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

Transformer fault diagnosis method and apparatus

A transformer fault and transformer technology, applied in the field of power system, can solve problems such as low accuracy of transformer fault diagnosis, and achieve the effects of improving fault diagnosis efficiency, improving the quality of distribution transformers, and improving accuracy

Inactive Publication Date: 2017-08-18
YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST +1
View PDF9 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a method and device for diagnosing transformer faults to solve the problem of low accuracy of transformer fault diagnosis

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 fault diagnosis method and apparatus
  • Transformer fault diagnosis method and apparatus
  • Transformer fault diagnosis method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0044] This embodiment is based on the first embodiment and is a further improvement on the first embodiment. In the first embodiment, in the step of obtaining the dissolved gas concentration in the insulating oil of the transformer, the confirmed fault types of the transformer include high temperature overheating, medium and low temperature overheating, Arcing and partial discharge fault types; gas concentrations include: specific gas concentrations for hydrogen, methane, ethane, acetylene, and ethylene.

[0045] Common fault types of transformers are divided into external faults and internal faults. Internal faults cannot be concluded by observing the type of fault, and usually the phenomenon of internal faults can only occur when the transformer is in operation, so it is very important to detect faults in transformers that are not in the running state, and can also be applied to the quality of transformers before use. check. The types of internal faults include thermal fau...

Embodiment 3

[0049] image 3 It is an exemplary flowchart of the process of constructing and training a neural network in Embodiment 1 of the present application. This embodiment is based on the first embodiment and is a further improvement on the first embodiment. see image 3 As shown, in this embodiment, the neural network is constructed and trained, including:

[0050] Step 301, determine the gas concentration as the input data of the neural network.

[0051] A neural network needs to start training a neural network by building a neural network, inputting data, and outputting results. Since the neural network algorithm or the improved neural network algorithm is a general artificial intelligence algorithm, the construction of the neural network is not described in detail in the embodiment of the present invention. The gas concentration in the fault comparison table is used as input data.

[0052] Step 302, determine the determined fault type corresponding to the gas concentration ...

Embodiment 4

[0061] Figure 4 It is an exemplary flow chart of the process of training the neural network according to the learning rate and the momentum coefficient in the third embodiment of the present application. This embodiment is based on the third embodiment and is a further improvement on the third embodiment. see Figure 4 As shown, in this embodiment, according to the learning rate and the momentum coefficient, the neural network is trained, including:

[0062] Step 401, initialize weight and bias parameters.

[0063] Step 402, input the gas concentration into the input node of the neural network.

[0064] Step 403, calculate the output value of the hidden layer node according to the weight and bias parameters.

[0065] Step 404, calculating the error term of the hidden layer node according to the output value of the hidden layer node.

[0066] Step 405: Update the first weight value and the first bias parameter of the hidden layer node according to the hidden layer node er...

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 fault diagnosis method and apparatus, relating to the technical field of a power system and particularly solving the problem of low fault diagnosis accuracy of a transformer. The method includes obtaining the dissolved gas concentration in the insulating oil of the transformer, wherein the transformer is a transformer having a determined fault type; establishing a fault parallel table of the fault types of the transformer and the gas concentration; taking the data in the fault parallel table as the training sample and the test sample, and constructing and training a nerve network; and inputting the concentration of the detected gas dissolved in the insulating oil of the transformer, and diagnosing the fault type of the transformer to be diagnosed. The transformer fault diagnosis method and apparatus are applicable to the transformer fault diagnosis.

Description

technical field [0001] The present application relates to the technical field of power systems, and in particular to a method and device for diagnosing transformer faults. Background technique [0002] The operating state of the transformer is an important factor affecting the reliability of the entire power transmission. In actual operation, various faults may occur in the transformer due to some accidental or non-accidental reasons. Among them, the most likely fault of the transformer is the insulation fault. Insulation faults are mainly caused by insulation aging or insulation weakening. Among them, partial discharge phenomenon is an important sign of transformer insulation level reduction. Therefore, importing the results of partial discharge test into the simulation system to classify and identify the discharge type can accurately and quickly It can accurately judge the potential insulation faults inside the transformer, so as to troubleshoot the transformer faults in t...

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): G01D21/02G01R31/00G06N3/04G06N3/08
CPCG06N3/04G06N3/08G01D21/02G01R31/00
Inventor 刘光祺杨航刘凌刘轩东王科钱国超邹徳旭颜冰
Owner YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com