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

Qualitative Analysis Method of Influencing Factors of Circuit Breaker Fault Based on Data

A technology of influencing factors and qualitative analysis, applied in special data processing applications, instruments, design optimization/simulation, etc., can solve problems such as the stability verification of circuit breaker failures with unknown causes of qualitative analysis, and achieve extended iterative computing capabilities and approximation accuracy. High, avoid the effect of dimensional disaster

Active Publication Date: 2020-09-04
无锡启工数据科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention is aimed at the analysis of current circuit breaker failure influencing factors, and proposes an efficient, accurate and comprehensive data-based qualitative analysis method for circuit breaker failure influencing factors, which is used to solve the problem of unknown cause of existing circuit breaker failure and a qualitative analysis model The question of stability verification

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
  • Qualitative Analysis Method of Influencing Factors of Circuit Breaker Fault Based on Data
  • Qualitative Analysis Method of Influencing Factors of Circuit Breaker Fault Based on Data
  • Qualitative Analysis Method of Influencing Factors of Circuit Breaker Fault Based on Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] At present, the cause analysis of switchgear failures in the power grid industry is mainly based on manual experience, which is highly subjective, has large errors, lacks pertinence in maintenance, and insufficient utilization of equipment information and fault data. The preprocessing part process is too simple to deal with high-dimensional data characteristics, and the stability of the analysis model is insufficient, and there is too little work in the verification stage, which is not conducive to the expansion of data, and the results are not objective and accurate enough.

[0026] Aiming at the problems of fault data processing, analysis model construction and model verification in the existing circuit breaker fault cause analysis method, the present invention proposes a data-based qualitative analysis method for circuit breaker fault influencing factors. For the main process, see figure 1 , mainly including the preprocessing of fault data, the construction and verifi...

Embodiment 2

[0040] The data-based qualitative analysis method of circuit breaker fault influencing factors is the same as embodiment 1, and the Gaussian mixture model described in step (3) of the present invention is mainly to provide a reasonable continuous attribute discretization method to adapt to the characteristics of switchgear fault data, and to ensure The accuracy of CMAR classification, the Gaussian mixture model believes that the probability density function curve of the data is obtained by mixing and weighting multiple single Gaussian distributions.

[0041] (3.1) Suppose a set of vector points x i (i=1,2...n'), a total of n' observations, the distribution of this group of points is composed of K Gaussian distribution mixture, which means that the sample points are discretized into K intervals during the discretization process, where the Gaussian mixture The definition of the model is:

[0042]

[0043] where π k ∈[0,1], Indicates the influence factor of each Gaussian d...

Embodiment 3

[0054] The qualitative analysis method of data-based circuit breaker fault influencing factors is the same as that of embodiment 1-2, and the fault data reduction described in the step (4) of the present invention is to calculate the information gain rate of each attribute, and perform sorting selection, information gain The specific calculation formula of the rate is as follows:

[0055]

[0056] In the formula, A represents an attribute, Gain(A) represents the information gain of attribute A, and SplitInfo A (S) represents the information generated after the attribute A in the dataset is divided.

[0057] The formula for calculating the information gain Gain(A) is as follows:

[0058]

[0059] Intrinsic information value SplitInfo A (S) The calculation formula is as follows:

[0060]

[0061] Among them, Info(S) and Info A (S) represent the entropy values ​​before and after the attribute division of the data set S, respectively, pi Indicates that any tuple in S ...

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 data-based qualitative analysis method for circuit breaker fault influencing factors, which solves the problems of insufficient utilization of existing circuit breaker fault data, too subjective fault cause positioning, insufficient stability of qualitative analysis models, and the like. The invention finds the key influencing factors of various faults of the circuit breaker by mining and analyzing the fault data of the circuit breaker. The implementation steps include: defining the original fault data set; fault data cleaning; fault data transformation; Influencing factors of various faults of circuit breakers. The present invention uses a supervised learning algorithm CMAR to model, and as the amount of data increases, the accuracy of the model will be continuously improved. At the same time, ten times of ten-fold cross-validation ensures the robustness of the qualitative analysis model and can effectively analyze the influencing factors of circuit breaker failures.

Description

technical field [0001] The invention belongs to the technical field of power equipment application, and mainly relates to the qualitative analysis and excavation of circuit breaker failure influencing factors, specifically a data-based qualitative analysis method of circuit breaker failure influencing factors, which is applied to the improvement of circuit breaker equipment and its operation Maintenance provides a reference basis. Background technique [0002] As the country's economic development has entered a new normal, electricity has become the driving force for the development of all walks of life, and people have put forward higher demands for uninterrupted supply of electricity. Due to various potential and complex factors, power transmission and distribution failures often occur during the power supply process, which will not only cause serious damage to economic development, but also affect industrial production efficiency and people's quality of life. How to ensu...

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): G06F30/20G06K9/62
CPCG06F30/20G06F18/285G06F18/214G06F18/24
Inventor 孔宪光黄小瑜常建涛王佩杨挺
Owner 无锡启工数据科技有限公司
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