, and when a fault occurs, OTDR (Optical

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
  • Real-time power cable monitoring and protection system based on deep learning
  • Real-time power cable monitoring and protection system based on deep learning
  • Real-time power cable monitoring and protection system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0021] In order to make the technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described clearly and completely in conjunction with specific embodiments and drawings. Obviously, the described embodiments are a part of the embodiments of the present invention. Not all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0022] Such as figure 1 As shown, the embodiment of the present invention provides a real-time monitoring and protection system for power optical cables based on deep learning, including a control unit 1, a real-time monitoring unit 2, a fault detection unit 3, a data analysis management unit 4, and an alarm and location unit 5. The wiring ports of the control unit 1 are connected to the wiring ports of the real-time moni...

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 provides a real-time power cable monitoring and protection system based on deep learning. The system comprises a control unit, a real-time monitoring unit, a fault detection unit, a dataanalysis management unit and an alarm and positioning unit; the real-time monitoring unit is used for monitoring optical power in the optical fiber of a cable in real time, and sending the optical power to the control unit; the control unit is used for starting the fault detection unit when the optical power in the optical fiber of the cable is changed; the fault detection unit is used for measuring fault data in the optical fiber, and sending the fault data to the data analysis management unit; the data analysis management unit is used for building a deep belief network classifier via a deeplearning method, analyzing the data via the deep belief network classifier to acquire an abnormal cable position, and sending the abnormal cable position to the alarm and positioning unit. Accordingto the system provided by the invention, the cable can be monitoring in real time and the accident of the cable can be prejudged, so that the system has the advantages of being real-time, online and reliable, and is extremely applicable to the power system communication network.

Description

technical field [0001] The invention relates to the technical field of power optical cable safety detection, in particular to a real-time monitoring and protection system for power optical cables based on deep learning. Background technique [0002] The smart grid requires the power system to realize the informatization, automation and interaction of the power grid, so the emergence of power optical cables solves the problem of efficient transmission of information. Power optical cable refers to all kinds of composite cables and special optical cables that take into account both power transmission and information communication in the power system. It can be roughly divided into 1. Ground wire wound optical cable GWWOP and bundled optical cable ADL, 2. All-dielectric self-supporting optical cable ADSS and metal self-supporting optical cable MASS, 3. Optical fiber composite overhead ground wire OPGW and optical fiber composite overhead phase wire OPPC, 4. Optical hybrid cable...

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): H04B10/077H04B10/079
CPCH04B10/077H04B10/0771H04B10/0793H04B10/0795
Inventor 王斌马东春雷丽萍高鼎孙凯杜宇仝景辉胡冠婧
Owner JINZHONG POWER SUPPLY COMPANY OF STATE GRID SHANXI ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products