Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Transformer partial discharge map generation method based on generated adversarial network

A partial discharge and transformer technology, applied in the field of transformer partial discharge map generation based on generative adversarial network, achieves the effect of simple operation, easy implementation and solving data shortage

Inactive Publication Date: 2019-08-20
XI'AN POLYTECHNIC UNIVERSITY
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Transformer is one of the important equipment in the substation link of power system, if it breaks down, it will cause huge economic loss

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
  • Transformer partial discharge map generation method based on generated adversarial network
  • Transformer partial discharge map generation method based on generated adversarial network
  • Transformer partial discharge map generation method based on generated adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0034] The present invention is based on the generator partial discharge map generation method of the transformer network, such as figure 1 As shown, the specific steps are as follows:

[0035] Step 1, using the collected transformer partial discharge atlas with labels as an input sample set;

[0036] In step 1, the labels are: five discharge forms: bubble discharge, floating potential discharge, insulating surface, interlayer discharge or sharp angle discharge;

[0037] Step 2, performing grayscale processing on the transformer partial discharge atlas with labels collected in step 1;

[0038] In step 2, the grayscale processing is the average grayscale method as shown in formula (1):

[0039] F(i,j)=(R(i,j)+G(i,j)+B(i,j)) / 3 (1)

[0040] Among them: F represents the image matrix after grayscale; R, G, B represent the components of the par...

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 transformer partial discharge map generation method based on a generated adversarial network. The method comprises the following steps of S1, taking a collected transformer partial discharge map with a label as an input sample set; S2, carrying out grayscale processing on the transformer partial discharge map with the label; S3, setting a random noise, and taking a Gaussian noise as the random noise which is about to be input; setting a loss function of a generator, getting the generator, taking the partial discharge map after grayscale processing and the random noiseas input of the generator, and passing the generator and generating a pseudo sample; S4, setting the loss function of a discriminator, generating the discriminator, taking the pseudo sample generatedin the S3 and an original partial discharge map as the input of the discriminator and determining, and carrying out parameter determination; and S5, after the parameter is determined, outputting theacquired transformer partial discharge map of the generated adversarial network if a device outputs 1, and abandoning if the device outputs 0. By using the method, the partial discharge map required by a researcher can be accurately generated.

Description

technical field [0001] The invention belongs to the technical field of online monitoring methods for transformers, and in particular relates to a method for generating partial discharge graphs of transformers based on generative confrontation networks. Background technique [0002] Transformer is one of the important equipments in the substation link of power system, if it breaks down, it will cause huge economic loss. Therefore, it is very necessary to carry out online monitoring and fault diagnosis of transformers. The common faults of transformers can be roughly divided into two categories: discharge faults and overheating faults. Discharge faults include: partial discharge, high-energy discharge and low-energy discharge. Among them, partial discharge is a kind of discharge in which only a part of the insulation system discharges without forming a penetrating discharge channel under the action of an electric field. The detection and evaluation of partial discharge is an ...

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): G01R31/12
CPCG01R31/1227
Inventor 黄新波蒋卫涛朱永灿曹雯田毅赵隆
Owner XI'AN POLYTECHNIC UNIVERSITY
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
Eureka Blog
Learn More
PatSnap group products