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

Transformer fault diagnosis method based on decision tree classifier

A technology for transformer fault and decision tree classification, which is used in instruments, measuring devices, etc.

Inactive Publication Date: 2020-12-11
NINGBO UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, although decision tree classifiers can solve many classification problems, so far, decision trees have not been applied to solve the problem 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 based on decision tree classifier
  • Transformer fault diagnosis method based on decision tree classifier
  • Transformer fault diagnosis method based on decision tree classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0038] The present invention discloses a transformer fault diagnosis method based on a decision tree classifier, such as below in connection with figure 1 Flow schematic illustrated embodiment will be described specific embodiments of the method of the present invention.

[0039] In the present embodiment case, transformer oil immersion at N partial discharge failure status 1 = 21 sets of data, there is a spark discharge failure status under N 2 = 16 sets of data, there is arcing fault condition under N 3 = 18 sets of data, there are N medium temperature thermal fault condition 4 = 23 sets of data, there is a low temperature thermal fault condition N 5 = 23 sets of data, there is a high temperature thermal fault condition N 6 = 24 sets of data. Using these data establish transformer fault diagnosis model and implementation of online troubleshooting...

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 based on a decision tree classifier, and aims to carry out feature expansion and transformation on dissolved gas concentration data in oil-immersed transformer oil and establish a decision tree classifier model based on the transformed features so as to implement fault diagnosis of a transformer. The method disclosed by the invention hasthe advantages that firstly, the discriminant least square algorithm is used for optimizing the characteristics suitable for classification, so that the most suitable characteristics can be optimizedfrom the perspective of improving the classification performance; and secondly, the decision-making tree classifier model is obtained by training the optimized features, and the classification effectof the decision-making tree can be ensured besides the characteristic that the decision-making tree is easy to understand. Therefore, the method provided by the invention is a feasible transformer fault diagnosis technology.

Description

Technical field [0001] The present invention relates to a fault diagnosis method for transformer, particularly to transformer fault diagnosis method based on a decision tree classifier. Background technique [0002] Transformer power delivery system is essential electrical equipment, as for its key distribution system operation, the operating state of the transformer will directly affect the operation of the entire power system. Moreover, the transformer operation under fault conditions will lead to direct or indirect economic losses of power system. Therefore, the study for transformer fault diagnosis is of great practical significance. In my country, the supply and distribution transformers used in the system are generally oil-immersed transformers, common ideas transformer fault diagnosis embodiment is a transformer oil dissolved gases (hydrogen, methane, ethane, ethylene, and acetylene) concentration data for analysis. Our currently conventionally used is a modified three-rat...

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): G01D21/02
CPCG01D21/02
Inventor 陈泰麒葛英辉其他发明人请求不公开姓名
Owner NINGBO UNIV