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

Harmonic source identification method based on weighted regularization extreme learning machine

An extreme learning machine and identification method technology, which is applied in the field of harmonic source identification based on weighted regularization extreme learning machine, can solve the problems of difficult to accurately obtain power system network parameters and ensure the accuracy of positioning.

Pending Publication Date: 2019-11-12
ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional harmonic source identification method is easily affected by factors such as changes in the characteristics of the load itself and the harmonic characteristics of adjacent buses, and it is difficult to accurately obtain the network parameters of the power system.
When the distribution network line parameters are unknown, it is difficult to ensure the positioning accuracy by using the traditional harmonic source location 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
  • Harmonic source identification method based on weighted regularization extreme learning machine
  • Harmonic source identification method based on weighted regularization extreme learning machine
  • Harmonic source identification method based on weighted regularization extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Below in conjunction with accompanying drawing, example is described in detail, the harmonic source identification flow chart of WRELM estimator of the present invention is as follows figure 1 As shown, the specific steps are as follows:

[0030] Step S1: the optimal configuration method of the distribution network monitoring device. by figure 2 Taking IEEE14 node topology diagram as an example, the specific process is as follows: a) Objective function. In order to reduce the investment cost, the least measuring devices should be used to make the system globally observable, then the objective function J is: n i Indicates the situation of installing nodes in the system, when η i =1, it means that node i is equipped with a measuring device, when η i =0, it means that no measuring device is installed on node i; N is the total number of nodes in the network. b) Constraints. In order to ensure the overall observability of the system, at least one measuring device at...

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 harmonic source identification method based on a weighted regularization extreme learning machine, and the method comprises the steps: carrying out the optimal configurationof measurement nodes of a power distribution network through employing a network topology method, and determining the number and installation positions of monitoring equipment; correspondingly forminga data pair according to the fundamental voltage amplitude, the harmonic voltage amplitude, the phase and the position vector of the bus where the harmonic source is located, which are obtained fromthe monitoring node, and forming a training data set and a test set of the harmonic source positioning estimator; and optimizing the activation function of the weighted regularization extreme learningmachine positioning estimator and the number of neurons in a hidden layer; and constructing a harmonic source positioning estimator by taking the amplitude and the phase vector of the obtained harmonic voltage as the input of a harmonic source positioning estimator model and taking the bus position vector of the corresponding harmonic source as the output, and identifying the harmonic source in the system.

Description

technical field [0001] The present invention relates to the technical field of harmonic source identification, in particular to a harmonic source identification method based on a Weighted and regularization extreme learning machine (WRELM). Background technique [0002] With the advancement of the Global Energy Internet, the harmonics generated by a large number of power electronic equipment are injected into the grid with the access of distributed power sources, and the proportion of nonlinear loads has also increased significantly. The resulting harmonics The pollution problem is getting worse. The harmonics generated by the harmonic source in the distribution network not only affect the normal use of electrical equipment, but also cause the reduction of the user's power quality, and even threaten the safe operation of the distribution network in severe cases. Therefore, effectively locating the harmonic source in the power system is not only beneficial to relevant person...

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): G06N3/06G06N3/08H02J3/00G01R23/16
CPCG06N3/08G06N3/061G01R23/16H02J3/00H02J3/01Y02E40/40
Inventor 雷达肖莹常潇李胜文杨超颖樊瑞刘翼肇王锬张敏李慧蓬赵军张世锋杨赟磊徐永海秦本双
Owner ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER
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