姚建刚;郭知非;陈锦攀;

• 1:湖南大学电气与信息工程学院
• 2:广东电网公司电力科学研究院

摘要(Abstract)：

电能质量扰动的分类包括特征向量提取和分类器构建2部分。基于小波和神经网络的分类方法大部分采用小波分解各层的能量分布作为特征向量,用单个神经网络给出分类结果,此类方法构建的分类器性能有待进一步提高。文章构建了一组基于小波变换的特征向量作为分类器的输入。通过基于最小二乘法的策略综合3个相互独立神经网络的输出以得到最后的判别结果。算例表明提出的分类器准确率高,在信噪比20 dB的情况下还可以达到93.18%的准确率。分类器能有效识别电压中断、电压暂降、电压暂升、谐波、振荡暂态和闪变6种常见电能质量扰动。

关键词(KeyWords)： 电能质量;扰动分类;小波变换;反向传播神经网

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 姚建刚;郭知非;陈锦攀;

Email:

DOI: 10.13335/j.1000-3673.pst.2012.05.013

参考文献(References)：

• [1]李智勇,吴为麟,林震宇.基于相空间重构和支持向量机的电能扰动分类方法[J].电力系统自动化,2007,31(5):70-75.Li Zhiyong,Wu Weilin,Lin Zhenyu.A power disturbanceclassification method based on phase space reconstruction and supportvector machines[J].Automation of Electric Power System,2007,31(5):70-75(in Chinese).
• [2]Whei-Min Lin,Chien-Hsien Wu,Chia-Hung Lin.Classification ofmultiple power quality disturbances using support vector machine andone-versus-one approach[C]//International Conference on PowerSystem Technology,Chongqing,China:IEEE,2006,1-8.
• [3]李威,王建赜,冉启文.一种新的电力系统暂态波形检测方法[J].电力系统自动化,2002,26(5):1-4.Li Wei,Wang Jianze,Ran Qiwen.A novel measurement method forpower system transient waveforms[J].Automation of Electric PowerSystem,2002,26(5):1-4(in Chinese).
• [4]Janik P,Lobos T,Schegner P.Classification of power quality eventsusing SVM networks[C]//Eighth IEE International Conference onDevelopments in Power System Protection,Amsterdam,Netherlands:IEE,2004:768-771.
• [5]Ying-tung H,Ying-ming W.Fuzzy power quality indicator[C]//Proceedings of the Sixth International Conference on MachineLearning and Cybernetics,Hong Kong,China:2007:1418-1423.
• [6]Hamzah N,Anuwar FH,Zakaria Z.Classification of transient inpower system using support vector machine[C]//5th internationalcolloquium on signal processing&its applications,Kuala LumpurMalaysia:IEEE,2009:418-422.
• [7]戴铭,何正友,赵静,等.一种小波变换和支持向量机相结合的配电网电容器投切扰动源定位方法[J].电网技术,2010,34(6):198-204.Dai Ming,He Zhengyou,Zhao Jing,et al.A method to locatedisturbance source due to capacitor switching in distribution networkbased on integration of wavelet transform with support vectormachine[J].Power System Technology,2010,34(6):198-204(inChinese).
• [8]张文涛,王成山.基于改进贝叶斯分类法的电能质量扰动分类方法[J].电网技术,2007,31(7):22-25.Zhang Wentao,Wang Chengshan.Power quality disturbanceclassification method based on improved bayes method[J].PowerSystem Technology,2007,31(7):22-25(in Chinese).
• [9]方群会,刘强,周林,等.模式分类方法在电能质量扰动信号分类中的应用综述[J].电网技术,2009,33(1):31-35.Fang Qunhui,Liu Qiang,Zhou Lin,et al.A Survey on Applicationof pattern classification in power quality disturbance signalsclassification[J].Power System Technology,2009,33(1):31-35(inChinese).
• [10]于静文,薛蕙,温渤婴.基于卡尔曼滤波的电能质量分析方法综述[J].电网技术,2010,34(2):97-103.Yu Jingwen,Xue Hui,Wen Boying.A survey on kalman filteringbased methods for power quality analysis[J].Power SystemTechnology,2010,34(2):97-103(in Chinese).
• [11]冯浩,周雒维,刘毅.基于复小波变换的暂态电能质量扰动检测与分类[J].电网技术,2010,34(3):91-95.Feng Hao,Zhou Luowei,Liu Yi.Detection and classification oftransient power quality disturbances based on complex wavelettransform[J].Power System Technology,2010,34(3):91-95(inChinese).
• [12]刘慧芳,陈勇胜,王群,等.基于小波变换和模糊逻辑的暂态电能质量扰动分类[J].电网技术,2008,32(3):84-87.Liu Huifang,Chen Yongsheng,Wang Qun,et al.Classification oftransient power quality disturbances based on wavelet transform andfuzzy logic[J].Power System Technology,2008,32(3):84-87(inChinese).
• [13]何朝辉.基于小波变换和人工神经网络的电能质量扰动分类[D].长沙:湖南大学,2009.
• [14]Santoso S,Powers E J,Grady W M.Power quality disturbancewaveform recognition using wavelet-based neural classifier—Part 1:Theoretical foundation[J].IEEE Trans.on Power Delivery,2000,15(1):222-228.
• [15]Santoso S,Powers E J,Grady W M.Power quality disturbancewaveform recognition using wavelet-based neural classifier—Part 2:Application[J].IEEE Trans.on Power Delivery,2000,15(1):229-235.
• [16]Zhu T X,Tso S K,Lo K L.Wavelet-based fuzzy reasoning approachto power-quality disturbance recognition[J].IEEE Trans.on PowerDelivery,2004,19(4):1928-1935.
• [17]Xinyi Gu,Lo K L.Wavelet transform based fuzzy logic for powerquality classification[C]//Universities Power Engineering Conference(UPEC),2010 45th International.Wales,UK:IEEE,2010:1-6.
• [18]Kocaman C,Usta H,Ozdemir M.Classification of two commonpower quality disturbances using wavelet based SVM[C]//MELECON 2010-2010 15th IEEE Mediterranean ElectrotechnicalConference.Valleta,Malta:IEEE,2010:587-591.
• [19]Nermeen Tt,Marija I.ANNs based on subtractive cluster feature forclassifying Power Quality[C]//Proceeding of North American PowerSymposium,Alberz,Canada:IEEE,2008(11):1-7.
• [20]肖湘宁.电能质量分析与控制[M].北京:中国电力出版社2008:35-44.
• [21]Masoum M A S.Jamali S,Ghaffarzadeh N.Detection andclassification of power quality disturbances using discrete wavelettransform and wavelet networks[J].IET Sci.Meas.Technol,2010,4(4):193-205.
• [22]Przemys aw J,Tadeusz L.Automated classification of power-qualitydisturbances using SVM and RBF networks[J].IEEE Trans.on PowerDelivery,2006(3):1663-1669.