Transformer Fault Type Classification Method Based on Improved Density Peak Clustering Algorithm

A transformer fault and clustering algorithm technology, applied in the field of data processing, can solve problems such as poor adaptability and complex fault mechanism of transformers, achieve good adaptability, improve classification efficiency and accuracy, and avoid chain effects

Active Publication Date: 2020-07-21
HUIZHOU POWER SUPPLY BUREAU OF GUANGDONG POWER GRID CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention solves the problem of poor adaptability of the traditional fault diagnosis method due to the complex fault mechanism of the transformer, and can be used in the fault diagnosis and classification of power transformers

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 Type Classification Method Based on Improved Density Peak Clustering Algorithm
  • Transformer Fault Type Classification Method Based on Improved Density Peak Clustering Algorithm
  • Transformer Fault Type Classification Method Based on Improved Density Peak Clustering Algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Such as figure 2 As shown, a kind of transformer fault type classification method based on the improved density peak clustering algorithm of the present invention mainly includes the following steps:

[0037] (1) Data import and preprocessing

[0038] The verification data used in the present invention is collected from a 110kV transformer of a power grid test institute in Guangdong, with a total of 186 sets of oil chromatographic data, covering eight types of typical transformer faults. The specific chromatographic data distribution and corresponding fault types are shown in Table 2. The data set Ω formed is:

[0039]

[0040] where x i,1 -x i,5 Represent the normalized values ​​of the five chromatographic characteristic gases of hydrogen, methane, ethane, ethylene and acetylene in the i-th group of oil chromatographic data, namely

[0041]

[0042] minx ·j for x ij The minimum value of the sample index in the column; max for x ij The maximum value of ...

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 method for classifying transformer fault types based on an improved density peak clustering algorithm, which includes: 1) collecting data from a transformer oil chromatography monitoring system, and forming a data set Ω after preprocessing; The density distribution characteristics of the data set Ω; 3) Use the density distribution characteristics ρ and the distance distribution characteristics δ of the data set Ω to construct a decision graph G, and identify the sample density center; 4) Calculate the similarity matrix γ of the data set Ω, and based on this Construct the density skeleton of each fault type data subset; 5) Classify the remaining points according to the distance distribution characteristics δ of each fault type data subset, and complete the fault type identification. The invention solves the problem of poor adaptability of the traditional fault diagnosis method due to the complex fault mechanism of the transformer, and can be targetedly used for fault diagnosis and classification of power transformers.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for diagnosing transformer fault types. Background technique [0002] With the continuous development of our country's economy, the huge demand for energy has promoted the rapid development of the electric power industry. However, with the increase of system scale, the impact of power equipment failure on people's production and modern life is also increasing. For safe production, it is inevitable to overhaul and maintain transformers, which are extremely important electrical equipment in power transmission and distribution systems. It cannot make up for the loss that may be caused by equipment failure. [0003] As the development direction of equipment maintenance, condition-based maintenance can judge the health status and development trend of equipment by combining the information provided during equipment operation and maintenance, and arrange maintenance i...

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): G06K9/62G06Q50/06
CPCG06Q50/06G06F18/23213G06F18/24133
Inventor 唐松平彭刚张云钟振鑫林志明黄晓波曾力吴涛史良肖云董玉玺王云龙柯祖梁巫小彬
Owner HUIZHOU POWER SUPPLY BUREAU OF GUANGDONG POWER GRID CO LTD
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap