Power quality disturbance identification method based on online weighted SVM training

A technology of power quality disturbance and identification method, which is applied in the direction of electrical components, circuit devices, AC network circuits, etc. It can solve problems such as over-limit, untimely busbar voltage regulation, and nonlinearity of power system components, so as to reduce the demand for system memory , Accelerate the disturbance identification speed, improve the speed and accuracy

Inactive Publication Date: 2017-09-01
EAST CHINA JIAOTONG UNIVERSITY
View PDF1 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0018] ①Nonlinear problems in power system components
[0026] ① Failure to establish a timely automatic control mechanism for bus voltage in substations
Untimely regulation of the busbar is the main cause of voltage over-limit
[0027] ② Lack of small hydropower grid connection management system
The non-standard connection of small hydropower will lead to the voltage limit of the 35KV and 10KV busbars in the substation
[0028] ③ Unreasonable grid configuration
For example, urbanization has developed rapidly in recent years, and the original suburbs have rapidly developed

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 identification method based on online weighted SVM training
  • Power quality disturbance identification method based on online weighted SVM training
  • Power quality disturbance identification method based on online weighted SVM training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0080] In order to make the objects and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0081] Adaptive technology based on the minimum mean square error algorithm is used to track the input signal by gradually modifying the weight coefficient. Once the statistical characteristics of the input signal change, it can automatically adjust the parameters to make the filter have better noise elimination ability, and More edge information and useful information are kept.

[0082] The input signal x(n) is defined as a one-dimensional time series, g(n) is a structural element, and the length of the structural element g(n) is smaller than the length of the signal x(n). For two structuring elements g1(n) and g2(n), And the length of g1(n)...

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 identification method based on online weighted SVM training. The method comprises: according to different characteristics of common power quality disturbance signals, a mathematical model of the disturbance signals is established; on the basis of the mathematical morphology, a generalized morphological filter of an adaptive LMS algorithm is constructed to carry out denoising processing on a power quality disturbance signal; wavelet transform is carried out to extract energy distribution of different frequency bands of the power quality disturbance signal; a fractal dimension of the power quality disturbance signal is extracted based on a fractal theory and the energy distribution and the fractal dimension form a quantification characteristic index of the disturbance signal; and according to time of power quality disturbance occurrence, disturbance data are assigned with different weights, online training and testing are realized, and identification classification is carried out on power quality disturbance.

Description

technical field [0001] The invention relates to the field of power quality identification, in particular to a power quality disturbance identification method based on online training weighted SVM. Background technique [0002] my country's power system has developed into a time-varying system with multiple variables and multiple objectives. In recent years, due to the profound changes in the power supply, grid and load of the power system, more and more nonlinear, impact and unbalanced loads have been put into use in the power system, such as steelmaking electric arc furnaces, electrified railways, power electronics Devices, etc., lead to a series of power quality disturbance problems such as voltage fluctuations and flicker, harmonics, and system frequency fluctuations. Therefore, the power quality problem has attracted extensive attention. In order to control the occurrence of disturbances and improve power quality, accurate detection and identification of power quality ...

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): H02J3/00
CPCH02J3/00H02J2203/20
Inventor 徐祥征李津
Owner EAST CHINA JIAOTONG UNIVERSITY
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