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

A Method for Recognition of Cable Partial Discharge Patterns Based on Depth Sample Enhancement

A technology of partial discharge and pattern recognition, which is applied in the direction of testing dielectric strength, etc., can solve the problems of a large amount of training data, cable operation failure, and errors, and achieve the effects of simple conversion process, error avoidance, and high prediction and recognition accuracy

Active Publication Date: 2022-04-12
JIAOZUO POWER SUPPLY COMPANY OF STATE GRID HENAN ELECTRIC POWER
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] High-voltage cables are one of the main forms of power transmission, and are widely used in wind farms, solar energy and other distributed energy transmission and grid connection, as well as offshore oil and gas platforms, offshore island power transmission, etc. , cable body or accessories manufacturing quality, laying installation quality and other reasons caused by cable operation failure will cause different degrees of economic loss and social impact
[0003] The traditional cable partial discharge pattern recognition method relies heavily on the selection of manual features, and the design of manual features is very dependent on expert experience, which will inevitably lead to errors. As an emerging field, deep learning overcomes the above shortcomings and can automatically learn the original The layered representation of data features, but requires a large amount of training data. Therefore, the present invention proposes a method that can avoid errors caused by selecting features based on expert experience, and can still accurately detect cable insulation defects in the case of small samples. Cable Partial Discharge Pattern Recognition Method Based on Depth Sample Enhancement for Type Recognition

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 Method for Recognition of Cable Partial Discharge Patterns Based on Depth Sample Enhancement
  • A Method for Recognition of Cable Partial Discharge Patterns Based on Depth Sample Enhancement
  • A Method for Recognition of Cable Partial Discharge Patterns Based on Depth Sample Enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] like Figure 5 As shown, a method for identifying partial discharge patterns of cables based on depth sample enhancement includes the following steps:

[0040] Step A: converting the collected partial discharge time-domain signal of the cable insulation defect into an image to obtain a two-dimensional image, which is used as an initial sample set;

[0041] When collecting the signal, first boost the voltage of the insulation defect until the defect breaks down, determine the breakdown voltage of the defect, and then select a certain number of discharge voltage values ​​within the defect discharge voltage range, maintain the discharge voltage, and collect the partial discharge current of the DC cable. domain signal, convert the time domain signal to an image, and follow the steps below: randomly select a time domain signal in a time period from the collected time domain signal, and form the signal index value corresponding to the signal point in this period of time. A 1...

Embodiment 2

[0055] like Figure 5 As shown, a method for identifying partial discharge patterns of cables based on depth sample enhancement includes the following steps:

[0056] Step A: converting the collected partial discharge time-domain signal of the cable insulation defect into an image to obtain a two-dimensional image, which is used as an initial sample set;

[0057] When collecting the signal, first boost the voltage of the insulation defect until the defect breaks down, determine the breakdown voltage of the defect, and then select a certain number of discharge voltage values ​​within the defect discharge voltage range, maintain the discharge voltage, and collect the partial discharge current of the DC cable. Domain signal, convert the time domain signal into an image, and follow the following steps: randomly select a time domain signal in a time period from the collected time domain signal, and form the signal index value corresponding to the signal point in this period of time...

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 a cable partial discharge pattern recognition method based on depth sample enhancement, comprising the following steps: converting the collected partial discharge time-domain signal of cable insulation defects into a two-dimensional image as an initial sample set, and inputting the two-dimensional image In the generated confrontation network, deep sample enhancement is performed, the enhanced samples are added to the initial sample set to form a new sample set, the convolutional neural network model is constructed, and the new sample set is used for supervised training of the convolutional neural network model. The trained convolutional neural network model is obtained, and the time-domain signal of the insulation discharge type to be predicted is converted into a two-dimensional image and input into the trained convolutional neural network model, and the predicted insulation defect discharge type is output. The invention can avoid errors caused by selecting features based on expert experience, and can still accurately identify types of cable insulation defects in the case of small samples, thereby improving identification speed and accuracy.

Description

technical field [0001] The invention belongs to the technical field of cable partial discharge identification methods, and in particular relates to a cable partial discharge pattern identification method based on depth sample enhancement. Background technique [0002] High-voltage cables are one of the main forms of power transmission. They are widely used in wind farms, solar energy and other distributed energy transmission and grid connection, as well as offshore oil and gas platforms, offshore island power transmission and other occasions. , cable body or accessories manufacturing quality, laying and installation quality and other reasons for cable operation failure will cause different degrees of economic losses and social impact. [0003] The traditional cable PD pattern recognition method relies heavily on the selection of manual features, and the design of manual features is very dependent on expert experience, which will inevitably bring errors. As an emerging field,...

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): G01R31/12
CPCG01R31/12
Inventor 杨贵营龙洁孙抗刘哲睿王海港郭琳李习斌
Owner JIAOZUO POWER SUPPLY COMPANY OF STATE GRID HENAN ELECTRIC POWER