基于HHT与BP网络的孤岛检测技术  

Islanding detection based on Hilbert-Huang transform and BP network

作　　者：党震宇 刘智铭[2] 张晓宇 闫娟 刘冰[2] 

机构地区：[1]中国煤炭科工集团沈阳设计研究院,辽宁沈阳110015 [2]东北电力大学自动化工程学院,吉林吉林132012 [3]江西鹰潭供电公司,江西鹰潭335001

出　　处：《电力系统保护与控制》2011年第17期103-108,113,共7页Power System Protection and Control

摘　　要：针对传统被动式孤岛检测方法盲区较大的缺点,提出了一种新的被动式孤岛检测方法。该方法采用希尔伯特-黄变换(HHT)检测公共耦合点(Point of common coupling,PCC)处电压(Vpcc)波形的频谱特征和奇异点出现的时刻,当奇异点出现后,经一个延迟再启动BP网络,BP网络通过识别当前Vpcc频谱所属类别的方式来判断是否出现孤岛现象。在考虑负荷变动、电网电压波动等多种扰动对孤岛检测的影响的基础上做了仿真实验。结果表明:该方法的检测盲区很小,且检测时间符合IEEEStd.2000-929标准的规定值,具有很高的准确性和可靠性。Traditional passive islanding detection method has a large blind area, thus a new passive islanding detection method is proposed. The method uses the Hilbert - Huang Transform （HHT） to detect the frequency spectrum characteristics of the voltage （Vpcc） waveform at the point of common coupling （PCC） and the time when singularity occurs. When the singularity appears, the BP network is started after a delay, which by identifying the current frequency spectrum category of Vpcc determines whether there is an island phenomenon. In consideration of the effects of load changes, voltage fluctuations and other disturbances on the island testing, simulation experiments are conducted. The results show that this method has small blind area, and the detection time meets the specified value of IEEE Std. 2000-929 standards, with high accuracy and reliability.

关 键 词：分布式发电系统 孤岛检测 HHT BP网络 模式识别 奇异点检测 

分 类 号：TM711[电气工程—电力系统及自动化] TM61