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

CNN-based rapid identification method for oscillation type of power system

An oscillation type, power system technology, applied in neural learning methods, electrical components, circuit devices, etc., can solve the problem of insufficient consideration of the non-stationary characteristics of the measured oscillation signal, and achieve the effect of fast identification

Pending Publication Date: 2021-01-08
STATE GRID SICHUAN ECONOMIC RES INST
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these studies all have the defect of insufficient consideration of the non-stationary characteristics of the measured oscillation signal.

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
  • CNN-based rapid identification method for oscillation type of power system
  • CNN-based rapid identification method for oscillation type of power system
  • CNN-based rapid identification method for oscillation type of power system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0105]In order to verify whether the algorithm can identify the new oscillation mode superimposed in the oscillation process of the system, the following ideal oscillation test signal is constructed:

[0106]

[0107]In formula (10), ε(t) represents a step function, and η(t) represents a noise signal.

[0108]The oscillating signal image is asFigure 4 As shown, the signal length is 2s, and the signal-to-noise ratio SNR=10dB. 1s ago, the signal contains two modes, where the frequency f1=0.84Hz, f2=1.21Hz, which belongs to low frequency oscillation. When t=1s, introduce a new oscillation mode, the frequency f3=8.8Hz, belongs to the subsynchronous oscillation, so the oscillation signal after 1s contains both low frequency oscillation and subsynchronous oscillation.

[0109]Step 7: Obtain samples of the oscillation signal to be tested through the sliding time window. The length of the sliding window is 1s, the sliding interval is 0.5s, and the sampling frequency is 400Hz. In order to identify the m...

Embodiment 2

[0115]In order to verify the actual identification effect of the present invention, a piece of oscillating signal measured data is obtained from the power system. Such asFigure 5As shown, the oscillation signal of this segment is excited by a small disturbance, and the time is located at 4s. In order to identify the type of oscillation excited by the disturbance, the data after the end of the disturbance is intercepted as the oscillation signal to be measured in this embodiment.

[0116]Step 7: Obtain samples of the oscillation signal to be tested through the sliding time window. The length of the sliding window is 1s, the sliding interval is 0.5s, and the sampling frequency is 400Hz. In this embodiment, after the disturbance ends, two segments of signals are taken as identification objects, which are 4-5s and 6-7s respectively, to verify whether the oscillation type will change.

[0117]Step 8: Process the oscillation signal to be measured and input it into the CNN model, and analyze the...

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 CNN-based power system oscillation type rapid identification method, and provides a power system oscillation type rapid identification method with accurate analysis, which comprises the following steps: generating power system oscillation sample data according to an EDSs mathematical model, and carrying out preprocessing operation on the oscillation sample data by adopting tiling and zero filling algorithms; determining a classification criterion according to identification requirements, and dividing and marking the oscillation sample data of the power system according to the classification criterion for subsequent network training and testing; building a CNN model, inputting a training sample for network training, and determining whether the network training is completed or not through testing the classification accuracy of the sample; inputting an oscillation signal to be measured into the CNN through sliding window sampling, and completing the identification of the oscillation type of the power system through output analysis. The method has the advantages of effectiveness, feasibility and the like for quickly identifying the oscillation type of a powersystem.

Description

Technical field[0001]The invention relates to the technical field of power system stability and control, and in particular to a method for quickly identifying the type of power system oscillation based on a convolutional neural network (CNN).Background technique[0002]Since the birth of the power system, oscillation research has become one of the important studies related to the dynamic performance and stability of the power system. After years of research, the characteristics of low frequency oscillation (LFO) and sub-synchronous oscillation (SSO) in traditional power systems have been fully revealed. Their common feature is dominated by rotating units with larger physical inertia, especially large synchronous generator sets. However, due to the rapid development of renewable energy, such as solar energy, wind energy, geothermal energy, biomass energy, etc., a large number of new energy grid-connected power generation equipment is connected to the grid through power electronic inver...

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): G06K9/00G06N3/04G06N3/08H02J3/00
CPCG06N3/08G06N3/084H02J3/002H02J2203/20G06N3/045G06F2218/08G06F2218/12
Inventor 魏俊叶圣永张文涛刘旭娜刘立扬韩宇奇李达赵达维龙川刘洁颖
Owner STATE GRID SICHUAN ECONOMIC RES INST
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