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

Power system overvoltage classification method based on sparse autocoder

A sparse auto-encoder, power system technology, applied in instrument, signal pattern recognition, character and pattern recognition and other directions, can solve problems such as poor generalization and long time

Inactive Publication Date: 2016-03-23
TSINGHUA UNIV
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although many feature extraction and classification methods have been proposed in the existing methods, the process of artificial feature design usually takes a long time to carry out, and the generalization is poor when dealing with different types of overvoltages.

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
  • Power system overvoltage classification method based on sparse autocoder
  • Power system overvoltage classification method based on sparse autocoder
  • Power system overvoltage classification method based on sparse autocoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The method for classifying overvoltage characteristics of a power system based on a sparse autoencoder proposed by the present invention will be described in detail below through an embodiment.

[0034] The waveform data used in this embodiment includes four types of ferroresonant overvoltage waveforms, and the four categories are fundamental frequency, two-frequency, three-frequency and chaotic ferroresonant overvoltage. This example is intended to illustrate the method proposed in the present invention and does not imply that the method is limited to the identification and classification of this type of overvoltage. The classification method of this embodiment specifically includes the following steps:

[0035] Step 1. Acquisition and preprocessing of voltage and current waveform data when overvoltage occurs:

[0036] Step 1.1 Obtain the voltage and current waveform data when overvoltage occurs in the power system, set the length of the waveform data, and generate a ...

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 power system overvoltage classification method based on a sparse autocoder, and belongs to online monitoring technology in the electrical field. The method comprises the following steps: obtaining a data set composed of waveform data, carrying out standard preprocessing on all waveforms in the data set to limit the data amplitudes of the waveforms between [0.1, 0.9], dividing the preprocessed waveform data set into a training sample set and a test sample set, extracting the features of the training sample set by using the sparse autocoder, and finally classifying the extracted features of the waveform data by using a multivariate logistic regression classifier. The method is used for automatically extracting the features from a large amount of monitored transient voltage and transient current signals in the case of overvoltage by using the sparse autocoder algorithm and classifying the overvoltage by using the features to accelerate the removal and recovery of faults, so as to help to improve the security and reliability of the power system.

Description

technical field [0001] The invention belongs to the online monitoring technology in the field of electric engineering, and in particular relates to a method based on a sparse autoencoder algorithm to realize overvoltage feature extraction and classification by monitoring voltage or current waveforms in a power system. Background technique [0002] Various types of overvoltages will appear during the operation of the power system, which threatens its operational reliability and safety. The existence of these overvoltages is quite unfavorable for occasions with high power quality requirements, and may cause damage to system insulation or equipment safety, and even cause chain accidents. With the development of smart grid, the voltage and current waveform data collected in the power system have increased greatly, and the accurate automatic classification of overvoltage can be realized, which can significantly reduce the workload of relevant staff to sort out various types of ov...

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
IPC IPC(8): G06K9/00
CPCG06F2218/02G06F2218/12
Inventor 何金良陈坤金胡军余占清
Owner TSINGHUA UNIV
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