Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Oil-immersed transformer fault data preprocessing method based on multiple stages

An oil-immersed transformer and fault data technology, applied in data processing applications, nuclear methods, instruments, etc., can solve the problem of low accuracy of transformer fault diagnosis algorithms, reduce the amount of misreported data, improve data quality, and reduce analysis volume effect

Pending Publication Date: 2019-11-19
XI'AN POLYTECHNIC UNIVERSITY
View PDF17 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a multi-stage based oil-immersed transformer fault data preprocessing method, which solves the "dirty data" generated due to accidental problems when the existing monitoring system uploads data, thus leading to accurate transformer fault diagnosis algorithms low degree problem

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-immersed transformer fault data preprocessing method based on multiple stages
  • Oil-immersed transformer fault data preprocessing method based on multiple stages
  • Oil-immersed transformer fault data preprocessing method based on multiple stages

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0042] The multi-stage oil-immersed transformer fault data preprocessing method based on the present invention, such as figure 1 As shown, the specific operation process includes the following steps:

[0043] Step 1, collect oil-immersed transformer data, and perform isolated point detection on it;

[0044] The specific process of step 1 is as follows:

[0045] Define the collected oil-immersed transformer data as X={x 1 ,x 2 ,...x N}, define that each object has m attributes, namely x i ={x i1 ,x i2 … x im}, i=(1,2,...n), in order to reduce the error, the input data is normalized in [-1,1], and the normalized X is recorded as X 1 , as shown in the following matrix:

[0046]

[0047] Calculate the similarity coefficient r between each pair of objects after normalization ij , to judge the degree of discreteness of each object in ...

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-immersed transformer fault data preprocessing method based on multiple stages. The method comprises the steps of acquiring the oil-immersed transformer data, carrying out isolated point detection on the oil-immersed transformer data, and preprocessing the oil-immersed transformer data according to the isolated point detection result to obtain the data set to be analyzed. Therefore, the data preprocessing is realized. According to the method disclosed by the invention, isolated point detection is carried out on original data by utilizing a clustering algorithm, rules are established according to related guide rule standards of the transformer, and pseudo-error data is eliminated, so that the misinformation data volume is greatly reduced, the fault diagnosis analysis quantity is reduced, and the workload of engineering personnel is reduced. The data collection agreement construction rule II is used for judging whether defects and redundancy exist or not, data is compensated through a data filling algorithm and a data reduction method, and the data quality is improved.

Description

technical field [0001] The invention belongs to the technical field of transformer fault monitoring, and in particular relates to a multi-stage based oil-immersed transformer fault data preprocessing method. Background technique [0002] Transformers are widely used in power systems, and their safe and stable operating status is related to the safety of the power grid and people, and failures will cause great economic losses. Therefore, the State Grid continues to apply advanced sensor technology and online monitoring methods to the monitoring of transformer status. The data returned by each online monitoring system can also "more accurately" reflect the operating status of the transformer. Uncertainty, misoperation by on-site personnel, and communication failures will generate some "dirty data" that will affect transformer fault diagnosis and analysis. [0003] Therefore, it is very important for the accuracy of transformer fault diagnosis to detect "dirty data" through da...

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
IPC IPC(8): G06K9/62G06Q10/00G06Q50/06G06N20/10
CPCG06Q10/20G06Q50/06G06N20/10G06F18/2433G06F18/2411Y04S10/50
Inventor 黄新波马玉涛朱永灿田毅
Owner XI'AN POLYTECHNIC UNIVERSITY
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
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