基于小波变换和神经网络的孤岛检测技术.pdfVIP

第 34 卷 第 4 期 中 国 电 机 工 程 学 报 Vol.34 No.4 Feb.5, 2014 2014 年 2 月 5 日 Proceedings of the CSEE ©2014 Chin.Soc.for Elec.Eng. 537 DOI ：10.13334/j.0258-8013.pcsee.2014.04.004 文章编号：0258-8013 (2014) 04-0537-08 中图分类号：TM 46 基于小波变换与神经网络的孤岛检测技术 1 1 2 谢东 ，张兴 ，曹仁贤 (1．合肥工业大学电气与自动化工程学院，安徽省 合肥市 230009 ； 2．阳光电源股份有限公司，安徽省 合肥市 230009) Islanding Detection Based on Wavelet Transform and Neural Network 1 1 2 XIE Dong , ZHANG Xing , CAO Renxian (1. School of Electric and Automatic Engineering, Hefei University of Technology, Hefei 230009, Anhui Province, China; 2. Sungrow Power Supply Co. Ltd, Hefei 230009, Anhui Province, China) ABSTRACT: The function of islanding detection is required 所提供的孤岛检测法没有向控制信号中加入扰动量，因而不 for the grid-connected inverter-based distributed generation 会对电能质量产生不良影响，克服了主动式孤岛检测方法的 system due to safety reasons and to maintain the quality of 不足，并具有很高的准确性与可靠性。 power supply. Passive methods have a large non detection zone 关键词：分布式发电；孤岛检测；小波变换；神经网络；特 and the detecting time is long, while active schemes have 征量 negative influence on power quality, so a novel passive islanding detection method was proposed. In this method, 0 引言 wavelet transform was adopted to extract feature vectors from 基于逆变器的分布式发电系统，在主电网因故 the voltage of point of common coupling (PCC) point and the output current of inverter, a