Supercharge Your Innovation With Domain-Expert AI Agents!

Fault Diagnosis Method of Oil-immersed Transformer Based on Genetic Programming and Logistic Language Regression

A technology for oil-immersed transformers and transformer faults, which is used in instruments, measuring electrical variables, and testing dielectric strength. Effect

Active Publication Date: 2019-01-29
ZHEJIANG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the correct rate of fault diagnosis is low, generally only about 80%

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
  • Fault Diagnosis Method of Oil-immersed Transformer Based on Genetic Programming and Logistic Language Regression
  • Fault Diagnosis Method of Oil-immersed Transformer Based on Genetic Programming and Logistic Language Regression
  • Fault Diagnosis Method of Oil-immersed Transformer Based on Genetic Programming and Logistic Language Regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] Firstly, the live detection data of medium and high temperature overheating fault transformers in Zhejiang Power Grid are selected, with a total of 14 sets of 899 data. Because the data has been counted for a long time, it is not the fault at the beginning. Therefore, the fault data is selected as the fault transformer data set. C 1 , selected from the live detection data of normal transformers in Zhejiang Power Grid, and selected 24 sets of 531 pieces of data and the data of the above 14 faulty transformers in normal state as the normal transformer data set C 2 . Then, 15 kinds of characteristic gas indicators dissolved in insulating oil that may be related to whether the transformer is faulty are selected, including CH 4 Concentration, C 2 h 6 Concentration, C 2 h 4 Concentration, CO 2 concentration, total hydrocarbon concentration, C 2 h 4 / H 2 Ratio, C 2 h 6 / H 2 Ratio, CO / CO 2 Ratio, CH 4 / (CH 4 +C 2 h 6 +C 2 h 4 ) relative concentration, H 2 / (...

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 fault diagnosis method for an oil-immersed type transformer based on genetic planning and logical language regression. The fault diagnosis method comprises the following steps: (1) selecting charged detection data of a faulty transformer as a faulty transformer data set C1 and selecting charged detection data of a normal transformer as a normal transformer data set C2; (2) selecting a plurality of preset characteristic gas indexes Xi related to whether the transformer is faulty or not, wherein i indicates the type of the characteristic gas indexes; (3) converting data of the characteristic gas indexes Xi in the data set C1 and the data set C2 into 0 or 1 by utilizing a selected separation threshold value to obtain a converted data set C'1 and a converted data set C'2; (4) performing regression processing on the converted data set C'1 and the converted data set C'2 by utilizing genetic programming and using logical languages, so that a regression equation for transformer fault diagnosis is obtained, and the characteristic gas indexes Xi related to transformer fault is determined. The fault diagnosis method disclosed by the invention is objective, fair, simple and easy to implement.

Description

technical field [0001] The invention relates to the field of fault diagnosis of oil-immersed transformers, in particular to a fault diagnosis method for oil-immersed transformers based on genetic programming and logic operations. Background technique [0002] The insulating oil in the oil-immersed transformer is a mixture of hydrocarbon molecules with different molecular weights. Electrical or thermal faults can break some C-H bonds and C-C bonds, accompanied by the generation of a small amount of active hydrogen atoms and unstable hydrocarbons. Free radicals of compounds, these hydrogen atoms or free radicals rapidly recombine through complex chemical reactions to form H 2 and low molecular hydrocarbon gases, such as CH 4 、C 2 h 6 、C 2 h 4 and C 2 h 2 etc. It is also possible to generate solid particle grade hydrocarbon polymers of carbon. Oxidation of oil also generates a small amount of CO and CO 2 , the long-term accumulation can reach a significant amount. The...

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): G01N33/28G01R31/12
CPCG01N33/28G01R31/1281
Inventor 华中生周健范逸文
Owner ZHEJIANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com