运行条件下GIS局部放电严重程度评估方法
|
摘要
运行条件下气体绝缘组合电器(gasinsulatedswitchgears,GIS)的局部放电检测已取得了大量的应用,但对于检测到局部放电信号的严重程度评估仍然是亟待解决的难题。利用变电站现场GIS的局部放电检测数据,结合长短时记忆网络(long short-term memory network,LSTM)和Bagging集成学习方法,提出一种运行条件下GIS局部放电严重程度评估方法。先明确了用GIS设备未来1个月内的故障概率来定义局部放电严重程度,并基于该定义对大量的变电站现场检测数据确定了数据标签,建立了数据集。针对数据样本不均衡,利用Bagging集成学习方法将N个LSTM深度网络构建成适用于局部放电严重程度评估的集成学习模型。通过对由局部放电数据特征值、局部放电技术影响因素、设备运行信息等组成的特征向量进行分析,模型最终可以输出局部放电严重程度评估结果。通过与普通LSTM网络、反向传播神经网络(backpropagationneuralnetwork,BPNN)以及Bagging-BPNN方法的对比,以及变电站现场检测案例分析,结果表明所提方法可以有效地对运行条件下GIS局部放电进行严重程度评估,易于实施,与普通LSTM、BPNN和Bagging-BPNN相比评估结果的可信度更高。
Partial discharge(PD) detection for the gas-insulated switchgear(GIS) in service has get got a large number of promotions, but the assessment of the severity of detected partial discharge signals is still an open question. In this paper, based on the partial discharge detection data from substation GIS on site, combined with the long short-term memory(LSTM) network and Bagging ensemble learning, a method for assessing the severity of partial discharge for GIS in service was proposed. First, the definition of partial discharge severity for GIS in service was defined by the failure probability, a large set of site data were established and data labels were determined based on the definition. Second, aiming at the problem of imbalanced data, an ensemble learning model for assessing the severity of partial discharge was constructed using N individual LSTM depth networks via Bagging ensemble learning. By analyzing the eigenvectors composed of the characteristic of partial discharge data, technical impact factors, and equipment operation information, the model can output the severity assessment result. The comparative experiments with common LSTM network, backpropagation neural network(BPNN) and Bagging-BPNN were undertaken,as well as on site detection case analysis, the results show that the proposed method can effectively assess the severity of GIS partial discharge under operating conditions and is easily to implement. Compared with common LSTM, BPNN and Bagging-BPNN, the proposed method has a higher credibility.
Partial discharge(PD) detection for the gas-insulated switchgear(GIS) in service has get got a large number of promotions, but the assessment of the severity of detected partial discharge signals is still an open question. In this paper, based on the partial discharge detection data from substation GIS on site, combined with the long short-term memory(LSTM) network and Bagging ensemble learning, a method for assessing the severity of partial discharge for GIS in service was proposed. First, the definition of partial discharge severity for GIS in service was defined by the failure probability, a large set of site data were established and data labels were determined based on the definition. Second, aiming at the problem of imbalanced data, an ensemble learning model for assessing the severity of partial discharge was constructed using N individual LSTM depth networks via Bagging ensemble learning. By analyzing the eigenvectors composed of the characteristic of partial discharge data, technical impact factors, and equipment operation information, the model can output the severity assessment result. The comparative experiments with common LSTM network, backpropagation neural network(BPNN) and Bagging-BPNN were undertaken,as well as on site detection case analysis, the results show that the proposed method can effectively assess the severity of GIS partial discharge under operating conditions and is easily to implement. Compared with common LSTM, BPNN and Bagging-BPNN, the proposed method has a higher credibility.
引文
[1]Rudd S,McArthur S D J,Judd M D.A generic knowledge-based approach to the analysis of partial discharge data[J].IEEE Transactions on Dielectrics and Electrical Insulation,2010,17(1):149-156.
[2]李军浩,韩旭涛,刘泽辉,等.电气设备局部放电检测技术述评[J].高电压技术,2015,41(8):2583-2601.Li Junhao,Han Xutao,Liu Zehui,et al.Review on partial discharge measurement technology of electrical equipment[J].High Voltage Engineering,2015,41(8):2583-2601(in Chinese).
[3]International Electrotechnical Commission.IEC 60270High-Voltage Test Techniques:Partial discharge measurements[S].Geneva,Switzerland:International Electrotechnical Commission,2015.
[4]姚勇,岳彦峰,黄兴泉.GIS超高频/超声波局放检测方法的现场应用[J].高电压技术,2008,34(2):422-424.Yao Yong,Yue Yanfeng,Huang Xingquan.Field application of GIS UHF/AE partial discharge detection method[J].High Voltage Engineering,2008,34(2):422-424(in Chinese).
[5]刘君华,姚明,黄成军,等.采用声电联合法的GIS局部放电定位试验研究[J].高电压技术,2009,35(10):2458-2463.Liu Junhua,Yao Ming,Huang Chengjun,et al.Experimental research on partial discharge localization in GIS using ultrasonic associated with electromagnetic wave method[J].High Voltage Engineering,2009,35(10):2458-2463(in Chinese).
[6]Sellars A G,Farish O,Peterson M M.UHF detection of leader discharges in SF6[J].IEEE Transactions on Dielectrics and Electrical Insulation,1995,1(2):143-154.
[7]Sellars A G,Farish O,Hampton B F.Assessing the risk of failure due to particle contamination of GIS using the UHF technique[J].IEEE Transactions on Dielectrics and Electrical Insulation,1994,1(2):323-331.
[8]Sellars A G,Farish O,Hampton B F,et al.Using the UHFtechnique to investigate PD produced by defects in solid insulation[J].IEEE Transactions on Dielectrics and Electrical Insulation,1995,2(3):448-459.
[9]Sellars A G,Farish O,Hampton B F.Characterising the discharge development due to surface contamination in GIS using the UHF technique[J].IEE ProceedingsScience,Measurement and Technology,1994,141(2):118-122.
[10]Qi B,Li C R,Geng B B,et al.Severity diagnosis and assessment of the partial discharge provoked by high-voltage electrode protrusion on GIS insulator surface[J].IEEE Trans.on Power Deliver,2011,26(4):2363-2369.
[11]齐波,李成榕,郝震,等.GIS设备绝缘子表面固定金属颗粒沿面局部放电发展的现象及特征[J].中国电机工程学报,2011,31(1):101-108.Qi Bo,Li Chengrong,Hao Zhen,et al.Evolution phenomena and features of surface partial discharge initiated by immobilized metal particles on GISinsulators[J].Proceedings of the CSEE,2011,31(1):101-108(in Chinese).
[12]Tang J,Jin M,Zeng F,et al.Assessment of PD severity in gas-insulated switchgear with an SSAE[J].IETScience,Measurement&Technology,2017,11(4):423-430.
[13]董玉林.组合电器局部放电特征提取与放电严重程度评估方法研究[D].重庆:重庆大学,2015.Dong Yulin.Research on feature extraction and severity assessment of partial discharge in GIS[D].Chongqing:Chongqing University,2015(in Chinese).
[14]王辉,郭志红,云玉新,等.GIS四种缺陷局放UHF信号标定技术研究[J].电力系统保护与控制,2012,40(21):7-13.Wang Hui,Guo Zhihong,Yun Yuxin,et al.Research of UHF calibration technique for four kinds of partial discharge defects in GIS[J].Power System Protection and Control,2012,40(21):7-13(in Chinese).
[15]张晓星,唐俊忠,唐炬,等.GIS中典型局放缺陷的UHF信号与放电量的相关分析[J].高电压技术,2012,38(1):59-65.Zhang Xiaoxing,Tang Junzhong,Tang Ju,et al.Relationship between UHF signals and discharge magnitude from typical partial discharge defects in GIS[J].High Voltage Engineering,2012,38(1):59-65(in Chinese).
[16]Gao W,Ding D,Liu W,et al.Investigation of the evaluation of the PD severity and verification of the sensitivity of partial-discharge detection using the UHFmethod in GIS[J].IEEE Transactions on Power Delivery,2014,29(1):38-47.
[17]Illias H A,Chen G,Lewin P L.Comparison between three-capacitance,analytical-based and finite element analysis partial discharge models in condition monitoring[J].IEEE Transactions on Dielectrics and Electrical Insulation,2017,24(1):99-109.
[18]Dezenzo T,Betz T,Schwarzbacher A.The different stages of PRPD pattern for positive point to plane corona driven by a DC voltage containing ripple[J].IEEE Transactions on Dielectrics and Electrical Insulation,2018,25(1):30-37.
[19]李建波,高文胜,刘卫东.直流GIL绝缘子表面附着金属颗粒局部放电发展过程及严重程度评估[J].高压电器,2018,54(5):9-16.Li Jianbo,Gao Wensheng,Liu Weidong.Evolution process and severity assessment of the partial discharge caused by immobilized metal particles on DC GILinsulator surface[J].High Voltage Apparatus,2018,54(5):9-16(in Chinese).
[20]李清泉,李斯盟,司雯,等.基于局部放电的电力变压器油纸绝缘状态评估关键问题分析[J].高电压技术,2017,43(8):2558-2565.Li Qingquan,Li Simeng,Si Wen,et al.Analysis of the key problem about insulation condition assessment of oil-paper in power transformers based on partial discharge[J].High Voltage Engineering,2017,43(8):2558-2565(in Chinese).
[21]陶加贵.组合电器局部放电多信息融合辨识与危害性评估研究[D].重庆:重庆大学,2013.Tao Jiagui.Study on partial discharge identification and harmfulness assessment for gas insulated switchgear[D].Chongqing:Chongqing University,2013(in Chinese).
[22]金虎.基于多参量的GIS局部放电发展过程研究及严重程度评估[D].北京:华北电力大学,2015.Jin Hu.GIS partial discharge development process research and its severity evaluation based on the multiple parameters[D].Beijing:North China Electric Power University,2015(in Chinese).
[23]律方成,金虎,王子建,等.基于组合核多特征融合的GIS局部放电检测与识别[J].电工技术学报,2014,29(10):334-340.LüFangcheng,Jin Hu,Wang Zijian,et al.GIS partial discharge detection and recognition based on the kernel combination and multiple feature fusion method[J].Transactions of China Electrotechnical Society,2014,29(10):334-340(in Chinese).
[24]CIGRE WG D1.03.Risk assessment on defects in GISbased on PD diagnostics[J].IEEE Transactions on Dielectrics and Electrical Insulation,2013,20(6):2165-2172.
[25]Sundermeyer M,Ney H,Schluter R.From feedforward to recurrent LSTM neural networks for language modeling[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2015,23(3):517-529.
[26]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[27]Cui Y,Ma H,Saha T.Improvement of power transformer insulation diagnosis using oil characteristics data preprocessed by SMOTEBoost technique[J].IEEETransactions on Dielectrics and Electrical Insulation,2014,21(5):2363-2373.
[28]He H,Garcia E A.Learning from imbalanced data[J].IEEE Transactions on Knowledge and Data Engineering,2009,21(9):1263-1284.
[29]周志华.机器学习[M].北京:清华大学出版社,2016:197-199.Zhou Zhihua.Machine learning[M].Beijing:Tsinghua University Press,2016:197-199(in Chinese).
[2]李军浩,韩旭涛,刘泽辉,等.电气设备局部放电检测技术述评[J].高电压技术,2015,41(8):2583-2601.Li Junhao,Han Xutao,Liu Zehui,et al.Review on partial discharge measurement technology of electrical equipment[J].High Voltage Engineering,2015,41(8):2583-2601(in Chinese).
[3]International Electrotechnical Commission.IEC 60270High-Voltage Test Techniques:Partial discharge measurements[S].Geneva,Switzerland:International Electrotechnical Commission,2015.
[4]姚勇,岳彦峰,黄兴泉.GIS超高频/超声波局放检测方法的现场应用[J].高电压技术,2008,34(2):422-424.Yao Yong,Yue Yanfeng,Huang Xingquan.Field application of GIS UHF/AE partial discharge detection method[J].High Voltage Engineering,2008,34(2):422-424(in Chinese).
[5]刘君华,姚明,黄成军,等.采用声电联合法的GIS局部放电定位试验研究[J].高电压技术,2009,35(10):2458-2463.Liu Junhua,Yao Ming,Huang Chengjun,et al.Experimental research on partial discharge localization in GIS using ultrasonic associated with electromagnetic wave method[J].High Voltage Engineering,2009,35(10):2458-2463(in Chinese).
[6]Sellars A G,Farish O,Peterson M M.UHF detection of leader discharges in SF6[J].IEEE Transactions on Dielectrics and Electrical Insulation,1995,1(2):143-154.
[7]Sellars A G,Farish O,Hampton B F.Assessing the risk of failure due to particle contamination of GIS using the UHF technique[J].IEEE Transactions on Dielectrics and Electrical Insulation,1994,1(2):323-331.
[8]Sellars A G,Farish O,Hampton B F,et al.Using the UHFtechnique to investigate PD produced by defects in solid insulation[J].IEEE Transactions on Dielectrics and Electrical Insulation,1995,2(3):448-459.
[9]Sellars A G,Farish O,Hampton B F.Characterising the discharge development due to surface contamination in GIS using the UHF technique[J].IEE ProceedingsScience,Measurement and Technology,1994,141(2):118-122.
[10]Qi B,Li C R,Geng B B,et al.Severity diagnosis and assessment of the partial discharge provoked by high-voltage electrode protrusion on GIS insulator surface[J].IEEE Trans.on Power Deliver,2011,26(4):2363-2369.
[11]齐波,李成榕,郝震,等.GIS设备绝缘子表面固定金属颗粒沿面局部放电发展的现象及特征[J].中国电机工程学报,2011,31(1):101-108.Qi Bo,Li Chengrong,Hao Zhen,et al.Evolution phenomena and features of surface partial discharge initiated by immobilized metal particles on GISinsulators[J].Proceedings of the CSEE,2011,31(1):101-108(in Chinese).
[12]Tang J,Jin M,Zeng F,et al.Assessment of PD severity in gas-insulated switchgear with an SSAE[J].IETScience,Measurement&Technology,2017,11(4):423-430.
[13]董玉林.组合电器局部放电特征提取与放电严重程度评估方法研究[D].重庆:重庆大学,2015.Dong Yulin.Research on feature extraction and severity assessment of partial discharge in GIS[D].Chongqing:Chongqing University,2015(in Chinese).
[14]王辉,郭志红,云玉新,等.GIS四种缺陷局放UHF信号标定技术研究[J].电力系统保护与控制,2012,40(21):7-13.Wang Hui,Guo Zhihong,Yun Yuxin,et al.Research of UHF calibration technique for four kinds of partial discharge defects in GIS[J].Power System Protection and Control,2012,40(21):7-13(in Chinese).
[15]张晓星,唐俊忠,唐炬,等.GIS中典型局放缺陷的UHF信号与放电量的相关分析[J].高电压技术,2012,38(1):59-65.Zhang Xiaoxing,Tang Junzhong,Tang Ju,et al.Relationship between UHF signals and discharge magnitude from typical partial discharge defects in GIS[J].High Voltage Engineering,2012,38(1):59-65(in Chinese).
[16]Gao W,Ding D,Liu W,et al.Investigation of the evaluation of the PD severity and verification of the sensitivity of partial-discharge detection using the UHFmethod in GIS[J].IEEE Transactions on Power Delivery,2014,29(1):38-47.
[17]Illias H A,Chen G,Lewin P L.Comparison between three-capacitance,analytical-based and finite element analysis partial discharge models in condition monitoring[J].IEEE Transactions on Dielectrics and Electrical Insulation,2017,24(1):99-109.
[18]Dezenzo T,Betz T,Schwarzbacher A.The different stages of PRPD pattern for positive point to plane corona driven by a DC voltage containing ripple[J].IEEE Transactions on Dielectrics and Electrical Insulation,2018,25(1):30-37.
[19]李建波,高文胜,刘卫东.直流GIL绝缘子表面附着金属颗粒局部放电发展过程及严重程度评估[J].高压电器,2018,54(5):9-16.Li Jianbo,Gao Wensheng,Liu Weidong.Evolution process and severity assessment of the partial discharge caused by immobilized metal particles on DC GILinsulator surface[J].High Voltage Apparatus,2018,54(5):9-16(in Chinese).
[20]李清泉,李斯盟,司雯,等.基于局部放电的电力变压器油纸绝缘状态评估关键问题分析[J].高电压技术,2017,43(8):2558-2565.Li Qingquan,Li Simeng,Si Wen,et al.Analysis of the key problem about insulation condition assessment of oil-paper in power transformers based on partial discharge[J].High Voltage Engineering,2017,43(8):2558-2565(in Chinese).
[21]陶加贵.组合电器局部放电多信息融合辨识与危害性评估研究[D].重庆:重庆大学,2013.Tao Jiagui.Study on partial discharge identification and harmfulness assessment for gas insulated switchgear[D].Chongqing:Chongqing University,2013(in Chinese).
[22]金虎.基于多参量的GIS局部放电发展过程研究及严重程度评估[D].北京:华北电力大学,2015.Jin Hu.GIS partial discharge development process research and its severity evaluation based on the multiple parameters[D].Beijing:North China Electric Power University,2015(in Chinese).
[23]律方成,金虎,王子建,等.基于组合核多特征融合的GIS局部放电检测与识别[J].电工技术学报,2014,29(10):334-340.LüFangcheng,Jin Hu,Wang Zijian,et al.GIS partial discharge detection and recognition based on the kernel combination and multiple feature fusion method[J].Transactions of China Electrotechnical Society,2014,29(10):334-340(in Chinese).
[24]CIGRE WG D1.03.Risk assessment on defects in GISbased on PD diagnostics[J].IEEE Transactions on Dielectrics and Electrical Insulation,2013,20(6):2165-2172.
[25]Sundermeyer M,Ney H,Schluter R.From feedforward to recurrent LSTM neural networks for language modeling[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2015,23(3):517-529.
[26]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[27]Cui Y,Ma H,Saha T.Improvement of power transformer insulation diagnosis using oil characteristics data preprocessed by SMOTEBoost technique[J].IEEETransactions on Dielectrics and Electrical Insulation,2014,21(5):2363-2373.
[28]He H,Garcia E A.Learning from imbalanced data[J].IEEE Transactions on Knowledge and Data Engineering,2009,21(9):1263-1284.
[29]周志华.机器学习[M].北京:清华大学出版社,2016:197-199.Zhou Zhihua.Machine learning[M].Beijing:Tsinghua University Press,2016:197-199(in Chinese).