Oil soaked transformer fault diagnosis method

An oil-immersed transformer, fault diagnosis technology, applied in the direction of instruments, measuring electrical variables, measuring devices, etc., can solve the problem that the transformer fault diagnosis method cannot meet the requirements well, and achieve good practicability, popularization, and high diagnosis The effect of accuracy

Inactive Publication Date: 2009-11-25
ZHEJIANG UNIV
View PDF0 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

None of the existing transformer fault diagnosis methods can meet the requirements well

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
  • Oil soaked transformer fault diagnosis method
  • Oil soaked transformer fault diagnosis method
  • Oil soaked transformer fault diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The invention combines existing data acquisition equipment, mature technology and frontier theoretical knowledge. The multi-classification SVM model using multi-core learning and multi-class objective function methods can effectively avoid the possibility of confusion and errors in the direct process from input data to output classification results.

[0015] The fault diagnosis method of the oil-immersed transformer of the present invention comprises the following steps:

[0016] 1. Obtain five kinds of gases dissolved in transformer oil (H 2 , CH 4 , C 2 h 2 , C 2 h 4 , C 2 h 6 ) data to form a DGA database as a feature parameter.

[0017] 2. Normalize the DGA raw data. details as follows:

[0018] (1) Get the original data from DGA, the pattern vector is: x i =(x i1 , x i2 , x i3 , x i4 , x i5 )

[0019] (2) Considering the huge difference and dispersibility of various dissolved gas contents, in order to reduce the influence caused by the large value ...

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 an oil soaked transformer fault diagnosis method, including the following steps: a sample is firstly obtained, and the concentration data of five gases in the sample is in normalized treatment, so that a training sample set and a test sample set are formed; the number of elementary kernel functions and the parameters of each basis kernel are determined, and the optimal punitive parameters are determined by using the method of cross validation; according to the optimal punitive parameters, corresponding disaggregated model is obtained by using training sample and multi-classification multi-kernel learning method; and the disaggregated model after trained is used for carrying out fault diagnosis of the sample to be tested in verification centralization. The invention can guarantee very high accuracy rate of diagnosis, and has very good practicability and generalization.

Description

technical field [0001] The invention belongs to the technical field of electric equipment, in particular to a fault diagnosis method for an oil-immersed transformer. Background technique [0002] Power transformer is an important equipment in power system. Using Dissolved Gas Analysis (DGA, Dissolved Gas Analysis) method to detect internal faults of oil-immersed transformers has become an important means of insulation supervision. The complexity of transformer structure and the diversity, randomness and ambiguity of fault causes, fault phenomena and fault mechanisms make it difficult to diagnose insulation faults. With the rapid development of computers, artificial intelligence technologies such as expert systems and pattern recognition have gained preliminary application research in fault diagnosis of power systems. In recent years, with the help of artificial neural network, fuzzy mathematics, clustering principle, and gray system theory, people have obtained some applica...

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): G01R31/00G06N1/00G06N99/00
Inventor 郭创新彭明伟朱承治曹晋彰高振兴
Owner ZHEJIANG UNIV
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