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

A Cluster Analysis Method for Transformer Condition Monitoring Data

A technology of monitoring data and cluster analysis, applied in the direction of instruments, measuring electronics, measuring devices, etc., can solve problems such as false alarms, monitoring data errors, lack of sufficient basis for setting alarm thresholds and alarm levels, etc., and achieve increased probability , The effect of improving the level of safety and stability

Active Publication Date: 2019-12-24
ELECTRIC POWER RES INST OF GUANGXI POWER GRID CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are limitations in the utilization and analysis of monitoring data
On the one hand, the current analysis methods for monitoring data are mainly static analysis threshold alarms, but the setting of alarm thresholds and alarm levels lacks sufficient basis, and is only suitable for discovering explicit defects
On the other hand, after collecting a large amount of data, the monitoring master station system platform lacks the means to analyze and process the data; therefore, it still needs to rely on manual experience to analyze data and predict faults, and it has not been able to realize effective and timely automatic error correction of data
In addition, due to on-site influence factors such as the aging of electronic components of the monitoring device, external environmental interference, and underpressure of the carrier gas, errors in the monitoring data and even false alarms are caused.

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
  • A Cluster Analysis Method for Transformer Condition Monitoring Data
  • A Cluster Analysis Method for Transformer Condition Monitoring Data
  • A Cluster Analysis Method for Transformer Condition Monitoring Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to better understand the present invention, the present invention will be further described below in conjunction with accompanying drawing and specific embodiment:

[0039] Such as figure 1 As shown, a cluster analysis method for transformer condition monitoring data includes the following steps:

[0040] S1: Data extraction: The terminal monitoring device extracts the phased monitoring data of dissolved gas in transformer oil, and the phased cycle is one to three months; the massive quasi-real-time data service platform extracts the operation time and manufacturing of corresponding transformers quotient, voltage level and the load within the corresponding time period.

[0041] S2: Data cleaning: normalize the monitoring data, that is, map the data to the [0,1] interval, the calculation formula is as follows:

[0042] ;

[0043] In the above formula, x ij is the monitoring data of a type of gas of the i-th transformer on day j, max j ( x ij ) for...

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 present invention relates to the technical field of state monitoring and fault diagnosis of power equipment, in particular to a method for cluster analysis of transformer state monitoring data; The analysis method of dissolved gas in oil with the same load rate) overcomes the key problem of troubleshooting latent faults of equipment and improves the security and stability of the power grid; successfully developed an inspection system covering data extraction, cleaning and fusion of dissolved gas in oil, and cluster analysis , effectively avoiding the passive situation of frequent transformer status monitoring false alarms and missing alarms, and achieving the comprehensive optimization of risk, efficiency and cost in one fell swoop.

Description

technical field [0001] The invention relates to the technical field of state monitoring and fault diagnosis of electric equipment, in particular to a cluster analysis method for transformer state monitoring data. Background technique [0002] Dissolved gas monitoring technology in transformer oil has been widely used in the power industry, and has achieved centralized monitoring on the provincial monitoring master station system platform. However, there are limitations in the utilization and analysis of monitoring data. On the one hand, the current analysis methods for monitoring data are mainly static analysis threshold alarms, but the setting of alarm thresholds and alarm levels lacks sufficient basis and is only suitable for discovering explicit defects. On the other hand, after collecting a large amount of data, the monitoring master station system platform lacks the means to analyze and process the data; therefore, it still needs to rely on manual experience to analyze...

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): G01R31/00G06K9/62
CPCG01R31/00G06F18/23213
Inventor 张炜张玉波黎新邬蓉蓉
Owner ELECTRIC POWER RES INST OF GUANGXI POWER GRID CO LTD
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