Method and system for recognizing DC cable partial discharge signal pattern based on compressive sensing theory

A DC cable, discharge signal technology, applied in character and pattern recognition, computer parts, instruments, etc., can solve the problems of uncertainty and diversity of detection signals, difficulty in partial discharge research, etc.

Inactive Publication Date: 2017-03-15
ZHOUSHAN ELECTRIC POWER SUPPLY COMPANY OF STATE GRID ZHEJIANG ELECTRIC POWER +2
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The partial discharge detection of AC cables is generally based on the IEC 60885-3 standard, but there is no standard or technical specification for partial discharge detection of DC XLPE cables. The signal has the characteristics of uncertainty and diversity, which makes the study of partial discharge under DC more difficult than under AC

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
  • Method and system for recognizing DC cable partial discharge signal pattern based on compressive sensing theory
  • Method and system for recognizing DC cable partial discharge signal pattern based on compressive sensing theory
  • Method and system for recognizing DC cable partial discharge signal pattern based on compressive sensing theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] For ease of understanding, the design principle of the DC cable partial discharge signal pattern recognition method based on compressive sensing theory according to the present invention will be described in detail below with reference to the accompanying drawings.

[0064] figure 1 It shows the three-dimensional atlas corresponding to the partial data of the training sample data A in an embodiment of the method of the present invention, figure 2 It shows the three-dimensional atlas corresponding to the data of a certain data y to be identified in an embodiment of the method of the present invention, image 3 It shows the three-dimensional map corresponding to the data of a certain coefficient vector x in an embodiment of the method of the present invention, Figure 4 The principle flow of the method of the present invention is illustrated. combined reference Figure 1-Figure 4 :

[0065] Firstly, obtain the partial discharge sample data of class C (in this embodim...

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 a system for recognizing a DC cable partial discharge signal pattern based on a compressive sensing theory. The method comprises the steps of acquiring training sample data A=[ A1, A2, ...Ac], wherein A belongs to R<m*n>; acquiring data y to be recognized, wherein y belongs to R<m>; constructing y=Ax, and solving x which is defined in the description, wherein x belongs to R<n>; constructing a residual error ri which is defined in the description; solving argmin(ri) to acquire a value which represents the category of a DC cable partial discharge signal pattern corresponding to the vector y to be recognized. The method disclosed by the invention can be used for recognizing the DC cable partial discharge signal pattern, and the category of the pattern corresponds to the category of a DC cable insulation defect. Effective recognition for the state of different insulation defects of a high-voltage DC cable, such as a crosslinked polyethylene cable, can be realized according to the method. Correspondingly, the invention further discloses a system for recognizing the DC cable partial discharge signal pattern based on the compressive sensing theory. The method and the system disclosed by the invention effectively fill up the defect that less researched is performed on DC cable partial discharge defect recognition; data driving is realized based on compressive sensing, and waste of effective information is reduced; and solving performed according to a Homotopy method enables the calculation speed to be high and the recognition rate to be high.

Description

technical field [0001] The invention relates to a signal pattern recognition method and system, in particular to a DC cable partial discharge signal pattern recognition method and system. Background technique [0002] Compared with traditional AC transmission technology, flexible DC transmission technology has many advantages such as strong controllability, large transmission capacity, and long transmission distance. In recent years, the number of domestic and foreign DC transmission lines in operation has been increasing, and the voltage level has been continuously improved. The XLPE DC cable developed by a company in 2014 with ±525kV, a transmission distance greater than 1500km, and a transmission power greater than 2.6GW represents the current DC cable manufacturing. The highest level of technology. Although DC cable technology has developed unprecedentedly, the research on operation and maintenance and signal post-processing technology such as insulation live detection ...

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): G06K9/00
CPCG06F2218/00
Inventor 宣耀伟胡凯乐彦杰徐蓓蓓杨丰源盛戈皞许永鹏钱勇罗林根宋辉江秀臣
Owner ZHOUSHAN ELECTRIC POWER SUPPLY COMPANY OF STATE GRID ZHEJIANG 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