基于并行隐马尔科夫模型的电能质量扰动事件分类
|
摘要
为满足电能质量扰动准确分类的需求,提出了一种基于极大重叠离散小波变换(MaximalOverlapDiscrete WaveletTransform, MODWT)和并行隐马尔科夫模型(ParallelHiddenMarkovModel, PHMM)的电能质量扰动分类方法。首先利用MODWT提出一种实用的电能质量扰动检测算法,该算法无需设定检测阈值,可准确获取扰动时段的起止时刻。接着提取扰动时段的电压谐波成分并组成特征向量。然后用PHMM分类器对扰动信号进行分类识别。PHMM方法克服了人工神经网络方法收敛性较差、训练时间较长的缺陷,使分类器性能大大提升。通过应用于现场实测扰动数据表明,所提出的方法适用于多种类型的电能质量扰动检测,分类正确率高,训练速度快,具有良好的应用价值。
In order to meet the requirements of accurately classifying power quality disturbances, a method for power quality disturbance classification is proposed based on Maximal Overlap Discrete Wavelet Transform(MODWT) and Parallel Hidden Markov Model(PHMM). Initially, a practical power quality disturbance detection algorithm is proposed by using MODWT. This algorithm can obtain the disturbance beginning and ending time accurately without setting detection threshold, from whose results the voltage harmonic components of power quality disturbance are extracted and used to form feature vector. Then, PHMM, as a classifier, is used to identify power quality disturbances. PHMM method solves the problem of poor convergence and longer training time for Artificial Neural Network(ANN) method, and thus the performance of the classifier is greatly improved. The test results based on power grid field data show that the proposed method is suitable for detecting various types of power quality disturbances, and it is characterized by high recognition correctness and less training time, and it will find extensive application.
In order to meet the requirements of accurately classifying power quality disturbances, a method for power quality disturbance classification is proposed based on Maximal Overlap Discrete Wavelet Transform(MODWT) and Parallel Hidden Markov Model(PHMM). Initially, a practical power quality disturbance detection algorithm is proposed by using MODWT. This algorithm can obtain the disturbance beginning and ending time accurately without setting detection threshold, from whose results the voltage harmonic components of power quality disturbance are extracted and used to form feature vector. Then, PHMM, as a classifier, is used to identify power quality disturbances. PHMM method solves the problem of poor convergence and longer training time for Artificial Neural Network(ANN) method, and thus the performance of the classifier is greatly improved. The test results based on power grid field data show that the proposed method is suitable for detecting various types of power quality disturbances, and it is characterized by high recognition correctness and less training time, and it will find extensive application.
引文
[1]徐文远,雍静.电力扰动数据分析学—电能质量监测数据的新应用[J].中国电机工程学报,2013,33(19):93-101.XUWilsun,YONGJing.Powerdisturbancedata analytics—new application of power quality monitoring data[J]. Proceedings of the CSEE, 2013, 33(19):93-101.
[2]任子晖,刘昊岳,徐进霞.基于小波变换和改进Prony方法的电能质量扰动分析[J].电力系统保护与控制,2016, 44(9):122-128.RENZihui,LIUHaoyue,XUJinxia.Powerquality disturbanceanalysisbasedonwavelettransformand improved Prony method[J]. Power System Protection and Control, 2016, 44(9):122-128.
[3]剧高峰,罗安.离散小波变换用于电能质量扰动数据实时压缩[J].电力系统自动化, 2002, 26(19):61-63.JUGaofeng,LUOAn.DWTapplicationtoreal-time compressionofpowerqualitydisturbancedata[J].AutomationofElectricPowerSystems,2002,26(19):61-63.
[4]李正明,徐敏,潘天红,等.基于小波变换和HHT的分布式并网系统谐波检测方法[J].电力系统保护与控制, 2014, 42(4):34-39.LIZhengming,XUMin,PANTianhong,etal.A harmonic detection method for distributed connected grid systembyusingwavelettransformandHHT[J].Power System Protection and Control, 2014, 42(4):34-39.
[5]张宇辉,陈晓东,王鸿懿.基于连续小波变换的电能质量测量与分类[J].电力自动化设备,2004,24(3):17-21.ZHANGYuhui,CHENXiaodong,WANGHongyi.Continuouswavelet-basedmeasuringandclassification ofshortdurationpowerqualitydisturbance[J].Electric Power Automation Equipment, 2004, 24(3):17-21.
[6]黄建明,瞿合祚,李晓明.基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类[J].电网技术,2016,40(10):3184-3191.HUANG Jianming, QU Hezuo, LI Xiaoming. Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis[J]. Power System Technology, 2016,40(10):3184-3191.
[7]覃星福,龚仁喜.基于广义S变换与PSO-PNN的电能质量扰动识别[J].电力系统保护与控制,2016,44(15):10-17.QINXingfu,GONGRenxi.Powerqualitydisturbances classificationbasedongeneralizedS-transformand PSO-PNN[J].PowerSystemProtectionandControl,2016, 44(15):10-17.
[8]RAHUL, KAPOOR R, TRIPATHI M M. Detection and classificationofmultiplepowersignalpatternswith Volterraseriesandintervaltype-2fuzzylogicsystem[J]Protection and Control of Modern Power Systems, 2017,2(2):92-101. DOI:10.1186/s41601-017-0039-z.
[9]陈伟根,谢波,龙震泽,等.基于小波包能量熵的油纸绝缘气隙放电阶段识别[J].中国电机工程学报,2016,36(2):563-569.CHENWeigen,XIEBo,LONGZhenze,etal.Stage identificationinair-gapdischargeofoil-impregnated paper insulation based on wavelet packet energy entropy[J].Proceedings of the CSEE, 2016, 36(2):563-569.
[10]何巨龙,王根平,刘丹,等.基于提升小波和改进BP神经网络的配电网系统电能质量扰动定位与识别[J].电力系统保护与控制, 2017, 45(10):69-76.HEJulong,WANGGenping,LIUDan,etal.Localization andidentificationofpowerqualitydisturbancein distribution network system based on lifting wavelet and improvedBPneuralnetwork[J].PowerSystemProtection and Control, 2017, 45(10):69-76.
[11]黄建明,李晓明,瞿合祚,等.考虑小波奇异信息与不平衡数据集的输电线路故障识别方法[J].中国电机工程学报, 2017, 37(11):3099-3107.HUANGJianming,LIXiaoming,QUHezuo,etal.Methodforfaulttypeidentificationoftransmissionline considering wavelet singular information and unbalanced dataset[J].ProceedingsoftheCSEE,2017,37(11):3099-3107.
[12]唐贵基,王晓龙.可调品质因子小波变换在滚动轴承微弱故障特征提取中的应用[J].中国电机工程学报,2016, 36(3):746-754.TANGGuiji,WANGXiaolong.Applicationoftunable Q-factor wavelet transform to feature extraction of weak faultforrollingbearing[J].ProceedingsoftheCSEE,2016, 36(3):746-754.
[13]COSTAFB,SOUZABA,BRITONSD.Real-time detectionofvoltagesagsbasedonwavelettransform[C]//TransmissionandDistributionConferenceand Exposition:LatinAmerica,November8-10,2010,Sao Paulo, Brazil:537-542.
[14]COSTAFB,DRIESENJ.Assessmentofvoltagesag indicesbasedonscalingandwaveletcoefficientenergy analysis[J]. IEEE Transactions on Power Delivery, 2012,28(1):336-346.
[15] SANTOSOS,POWERSEJ,GRADYWM.Power quality disturbance waveform recognition using waveletbased neural network classification-part 2:application[J].IEEETransactionsonPowerDelivery,2000,15(1):229-235.
[16]CESARDG,VALDOMIROVG,GABRIELOP.Automaticpowerqualitydisturbancesdetectionand classificationbasedondiscretewavelettransformand artificial intelligence[C]//Transmission and Distribution Conference and Exposition:Latin America, August 15-18,2006, Caracas, Venezuela:1-6.
[17]秦英林,田立军,常学飞.基于小波变换能量分布和神经网络的电能质量扰动分类[J].电力自动化设备,2009, 29(7):64-67.QINYinglin,TIANLijun,CHANGXuefei.Classification ofpowerqualitydisturbancebasedonwaveletenergy distributionandneuralnetwork[J].ElectricPower Automation Equipment, 2009, 29(7):64-67.
[18]管春,周雒维,卢伟国.基于多标签RBF神经网络的电能质量复合扰动分类方法[J].电工技术学报,2011,26(8):198-204.GUANChun,ZHOULuowei,LUWeiguo.Recognition ofmultiplepowerqualitydisturbancesusingmulti-label RBFneuralnetworks[J].TransactionsofChina Electrotechnical Society, 2011, 26(8):198-204.
[19] ABDEL-GALIL T K, EL-SAADANY E F, YOUSSEF A M, et al. Disturbance classification using hidden Markov models and vector quantization[J]. IEEE Transactions on Power Delivery, 2005, 20(3):2129-2135.
[20]朱珂,倪建,刘颖英,等.面向电力扰动数据分析的暂态扰动检测[J].电工技术学报, 2017, 32(3):35-44.ZHUKe,NIJian,LIUYingying,etal.Detecttransient power disturbance for power disturbance data analytics[J].TransactionsofChinaElectrotechnicalSociety,2017,32(3):35-44.
[21]周翔,王丰华,傅坚,等.基于混动理论和K-means聚类的有载分接开关机械状态监测[J].中国电机工程学报, 2015, 35(6):1541-1548.ZHOUXiang,WANGFenghua,FUJian,etal.Mechanical condition monitoring of on-load tap changers based on chaos theory and K-means clustering method[J].Proceedings of the CSEE, 2015, 35(6):1541-1548.
[22] XIE X L, BENI G. A validity measure for fuzzy clustering[J].IEEETransactionsonPatternAnalysis&Machine Intelligence, 1991, 13(13):841-847.
[23]唐飞,王波,查晓明,等.基于双阶段并行隐马尔科夫模型的电力系统暂态稳定评估[J].中国电机工程学报,2013, 33(10):90-97.TANGFei,WANGBo,ZHAXiaoming,etal.Power systemtransientstabilityassessmentbasedontwo-stage parallelhiddenMarkovmodel[J].Proceedingsofthe CSEE, 2013, 33(10):90-97.
[2]任子晖,刘昊岳,徐进霞.基于小波变换和改进Prony方法的电能质量扰动分析[J].电力系统保护与控制,2016, 44(9):122-128.RENZihui,LIUHaoyue,XUJinxia.Powerquality disturbanceanalysisbasedonwavelettransformand improved Prony method[J]. Power System Protection and Control, 2016, 44(9):122-128.
[3]剧高峰,罗安.离散小波变换用于电能质量扰动数据实时压缩[J].电力系统自动化, 2002, 26(19):61-63.JUGaofeng,LUOAn.DWTapplicationtoreal-time compressionofpowerqualitydisturbancedata[J].AutomationofElectricPowerSystems,2002,26(19):61-63.
[4]李正明,徐敏,潘天红,等.基于小波变换和HHT的分布式并网系统谐波检测方法[J].电力系统保护与控制, 2014, 42(4):34-39.LIZhengming,XUMin,PANTianhong,etal.A harmonic detection method for distributed connected grid systembyusingwavelettransformandHHT[J].Power System Protection and Control, 2014, 42(4):34-39.
[5]张宇辉,陈晓东,王鸿懿.基于连续小波变换的电能质量测量与分类[J].电力自动化设备,2004,24(3):17-21.ZHANGYuhui,CHENXiaodong,WANGHongyi.Continuouswavelet-basedmeasuringandclassification ofshortdurationpowerqualitydisturbance[J].Electric Power Automation Equipment, 2004, 24(3):17-21.
[6]黄建明,瞿合祚,李晓明.基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类[J].电网技术,2016,40(10):3184-3191.HUANG Jianming, QU Hezuo, LI Xiaoming. Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis[J]. Power System Technology, 2016,40(10):3184-3191.
[7]覃星福,龚仁喜.基于广义S变换与PSO-PNN的电能质量扰动识别[J].电力系统保护与控制,2016,44(15):10-17.QINXingfu,GONGRenxi.Powerqualitydisturbances classificationbasedongeneralizedS-transformand PSO-PNN[J].PowerSystemProtectionandControl,2016, 44(15):10-17.
[8]RAHUL, KAPOOR R, TRIPATHI M M. Detection and classificationofmultiplepowersignalpatternswith Volterraseriesandintervaltype-2fuzzylogicsystem[J]Protection and Control of Modern Power Systems, 2017,2(2):92-101. DOI:10.1186/s41601-017-0039-z.
[9]陈伟根,谢波,龙震泽,等.基于小波包能量熵的油纸绝缘气隙放电阶段识别[J].中国电机工程学报,2016,36(2):563-569.CHENWeigen,XIEBo,LONGZhenze,etal.Stage identificationinair-gapdischargeofoil-impregnated paper insulation based on wavelet packet energy entropy[J].Proceedings of the CSEE, 2016, 36(2):563-569.
[10]何巨龙,王根平,刘丹,等.基于提升小波和改进BP神经网络的配电网系统电能质量扰动定位与识别[J].电力系统保护与控制, 2017, 45(10):69-76.HEJulong,WANGGenping,LIUDan,etal.Localization andidentificationofpowerqualitydisturbancein distribution network system based on lifting wavelet and improvedBPneuralnetwork[J].PowerSystemProtection and Control, 2017, 45(10):69-76.
[11]黄建明,李晓明,瞿合祚,等.考虑小波奇异信息与不平衡数据集的输电线路故障识别方法[J].中国电机工程学报, 2017, 37(11):3099-3107.HUANGJianming,LIXiaoming,QUHezuo,etal.Methodforfaulttypeidentificationoftransmissionline considering wavelet singular information and unbalanced dataset[J].ProceedingsoftheCSEE,2017,37(11):3099-3107.
[12]唐贵基,王晓龙.可调品质因子小波变换在滚动轴承微弱故障特征提取中的应用[J].中国电机工程学报,2016, 36(3):746-754.TANGGuiji,WANGXiaolong.Applicationoftunable Q-factor wavelet transform to feature extraction of weak faultforrollingbearing[J].ProceedingsoftheCSEE,2016, 36(3):746-754.
[13]COSTAFB,SOUZABA,BRITONSD.Real-time detectionofvoltagesagsbasedonwavelettransform[C]//TransmissionandDistributionConferenceand Exposition:LatinAmerica,November8-10,2010,Sao Paulo, Brazil:537-542.
[14]COSTAFB,DRIESENJ.Assessmentofvoltagesag indicesbasedonscalingandwaveletcoefficientenergy analysis[J]. IEEE Transactions on Power Delivery, 2012,28(1):336-346.
[15] SANTOSOS,POWERSEJ,GRADYWM.Power quality disturbance waveform recognition using waveletbased neural network classification-part 2:application[J].IEEETransactionsonPowerDelivery,2000,15(1):229-235.
[16]CESARDG,VALDOMIROVG,GABRIELOP.Automaticpowerqualitydisturbancesdetectionand classificationbasedondiscretewavelettransformand artificial intelligence[C]//Transmission and Distribution Conference and Exposition:Latin America, August 15-18,2006, Caracas, Venezuela:1-6.
[17]秦英林,田立军,常学飞.基于小波变换能量分布和神经网络的电能质量扰动分类[J].电力自动化设备,2009, 29(7):64-67.QINYinglin,TIANLijun,CHANGXuefei.Classification ofpowerqualitydisturbancebasedonwaveletenergy distributionandneuralnetwork[J].ElectricPower Automation Equipment, 2009, 29(7):64-67.
[18]管春,周雒维,卢伟国.基于多标签RBF神经网络的电能质量复合扰动分类方法[J].电工技术学报,2011,26(8):198-204.GUANChun,ZHOULuowei,LUWeiguo.Recognition ofmultiplepowerqualitydisturbancesusingmulti-label RBFneuralnetworks[J].TransactionsofChina Electrotechnical Society, 2011, 26(8):198-204.
[19] ABDEL-GALIL T K, EL-SAADANY E F, YOUSSEF A M, et al. Disturbance classification using hidden Markov models and vector quantization[J]. IEEE Transactions on Power Delivery, 2005, 20(3):2129-2135.
[20]朱珂,倪建,刘颖英,等.面向电力扰动数据分析的暂态扰动检测[J].电工技术学报, 2017, 32(3):35-44.ZHUKe,NIJian,LIUYingying,etal.Detecttransient power disturbance for power disturbance data analytics[J].TransactionsofChinaElectrotechnicalSociety,2017,32(3):35-44.
[21]周翔,王丰华,傅坚,等.基于混动理论和K-means聚类的有载分接开关机械状态监测[J].中国电机工程学报, 2015, 35(6):1541-1548.ZHOUXiang,WANGFenghua,FUJian,etal.Mechanical condition monitoring of on-load tap changers based on chaos theory and K-means clustering method[J].Proceedings of the CSEE, 2015, 35(6):1541-1548.
[22] XIE X L, BENI G. A validity measure for fuzzy clustering[J].IEEETransactionsonPatternAnalysis&Machine Intelligence, 1991, 13(13):841-847.
[23]唐飞,王波,查晓明,等.基于双阶段并行隐马尔科夫模型的电力系统暂态稳定评估[J].中国电机工程学报,2013, 33(10):90-97.TANGFei,WANGBo,ZHAXiaoming,etal.Power systemtransientstabilityassessmentbasedontwo-stage parallelhiddenMarkovmodel[J].Proceedingsofthe CSEE, 2013, 33(10):90-97.