Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for fusing and correcting online monitoring data and live detection data of oil-filled transformer

An oil-immersed transformer, live detection technology, applied in the field of statistical analysis

Active Publication Date: 2017-01-25
ZHEJIANG UNIV
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In summary, there is still a certain gap between the method of Lin (2011) and the actual needs of transformer data fusion

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
  • Method for fusing and correcting online monitoring data and live detection data of oil-filled transformer
  • Method for fusing and correcting online monitoring data and live detection data of oil-filled transformer
  • Method for fusing and correcting online monitoring data and live detection data of oil-filled transformer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] We use the following example to illustrate the effect of the fusion correction method for online monitoring data and live detection data proposed by the present invention.

[0053] First, the concentration of hydrogen in the oil of an oil-immersed transformer is obtained through remote online monitoring equipment, which is recorded as the online monitoring data; the concentration of hydrogen in the oil of the oil-immersed transformer obtained by manual sampling is recorded as the live detection data; The live detection data is preprocessed so that the time interval of the online monitoring data is the same, which is 1 day, and the time points of the online monitoring data and the live detection data correspond one-to-one. For the missing online monitoring data, the online monitoring data is filled by linear interpolation, and finally the online monitoring characteristic gas content-time series with complete observations and the charged detection characteristic gas conten...

Embodiment 2～3

[0078] Using the same fusion correction method as in Example 1, the hydrogen concentration-time curve obtained after fusion correction, the hydrogen concentration-time curve of online monitoring and the hydrogen concentration-time curve of charged detection are shown in figure 2 , image 3 .

Embodiment 4

[0080] Using the same fusion correction method as in Example 1, the hydrogen concentration-time curve obtained after fusion correction, the hydrogen concentration-time curve of online monitoring and the hydrogen concentration-time curve of charged detection are shown in Figure 4 Top middle image.

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 fusing and correcting online monitoring data and live detection data of an oil-filled transformer. According to the method, firstly, the online monitoring data and the live detection data are preprocessed to obtain two groups of feature gas content-time sequences with the same time intervals and mutually corresponding time points; then, a hierarchical Bayesian model is built according to the online monitoring feature gas content-time sequences and the live detection feature gas content-time sequences; the hierarchical Bayesian model is subjected to estimation by using a maximum expectation algorithm to obtain the distribution condition of a hyper-parameter eta and a parameter vector beta=[beta<o>, beta<f>]; then, the beta is multiplied by the orthogonal vector Z to obtain the average value of the Zbeta<f>; the average value is used as the replacing value of missing data to be supplemented into the live detection data to obtain the fused and corrected transformer operation data. The transformer operation data and the live detection data have the approximately identical measuring degree level; the change trend of the online monitoring data is remained to the maximum degree; the advantage complementation is realized; the respective limitation of the online data and the live data is broken.

Description

technical field [0001] The invention relates to the field of statistical analysis, in particular to a method for merging and correcting on-line monitoring data of an oil-immersed transformer and live detection data. Background technique [0002] At present, there are two monitoring methods for oil-immersed transformers, one is using online monitoring, that is, using infrared spectrometer remote online monitoring equipment; the other is live detection, that is, professionals go to the site to sample and test the transformer oil. The monitoring interval of online data is short (usually 1 day), and the data distribution is relatively dense, but due to the problems of the online monitoring device itself, its accuracy needs to be verified. The live detection data comes from the sampling detection of professionals, and the accuracy is high, but the cost of manual detection is high, so the detection interval is long (usually more than 1 month). Online monitoring data can make up f...

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): G06F19/00
CPCG16Z99/00
Inventor 华中生
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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