A Dataset Oversampling Method for Circuit Breaker Imbalance Monitoring

A monitoring data and oversampling technology, applied in the field of machine learning, can solve the problem of unbalanced monitoring data categories, and achieve the effect of supplementing effective classification information, increasing the number of samples, and avoiding bias.

Active Publication Date: 2022-07-19
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present invention provides a circuit breaker imbalance monitoring data set oversampling method, which is used to solve the problem of category imbalance of circuit breaker monitoring data in the prior art through a new machine learning method

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 Dataset Oversampling Method for Circuit Breaker Imbalance Monitoring
  • A Dataset Oversampling Method for Circuit Breaker Imbalance Monitoring
  • A Dataset Oversampling Method for Circuit Breaker Imbalance Monitoring

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0102] Collect the circuit breaker imbalance monitoring dataset. The vibration signal during the closing process of the circuit breaker is used as the monitoring signal, and the vibration signals in different states are collected to form an unbalanced data set S={xi,yi}, where x i is the sample data, y i for x i the corresponding status category. Specifically, 60 groups of vibration signals under normal conditions were collected, and 30 groups of vibration signals were collected under the fatigue of closing spring (fault 1), the loosening of base screws (fault 2), and the fatigue of opening spring (fault 3). An imbalanced dataset with a class imbalance ratio of 2:1 is established. Extract the piecewise energy entropy of the vibration signal, the characteristics are as attached Figure 5 shown.

[0103] The normal and fault states are sorted in descending order by their number of samples. The reordered state sequence is, normal state, fault 1, fault 2, fault 3. The norma...

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 an oversampling method for a circuit breaker unbalance monitoring data set, which includes the following contents: collecting the circuit breaker unbalance monitoring data, and obtaining a monitoring sample data set S; The number of samples, sort the state categories; take the state category with the largest number of samples as the majority category, and the remaining categories as the minority category; perform oversampling on the minority categories in sequence until all the minority categories are oversampled ; The new samples collected by each oversampling are added to the current monitoring sample data set to generate a new monitoring sample data set, and the next minority category of oversampling is performed according to the new monitoring sample data set.

Description

technical field [0001] The invention relates to the technical field of machine learning, and more particularly to an oversampling method for a circuit breaker imbalance monitoring data set. Background technique [0002] In recent years, the intelligent fault diagnosis of circuit breakers based on machine learning technology has received extensive research and attention. The diagnosis method can automatically diagnose whether the circuit breaker is faulty according to the monitored signal, and give an early warning. The core of this diagnostic method relies on a satisfactory monitoring dataset to train a diagnostic model to ensure high diagnostic performance. A satisfactory dataset means not only sufficient monitoring data and less noise, but also a comparable number of samples for different state categories. [0003] However, in practical applications, the high-voltage circuit breaker is in normal operation for most of its entire life cycle, so there is a lack of a suffici...

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): G06K9/00G06K9/62G06N20/00G01R31/327
CPCG06N20/00G01R31/327G06F2218/04G06F2218/12G06F18/24147G06F18/214
Inventor 万书亭陈磊李少鹏豆龙江
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap