基于SF_6分解特性的局部放电故障程度评估
|
摘要
如何对直流SF6气体绝缘设备(gas-insulated equipment, GIE)内部局部放电(partial discharge,PD)严重程度进行科学的评估是目前还未解决的问题。由于GIE内部绝缘材料的分解情况与设备内部绝缘状态直接相关,提出利用SF6PD分解特性对GIE内部PD程度进行评估,具体为:建立出自由金属微粒缺陷模型,并将由该缺陷引起的PD划分为3个等级,在每个等级下各选2个电压开展SF6分解实验;基于最大相关最小冗余(minimumredundancymaximumcorrelation,m RMR)原则对SF6分解组分进行特征选择,并分别运用反向传播神经网络和支持向量机分类器诊断PD严重程度,提取出最能有效表征PD程度的SF6分解组分含量的比值集合,对PD状态进行评估。研究表明,SF6分解组分含量与PD严重程度之间存在一定的关联关系,C(CO2)/CT1、C(CF4)/C(SO2)、C(CO2)/C(SOF2)和C(CF4)/C(CO2)能够有效地诊断PD严重程度。
The problem that how to scientifically assess the severity of partial discharge(PD) in gas-insulated equipment(GIE) of the SF6 has not yet been solved. The decomposition of the internal insulation material of GIE is directly related to the internal insulation status of the equipment, therefore, in this paper, using SF6 decomposition characteristics to evaluate the internal PD degree of GIE was proposed. A free metal particle defect model was developed on the established SF6 DC-PD decomposition experiment platform, and the PD caused by this defect was divided into three levels. Two kinds of voltage in each of the PD levels were selected for the decomposition experiments of SF6. Based on the principle of minimumredundancy-maximum-relevance(mRMR), the characteristics of SF6 decomposed components had been selected. The PD severity was diagnosed by back propagation neural network(BPNN) and support vector machine(SVM) algorithms, and the ratio of SF6 decomposition components which could most effectively characterize the severity of PD was extracted, and the PD status was evaluated. The results show that there was a certain relationship between the SF6 decomposed components and the PD severity. C(CO2)/CT1、C(CF4)/C(SO2)、C(CO2)/C(SOF2) and C(CF4)/C(CO2)can effectively diagnose PD severity.
The problem that how to scientifically assess the severity of partial discharge(PD) in gas-insulated equipment(GIE) of the SF6 has not yet been solved. The decomposition of the internal insulation material of GIE is directly related to the internal insulation status of the equipment, therefore, in this paper, using SF6 decomposition characteristics to evaluate the internal PD degree of GIE was proposed. A free metal particle defect model was developed on the established SF6 DC-PD decomposition experiment platform, and the PD caused by this defect was divided into three levels. Two kinds of voltage in each of the PD levels were selected for the decomposition experiments of SF6. Based on the principle of minimumredundancy-maximum-relevance(mRMR), the characteristics of SF6 decomposed components had been selected. The PD severity was diagnosed by back propagation neural network(BPNN) and support vector machine(SVM) algorithms, and the ratio of SF6 decomposition components which could most effectively characterize the severity of PD was extracted, and the PD status was evaluated. The results show that there was a certain relationship between the SF6 decomposed components and the PD severity. C(CO2)/CT1、C(CF4)/C(SO2)、C(CO2)/C(SOF2) and C(CF4)/C(CO2)can effectively diagnose PD severity.
引文
[1]Mendik M,Lowder S M,Elliott F.Long term performance verification of high voltage DC GIS[C]//Proceedings of IEEE Transmission and Distribution Conference.New Orleans,LA,USA:IEEE,1999:484-488.
[2]Hasegawa T,Yamaji K,Hatano M.Development of insulation structure and enhancement of insulation reliability of 500 kV DC GIS[J].IEEE Transactions on Power Delivery,1997,12(1):192-202.
[3]张晓星,姚尧,唐炬,等.SF6放电分解气体组分分析的现状和发展[J].高电压技术,2008,34(4):664-669.Zhang Xiaoxing,Yao Yao,Tang Ju,et al.Actuality and perspective of proximate analysis of SF6 decomposed products under partial discharge[J].High Voltage Engineering,2008,34(4):664-669(in Chinese).
[4]Chu F Y.SF6 decomposition in gas-insulated equipment[J].IEEE Transactions on Dielectrics and Electrical Insulation.1986,21(5):693-725.
[5]Van Brunt R J,Herron J T.Fundamental processes of SF6decomposition and oxidation in glow and corona discharges[J].IEEE Transactions on Dielectrics and Electrical Insulation.1990,25(1):75-94.
[6]唐炬,杨东,曾福平,等.基于分解组分分析的SF6设备绝缘故障诊断方法与技术的研究现状[J].电工技术学报,2016,31(20):41-54.Tang Ju,Yang Dong,Zeng Fuping,et al.Research status of SF6 insulation equipment fault diagnosis method and technology based on decomposed components analysis[J].Transactions of China Electrotechnical Society,2016,31(20):41-54(in Chinese).
[7]Dreisbusch K,Kranz H G,Schnettler A.Determination of a failure probability prognosis based on PD-diagnostics in GIS[J].IEEE Transactions on Dielectrics and Electrical Insulation,2009,15(6):1707-1714.
[8]刘帆.局部放电下六氟化硫分解特性与放电类型辨识及影响因素校正[D].重庆:重庆大学,2013.Liu Fan.Decomposition characteristics of SF6 under PD&recognition of PD category and calibration of impact factors[D].Chongqing:Chongqing University,2013(in Chinese).
[9]Van Brunt R J.Production rates for oxy-fluorides SOF2,SO2F2 and SOF4 in SF6 corona discharges[J].Journal of Research of the National Bureau of Standards,1985,90(3):229-253.
[10]Van Brunt R J,Herron J T,Plasma chemical model for decomposition of SF6 in a negative glow corona discharge[J].Physica Scripta,2007,1994(T53):9.
[11]Tang J,Liu F,Zhang X,et al.Partial discharge recognition through an analysis of SF6 decomposition products part 1:decomposition characteristics of SF6 under four different partial discharges[J].IEEE Transactions on Dielectrics&Electrical Insulation,2012,19(1):29-36.
[12]Tang J,Liu F,Meng Q,et al.Partial discharge recognition through an analysis of SF6 decomposition products part 2:feature extraction and decision tree-based pattern recognition[J].IEEE Transactions on Dielectrics&Electrical Insulation,2012,19(1):37-44.
[13]Tang J,Zeng F,Pan J,et al.Correlation analysis between formation process of SF6 decomposed components and partial discharge qualities[J].IEEE Transactions on Dielectrics&Electrical Insulation,2013,20(3):864-875.
[14]Tang J,Pan J,Zhang X,et al.Correlation analysis between SF6,decomposed components and charge magnitude of partial discharges initiated by free metal particles[J].IET Science Measurement&Technology,2014,8(4):170-177.
[15]Ashkezari A D,Ma H,Saha T K,et al.Investigation of feature selection techniques for improving efficiency of power transformer condition assessment[J].IEEETransactions on Dielectrics&Electrical Insulation,2014,21(2):836-844.
[16]Peng H,Long F,Ding C.Feature selection based on mutual information:criteria of max-dependency,max-relevance,and min-redundancy[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2005,27(8):1226-1238.
[17]Li Y,Yang Y,Li G,et al.A fault diagnosis scheme for planetary gearboxes using modified multi-scale symbolic dynamic entropy and mRMR feature selection[J].Mechanical Systems&Signal Processing,2017,91:295-312.
[18]Escalona-Vargas D,Siegel E R,Murphy P,et al.Selection of reference channels based on mutual information for frequency-dependent subtraction method applied to fetal biomagnetic signals[J].IEEE Transactions on Biomedical Engineering,2017,64(5):1115-1122.
[19]Ramirez-Gallego S,Lastra I,Martinez-Rego D,et al.Fast m RMR:Fast minimum redundancy maximum relevance algorithm for high dimensional big data[J].International Journal of Intelligent Systems,2017,32(2):134-152.
[20]Aminian M,Aminian F.Neural-network based analog-circuit fault diagnosis using wavelet transform as preprocessor[J].IEEE Transactions on Circuits&Systems II Analog&Digital Signal Processing,2000,47(2):151-156.
[21]Karnin E D.A simple procedure for pruning backpropagation trained neural networks[J].IEEE Transactions on Neural Networks,1990,1(2):239-42.
[22]Majidi M,Fadali M S,Etezadi-Amoli M,et al.Partial discharge pattern recognition via sparse representation and ANN[J].IEEE Transactions on Dielectrics&Electrical Insulation,2015,22(2):1061-1070.
[23]Gulski E,Krivda A.Neural networks as a tool for recognition of partial discharges[J].IEEE Transactions on Dielectrics and Electrical Insulation,1993,28(6):984-1001.
[24]Satish L,Zaengl W S.Artificial neural networks for recognition of 3-D partial discharge patterns[J].IEEETransactions on Dielectrics&Electrical Insulation,1994,1(2):265-275.
[25]Hozumi N,Okamoto T,Imajo T.Discrimination of partial discharge patterns using a neural network[J].IEEETransactions on Electrical Insulation,1991,27(3):550-556.
[26]Leng X,Wang J,Ji H,et al.Prediction of sizefractionated airborne particle-bound metals using MLR,BP-ANN and SVM analyses.[J].Chemosphere,2017,180:513-522.
[27]Tang J,Zhuo R,Wang D B,et al.Application of SA-SVM incremental algorithm in GIS PD pattern recognition[J].Journal of Electrical Engineering&Technology,2016,11(1):192-199.
[28]Tang J,Tao J,Zhang X,et al.Multiple SVM-RFE for feature subset selection in partial discharge pattern recognition[J].International Review of Electrical Engineering,2012,7(4):5240-5246.
[29]Tang J,Wang D,Fan L,et al.Feature parameters extraction of gis partial discharge signal with multifractal detrended fluctuation analysis[J].IEEE Transactions on Dielectrics&Electrical Insulation,2015,22(5):3037-3045.
[30]李赢,舒乃秋.基于模糊聚类和完全二叉树支持向量机的变压器故障诊断[J].电工技术学报,2016,31(4):64-70.Li Ying,Shu Naiqiu.Transformer fault diagnosis based on fuzzy clustering and complete binary tree support vector machine[J].Transactions of China Electrotechnical Society,2016,31(4):64-70(in Chinese).
[31]IEC.IEC-60270 High-voltage Test Techniques-Partial Discharge Measurements[S].Geneva:IEC,2000.
[32]唐炬.组合电器局放在线监测外置传感器和复小波抑制干扰的研究[D].重庆:重庆大学,2004.Tang Ju.Study of outer sensors for on-line monitoring partial discharge in GIS and interference suppression with complex wavelet[D].Chongqing:Chongqing University,2004(in Chinese).
[33]戴琦伟.自由金属微粒对SF6及SF6/CO2工频击穿特性的影响[D].重庆:重庆大学,2016.Dai Qiwei.Influence of free metal particles on the power frequency breakdown performance of SF6 and SF6/CO2[D].Chongqing:Chongqing University,2016(in Chinese).
[34]Purnomoadi A P,Al-Suhaily M,Meijer S,et al.The influence of free moving particles on the breakdown voltage of GIS under different electrical stresses[C]//IEEE International Conference on Condition Monitoring and Diagnosis(CMD),Bali,Indonesia,2012:383-386.
[35]中华人民共和国电力工业部.DL/T 596-1996电力设备预防性试验规程[S].北京:中国电力出版社,1996.
[36]Kraskov A,St?Gbauer H,Grassberger P.Estimating mutual information[J].Physical Review E Statistical Nonlinear&Soft Matter Physics,2004,69(2):066138.
[2]Hasegawa T,Yamaji K,Hatano M.Development of insulation structure and enhancement of insulation reliability of 500 kV DC GIS[J].IEEE Transactions on Power Delivery,1997,12(1):192-202.
[3]张晓星,姚尧,唐炬,等.SF6放电分解气体组分分析的现状和发展[J].高电压技术,2008,34(4):664-669.Zhang Xiaoxing,Yao Yao,Tang Ju,et al.Actuality and perspective of proximate analysis of SF6 decomposed products under partial discharge[J].High Voltage Engineering,2008,34(4):664-669(in Chinese).
[4]Chu F Y.SF6 decomposition in gas-insulated equipment[J].IEEE Transactions on Dielectrics and Electrical Insulation.1986,21(5):693-725.
[5]Van Brunt R J,Herron J T.Fundamental processes of SF6decomposition and oxidation in glow and corona discharges[J].IEEE Transactions on Dielectrics and Electrical Insulation.1990,25(1):75-94.
[6]唐炬,杨东,曾福平,等.基于分解组分分析的SF6设备绝缘故障诊断方法与技术的研究现状[J].电工技术学报,2016,31(20):41-54.Tang Ju,Yang Dong,Zeng Fuping,et al.Research status of SF6 insulation equipment fault diagnosis method and technology based on decomposed components analysis[J].Transactions of China Electrotechnical Society,2016,31(20):41-54(in Chinese).
[7]Dreisbusch K,Kranz H G,Schnettler A.Determination of a failure probability prognosis based on PD-diagnostics in GIS[J].IEEE Transactions on Dielectrics and Electrical Insulation,2009,15(6):1707-1714.
[8]刘帆.局部放电下六氟化硫分解特性与放电类型辨识及影响因素校正[D].重庆:重庆大学,2013.Liu Fan.Decomposition characteristics of SF6 under PD&recognition of PD category and calibration of impact factors[D].Chongqing:Chongqing University,2013(in Chinese).
[9]Van Brunt R J.Production rates for oxy-fluorides SOF2,SO2F2 and SOF4 in SF6 corona discharges[J].Journal of Research of the National Bureau of Standards,1985,90(3):229-253.
[10]Van Brunt R J,Herron J T,Plasma chemical model for decomposition of SF6 in a negative glow corona discharge[J].Physica Scripta,2007,1994(T53):9.
[11]Tang J,Liu F,Zhang X,et al.Partial discharge recognition through an analysis of SF6 decomposition products part 1:decomposition characteristics of SF6 under four different partial discharges[J].IEEE Transactions on Dielectrics&Electrical Insulation,2012,19(1):29-36.
[12]Tang J,Liu F,Meng Q,et al.Partial discharge recognition through an analysis of SF6 decomposition products part 2:feature extraction and decision tree-based pattern recognition[J].IEEE Transactions on Dielectrics&Electrical Insulation,2012,19(1):37-44.
[13]Tang J,Zeng F,Pan J,et al.Correlation analysis between formation process of SF6 decomposed components and partial discharge qualities[J].IEEE Transactions on Dielectrics&Electrical Insulation,2013,20(3):864-875.
[14]Tang J,Pan J,Zhang X,et al.Correlation analysis between SF6,decomposed components and charge magnitude of partial discharges initiated by free metal particles[J].IET Science Measurement&Technology,2014,8(4):170-177.
[15]Ashkezari A D,Ma H,Saha T K,et al.Investigation of feature selection techniques for improving efficiency of power transformer condition assessment[J].IEEETransactions on Dielectrics&Electrical Insulation,2014,21(2):836-844.
[16]Peng H,Long F,Ding C.Feature selection based on mutual information:criteria of max-dependency,max-relevance,and min-redundancy[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2005,27(8):1226-1238.
[17]Li Y,Yang Y,Li G,et al.A fault diagnosis scheme for planetary gearboxes using modified multi-scale symbolic dynamic entropy and mRMR feature selection[J].Mechanical Systems&Signal Processing,2017,91:295-312.
[18]Escalona-Vargas D,Siegel E R,Murphy P,et al.Selection of reference channels based on mutual information for frequency-dependent subtraction method applied to fetal biomagnetic signals[J].IEEE Transactions on Biomedical Engineering,2017,64(5):1115-1122.
[19]Ramirez-Gallego S,Lastra I,Martinez-Rego D,et al.Fast m RMR:Fast minimum redundancy maximum relevance algorithm for high dimensional big data[J].International Journal of Intelligent Systems,2017,32(2):134-152.
[20]Aminian M,Aminian F.Neural-network based analog-circuit fault diagnosis using wavelet transform as preprocessor[J].IEEE Transactions on Circuits&Systems II Analog&Digital Signal Processing,2000,47(2):151-156.
[21]Karnin E D.A simple procedure for pruning backpropagation trained neural networks[J].IEEE Transactions on Neural Networks,1990,1(2):239-42.
[22]Majidi M,Fadali M S,Etezadi-Amoli M,et al.Partial discharge pattern recognition via sparse representation and ANN[J].IEEE Transactions on Dielectrics&Electrical Insulation,2015,22(2):1061-1070.
[23]Gulski E,Krivda A.Neural networks as a tool for recognition of partial discharges[J].IEEE Transactions on Dielectrics and Electrical Insulation,1993,28(6):984-1001.
[24]Satish L,Zaengl W S.Artificial neural networks for recognition of 3-D partial discharge patterns[J].IEEETransactions on Dielectrics&Electrical Insulation,1994,1(2):265-275.
[25]Hozumi N,Okamoto T,Imajo T.Discrimination of partial discharge patterns using a neural network[J].IEEETransactions on Electrical Insulation,1991,27(3):550-556.
[26]Leng X,Wang J,Ji H,et al.Prediction of sizefractionated airborne particle-bound metals using MLR,BP-ANN and SVM analyses.[J].Chemosphere,2017,180:513-522.
[27]Tang J,Zhuo R,Wang D B,et al.Application of SA-SVM incremental algorithm in GIS PD pattern recognition[J].Journal of Electrical Engineering&Technology,2016,11(1):192-199.
[28]Tang J,Tao J,Zhang X,et al.Multiple SVM-RFE for feature subset selection in partial discharge pattern recognition[J].International Review of Electrical Engineering,2012,7(4):5240-5246.
[29]Tang J,Wang D,Fan L,et al.Feature parameters extraction of gis partial discharge signal with multifractal detrended fluctuation analysis[J].IEEE Transactions on Dielectrics&Electrical Insulation,2015,22(5):3037-3045.
[30]李赢,舒乃秋.基于模糊聚类和完全二叉树支持向量机的变压器故障诊断[J].电工技术学报,2016,31(4):64-70.Li Ying,Shu Naiqiu.Transformer fault diagnosis based on fuzzy clustering and complete binary tree support vector machine[J].Transactions of China Electrotechnical Society,2016,31(4):64-70(in Chinese).
[31]IEC.IEC-60270 High-voltage Test Techniques-Partial Discharge Measurements[S].Geneva:IEC,2000.
[32]唐炬.组合电器局放在线监测外置传感器和复小波抑制干扰的研究[D].重庆:重庆大学,2004.Tang Ju.Study of outer sensors for on-line monitoring partial discharge in GIS and interference suppression with complex wavelet[D].Chongqing:Chongqing University,2004(in Chinese).
[33]戴琦伟.自由金属微粒对SF6及SF6/CO2工频击穿特性的影响[D].重庆:重庆大学,2016.Dai Qiwei.Influence of free metal particles on the power frequency breakdown performance of SF6 and SF6/CO2[D].Chongqing:Chongqing University,2016(in Chinese).
[34]Purnomoadi A P,Al-Suhaily M,Meijer S,et al.The influence of free moving particles on the breakdown voltage of GIS under different electrical stresses[C]//IEEE International Conference on Condition Monitoring and Diagnosis(CMD),Bali,Indonesia,2012:383-386.
[35]中华人民共和国电力工业部.DL/T 596-1996电力设备预防性试验规程[S].北京:中国电力出版社,1996.
[36]Kraskov A,St?Gbauer H,Grassberger P.Estimating mutual information[J].Physical Review E Statistical Nonlinear&Soft Matter Physics,2004,69(2):066138.