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

A Dynamic Threshold Setting Method for Power Equipment Based on Historical Data Clustering

A technology of electric equipment and historical data, applied in the direction of electric digital data processing, special data processing applications, instruments, etc., can solve the problems that the changes cannot be effectively synchronized, and cannot accurately reflect the dynamic equipment operating status, etc., to achieve the effect of improving efficiency

Active Publication Date: 2017-09-26
KUNMING UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The threshold setting of the existing power equipment operating status division is mostly set directly according to the initial information of the power equipment (such as general value, regulation value, experience value, pre-test value). Once set, it cannot be changed and cannot accurately reflect the dynamic state. The actual operating status of the equipment, the threshold setting and the actual operating changes cannot be effectively synchronized

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 Dynamic Threshold Setting Method for Power Equipment Based on Historical Data Clustering
  • A Dynamic Threshold Setting Method for Power Equipment Based on Historical Data Clustering
  • A Dynamic Threshold Setting Method for Power Equipment Based on Historical Data Clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Embodiment 1: Taking the online monitoring of transformers as an example, the monitored quantities are the gas and components in the transformer oil, and the partial discharge quantity. The two-dimensional coordinates associated with each two quantities are established based on the simultaneous correlation between the monitored quantities, and the monitored quantities are projected In two-dimensional space, different state regions are divided. Refer to the historical data of the transformer (nameplate value, regulation value, preventive test value) to define four partitions of the transformer operating state (such as figure 1 shown).

[0045] Based on the principle of probability distribution, the historical data of transformers (including at least the data of generalized value, regulation value, experience value and pre-test value) are used to determine the original boundary and select the threshold for the four state partitions. The preliminary boundary of area A can...

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 relates to a dynamic threshold setting method for power equipment based on historical data clustering. When processing and applying online monitoring data of substation equipment, based on the collected historical data, the power equipment is preliminarily divided according to the range of numerical distribution space For different state spaces of operation, based on the standards defined by relevant operation specifications of power equipment and the distribution range of historical data, the determination of the original boundary of the state space and the selection of threshold values ​​are carried out; the monitoring data is initially clustered according to the area where the data appears, and the history The state space determined by the data is based on clustering, distinguishing and matching the monitoring data and the state space range according to the degree of proximity, forming the numerical range of the monitoring data in different states of equipment operation; in the continuous supplementation and differentiation and matching of equipment operation monitoring data, According to the probability distribution range of data occurrence, its boundary is gradually corrected, and the dynamic power equipment operation status threshold setting is completed to form the basis for judging the equipment operation status.

Description

technical field [0001] The invention relates to a method for setting dynamic thresholds of power equipment based on historical data clustering, and belongs to the technical field of power system equipment monitoring. Background technique [0002] With the integration and development of smart grid and Internet of Things technology at all levels, Internet of Things technology has gained more and more applications in the online monitoring of substations. The online monitoring of power equipment based on the Internet of Things technology generates massive heterogeneous data. Based on the analysis and processing of such data, the operating status of the equipment is judged to form the entire process of operation management of the equipment. Different operations of the equipment are required. The state is divided into regions. The threshold setting of the existing power equipment operating status division is mostly directly set according to the initial information of the power eq...

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): G06F19/00
Inventor 束洪春曹立平董俊
Owner KUNMING UNIV OF SCI & TECH
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