Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine)

A technology of power quality disturbance and classification method, applied in the direction of measuring electrical variables, character and pattern recognition, measuring electricity, etc., can solve the problems of not finding parameters, searching for optimization, etc., to achieve high accuracy, accurate and reliable identification, and improve training speed. The effect of classification accuracy

Inactive Publication Date: 2014-04-23
SHANDONG UNIV OF SCI & TECH
View PDF0 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, at the present stage, the SVM classifier used for the identification and classification of power quality disturbances is all given parameters in terms of parameter selection, and the best method has not been found to optimize the parameters

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 quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine)
  • Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine)
  • Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0023] Such as Figures 1 to 7 As shown, the power quality disturbance identification and classification method based on PSO optimized SVM includes the following steps:

[0024] a. Establish a signal model containing common dynamic disturbance signals. Common disturbance signals include five types of voltage swell signals, voltage sag signals, temporary voltage interruption signals, transient pulse signals and transient oscillation signals. Table 1 shows the five A model of a common dynamic disturbance signal and the corresponding parameter settings.

[0025] Table 1 Five common dynamic disturbance signal models

[0026]

[0027] The disturbance signal is extracted from the input voltage signal by complex wavelet transform, and the disturbance signal is decomposed by multi-scale complex wavelet by constructing the Db4 orthogonal compact sup...

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 power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for an SVM (Support Vector Machine). Detection and positioning are performed on a disturbing signal by use of complex wavelet transform, and a feature vector of dynamic power quality disturbance is effectively extracted; after parameters of the SVM are optimized by virtue of a PSO algorithm, automatic recognition and classification are performed on the dynamic power quality disturbance according to an extracted feature signal; complex wavelet transform can be used for overcoming the defect that original wavelet change can be used for only analyzing signal amplitude frequency, meanwhile resolving the amplitude frequency and phase frequency characteristics of signals, providing multiple types of combination information and more accurately recognizing most common dynamic disturbing signals in a power system. Compared with a traditional method of recognizing an interference signal by use of a neural network and the like, the method disclosed by the invention is accurate and reliable in recognition and higher in accuracy rate.

Description

technical field [0001] The invention belongs to the field of power system power quality analysis technology research, in particular to a power quality disturbance identification and classification method based on PSO optimized SVM. Background technique [0002] The power quality (Power Quality, PQ) problem has aroused widespread concern of electric power industry workers. With the development of the field of industrial control in the direction of nonlinearity, network integration, and large-scale, and the continuous increase of nonlinear load capacity such as large-scale rectification equipment and frequency conversion speed control equipment in the system, the power quality of multi-grid power supply has caused serious pollution and seriously affected the power supply. The quality of electric power supplied by enterprises, and the accurate identification and classification of power quality disturbances are the prerequisites for ensuring the safe and economical operation of ...

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): G01R31/00G06K9/62
Inventor 杨宁霞
Owner SHANDONG UNIV OF SCI & TECH
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