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

A method and system for early diagnosis and early war of transformer fault

A transformer fault and early diagnosis technology, applied in prediction, instrumentation, calculation models, etc., can solve problems such as outliers, data objects not assigned to a certain class, etc., and achieve the effect of improving efficiency

Active Publication Date: 2019-01-15
NANJING NARI GROUP CORP +1
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Although the FCM clustering algorithm is very mature in theory and easy to use, it also has an obvious shortcoming, that is, the user must give the number K of clusters to be generated in advance. In many cases, the transformer fault we face Data is a dynamic data set, and the number of clusters is not constant, so FCM encounters bottlenecks in monitoring data processing and analysis
[0005] There is another difficult problem in the traditional ant colony clustering algorithm - the outlier problem. The main reason is that at the end of the algorithm, there are some free data objects that are not assigned to a certain class, including when the algorithm ends. The data objects that are burdened and the data objects that are forced to drop during some algorithm iterations

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 method and system for early diagnosis and early war of transformer fault
  • A method and system for early diagnosis and early war of transformer fault
  • A method and system for early diagnosis and early war of transformer fault

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] If the distance between two classes is the smallest, then the two classes can be considered to be aggregated into one class. And each class is an area. When calculating the distance between classes, the distance between the center points of the two classes is calculated. The distance between the two classes is the smallest and the two classes can be merged, namely:

[0075] In S4, merging the classes with high similarity and outliers in the clustering results includes:

[0076] S411, calculating the distance D between each type and each outlier point and the center point of other adjacent classes or outlier points in the results of the classic ant colony clustering algorithm of S3;

[0077] S412, setting the minimum class number threshold, if the total number of current class and outlier points is greater than the minimum class number threshold, then merge the two classes or two outlier points or classes and outlier points with the smallest distance, and recalculate Fo...

Embodiment 2

[0080] In order to speed up the rapid diffusion of clusters from the high-density area to the outside, the class merging algorithm in this embodiment is: arrange all the distances from small to large, when the distance D i and the previous distance D i-1 When the ratio of is less than the threshold σ, the distance D i as with D i The two types of related merging ties. which is:

[0081] In S4, merging the classes with high similarity and outliers in the clustering results includes:

[0082] S421, calculating the distance D between each type and each outlier point and other adjacent classes or outlier points in the result of the S3 classic ant colony clustering algorithm;

[0083] S422. Sorting the calculated multiple distances D according to their size;

[0084] S423, calculate any distance D i The ratio between the adjacent and smaller distance, if the ratio is less than the preset threshold σ, the distance D i The corresponding two classes or two outliers or classes a...

Embodiment 3

[0094] This embodiment is a specific implementation of steps S3 and S4, using the merging algorithm described in Embodiment 1, and its pseudocode is as follows:

[0095] ①In the initialization algorithm, the number of ants m, the number of data objects n, the maximum number of iterations T, the grid side length Z, the local side length s and other related parameters; the more the number of ants, the higher the clustering efficiency, and the object That is, the transformer monitoring data; the specific relevant parameters are as follows:

[0096] Table 1 Algorithm related parameters

[0097]

[0098]

[0099] ② Perform data preprocessing on the fault gas characteristic data;

[0100] ③ Randomly project data objects and ants into a two-dimensional grid, and only one object is allowed in a grid;

[0101] ④Repeat and iterate the following process:

[0102] For t=1 to T do{

[0103] For i=1 to m{

[0104] Calculate the number of data objects in the neighborhood of ant i wi...

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 transformer fault early diagnosis and early warning method and system, comprising: S1, acquiring the current monitoring data of the transformer and the historical monitoringdata of known fault types; S2, standardizing the acquired data; 3, clustering the standardized eigenvalue by using the classical ant colony clustering algorithm; S4, merging the outliers and the clusters with high similarity in the clustering result as the final clustering result; S5, searching the cluster position where the current monitoring data is located, and judging the fault type corresponding to the current monitoring data according to the fault type to which most of the fault data in the corresponding cluster belong; S6, outputting the judgment result of the fault type. The inventiondynamically analyzes the gas characteristic data of the transformer fault based on the clustering algorithm, so as to accurately judge the health condition of the equipment and early warn the equipment fault.

Description

technical field [0001] The invention relates to the technical field of transformer fault diagnosis, in particular to a transformer fault early diagnosis and early warning method and system. Background technique [0002] With the rapid development of my country's power industry, the demand for electricity has also shown a rapid growth trend. Since 2009, the State Grid Corporation of China has proposed a smart grid development strategy. Ensuring the safe and reliable operation of intelligent substations is the key to realizing the stable operation of the entire smart grid. One of the main conditions of the intelligent power transformer, and the intelligent power transformer is an important part of the intelligent substation, so the timely and reliable diagnosis of the potential failure of the intelligent power transformer to ensure the safe, stable and economical operation of the power grid. [0003] At present, fault diagnosis methods based on various clustering algorithms hav...

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): G06Q10/00G06Q10/04G06N3/00G06F16/28
CPCG06N3/006G06Q10/04G06Q10/20
Inventor 李冰郭壁垒姜晓程潇黠彭文才孙延岭熊光亚潘伟峰姜鑫景波云徐高志罗孝兵华涛李桂平
Owner NANJING NARI GROUP CORP
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