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

A Cyclic Progressive Partial Discharge Discrimination Method

A partial discharge and discrimination method technology, applied in the field of cyclic progressive partial discharge discrimination, can solve the problems of misjudging noise as partial discharge, misjudgment and false alarm, etc., and achieves the effect of low misjudgment rate, accurate judgment and abundant samples

Active Publication Date: 2022-07-22
广州智丰电气科技有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, the output result of this judgment method is only to judge whether the detected signal is partial discharge or noise, and this method is an instantaneous judgment result, without comprehensive judgment of each frequency, it is easy to misjudge some low-frequency, high-frequency or specific frequency noise as Partial discharge, causing misjudgment and false alarm

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 Cyclic Progressive Partial Discharge Discrimination Method
  • A Cyclic Progressive Partial Discharge Discrimination Method
  • A Cyclic Progressive Partial Discharge Discrimination Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0058] like Figure 7 As shown, the background data processing and analysis center MS starts to discriminate after receiving the detection signal, and reads the detection data into the logic gate f 1 -q-n 1 -t 1 Eigenvalue discrimination, preliminary discrimination threshold setting: f 1 (1~5MHz), q(50~80pC), n 1 (20~30pps), t 1 (3~5min), preliminarily determine whether the detected signal is PD or noise. If the eigenvalues ​​f, q, n, and t of the detected signal all meet the set threshold, it is determined as PD, and the first neural network judgment mechanism is entered; Otherwise, it is judged as the end judgment of noise.

[0059] The first neural network discrimination mechanism: discriminate the three-dimensional map feature of the detected signal, give a partial discharge similarity percentage value, and then judge whether the detected signal is partial discharge or noise. If the percentage value of the detected signal output is greater than or equal to 90% For pa...

Embodiment approach 2

[0067] like Figure 8 As shown, the neural network can discriminate more than two types of PD and Noise by discriminating signal types. The output layer contains 6 PD types and 3 Noise types, a total of 9 type data parameter libraries, which are:

[0068] PD1—insulation hole partial discharge signal;

[0069] PD2—insulation interface creepage partial discharge signal;

[0070] PD3—Insulation impurity partial discharge signal;

[0071] PD4—interface gap partial discharge signal;

[0072]PD5—Inner conductor raised partial discharge signal (tip discharge);

[0073] PD6—outer conductor raised partial discharge signal (tip discharge);

[0074] Noise1—single-group, double-group, three-group, multi-group corona noise;

[0075] Noise2—vertical building-like, horizontal pie-like double-cluster noise;

[0076] Noise3—Noisy, no phase characteristic noise.

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 relates to the field of cable partial discharge detection methods, in particular to a cyclic progressive partial discharge discrimination method, including a logic gate discrimination process and a neural network discrimination process. The logic gate discrimination process is obtained by reading the transmission of a partial discharge signal processing device. The frequency f, phase φ, discharge amount q, density n, and duration t of the PD signal are taken as characteristic quantities, and the PD signal is discriminated by the eigenvalues ​​of the logic gate f‑q‑n‑t according to the above five characteristic quantities, and at the same time After each logic gate discrimination, a neural network discrimination is performed. Only when the logic gate discrimination and neural network discrimination on the four frequencies are both judged as partial discharge, the output discrimination result is partial discharge; when any logic gate discrimination or neural network discrimination is performed. If the network judges it to be noise, it will return to re-read the data for judgment. There are series logic gate judgment and neural network judgment, and the judgment mechanism is set according to the characteristics of the partial discharge signal, which greatly improves the accuracy of the judgment.

Description

technical field [0001] The invention relates to the field of cable partial discharge detection methods, in particular to a cyclic progressive partial discharge discrimination method. Background technique [0002] Partial discharge ("partial discharge" for short) is an important cause of the final insulation breakdown of high-voltage electrical equipment, and it is also an important indicator of insulation deterioration, and it is a precursor to insulation damage. One of the effective means to find insulation defects is to prevent sudden breakdown accidents of cable lines. Since the online monitoring is automatic and unmanned, the online monitoring system has a high-accuracy partial discharge interpretation mechanism because it is far away from human monitoring. It is important for the online monitoring system to obtain effective and accurate monitoring results and to ensure the reliable operation of the power cable. significance. [0003] Patent document CN103513168 B disc...

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): G01R31/12G06N3/08
CPCG01R31/1272G06N3/08
Inventor 东盛刚刘毅坚周智鹏鲁晶晶谢艳婷唐敏玲蔡诗廷邹梓健
Owner 广州智丰电气科技有限公司
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