Application of Improved PNN Neural Network in Sub-synchronous/Super-synchronous Oscillation Monitoring of Power System

ZHAO Yan; ZHAO Qi; ZHANG Jinsong; NIE Yonghui

doi:10.14044/j.1674-1757.pcrpc.2022.05.012

您当前的位置：

首页 >

文章列表页 >

Application of Improved PNN Neural Network in Sub-synchronous/Super-synchronous Oscillation Monitoring of Power System

更新时间：2024-09-21

- Application of Improved PNN Neural Network in Sub-synchronous/Super-synchronous Oscillation Monitoring of Power System
- POWER CAPACITOR & REACTIVE POWER COMPENSATION Vol. 43, Issue 5, Pages: 76-83(2022)
- 作者机构：
  
  1. 东北电力大学输变电技术学院
  2. 东北电力大学电气工程学院
- 作者简介：
- 基金信息：
- DOI：10.14044/j.1674-1757.pcrpc.2022.05.012
  CLC： TM712;TP183
- Published：2022，
- 稿件说明：
移动端阅览
ZHAO YAN, ZHAO QI, ZHANG JINSONG, et al. Application of Improved PNN Neural Network in Sub-synchronous/Super-synchronous Oscillation Monitoring of Power System. [J]. Power capacitor & reactive power compensation, 2022, 43(5): 76-83.
DOI：

ZHAO YAN, ZHAO QI, ZHANG JINSONG, et al. Application of Improved PNN Neural Network in Sub-synchronous/Super-synchronous Oscillation Monitoring of Power System. [J]. Power capacitor & reactive power compensation, 2022, 43(5): 76-83. DOI： 10.14044/j.1674-1757.pcrpc.2022.05.012.

摘要

电力系统次/超同步振荡的常用的检测（标题用的是监测，让作者再看看）方法是：首先对实测数据进行滤波得到次/超同步振荡信号分量，再根据对各分量信号进行参数辨识的结果，来确认是否发生次/超同步振荡。这样，振荡判断的准确性就受到滤波器的效果和参数辨识方法准确性的双重影响。为了解决上述问题，提出将同步压缩小波变换（SST）和深度学习方法—概率神经网络（PNN神经网络）相结合应用于次/超同步振荡的监测。首先，用SST变换替代传统滤波器实现滤波的功能，得到次同步频率、工频频率和超同步频率的信号分量。然后，不再进行参数辨识，而是直接将得到的各类信号分量数据直接交于PNN神经网络进行分类，直接挖掘次/超同步振荡数据的特点，达到在线监测的目的。仿真和实例均验证了方法的可靠性。

Abstract

The common detection method of sub-synchronous/super-synchronous oscillation is that the actually measured data is filtered firstly to obtain the sub/super-synchronous oscillation signal component.Then

the occurrence of the sub/super-synchronous oscillation is defined in accordance with the parameter identification result of each component signal. Thus

the accuracy of oscillation judgment is affected by both the effect of filter and the accuracy of parameter identification method.For solving above problem

a deep learning method

probabilistic neural network（PNN）combined with SST filtering is proposed to monitor the sub/super-synchronous oscillations of power systems. First

SST transform is used to replace traditional filter to achieve filtering function and the signal component of sub-synchronous frequency

power frequency and super-synchronous frequency are obtained. Then

parameter identification is not performed anymore

but the obtained each type of signal component is submitted to PNN neural network directly for classification

and the characteristics of sub/super-synchronous oscillation data are directly mined to achieve the purpose of online monitoring. The reliability of the method is verified by simulation and example.

关键词

次同步振荡超同步振荡深度学习PNN神经网络同步压缩小波变换(SST)在线监测

Keywords

sub-synchronousoscillationsuper-synchronousoscillationdeeplearningPNNneuralnetworksynchronous compression wavelet transform（SST）on-line monitoring

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application Study of the On-line Monitoring System of Shunt Capacitors

Research of On-Iine Monitoring Methods of Dielectric Loss for Capacitive Equipment and Some Suggestions

On-line Monitoring and Early Warning of the Shunt Capacitor Based on SCADA

Research of On-line Monitoring System for High Voltage Shunt Capacitors

Intelligent On-line Monitoring of Power Capacitor Equipment in the Substation

Related Author

倪学锋

严飞

陆培钧

黄松波

金向朝

Xiao Shi-wu

WANG Rui-chuang

XI Zhao-hui1

Related Institution

武汉高压研究院

广东电网公司佛山供电局

Sifang Institute of North China Electric Power University

Chongqing Municipal Urban Power Supply Bureau

State Key Laboratory of Power Transmission Equipment & System Security and New Technology,Chongqing University

⁰