基于并行化大数据流及迁移学习的配电变压器故障在线辨识–诊断模型
|
摘要
针对配变故障在线诊断对计算速度的要求,以及配变单体在线监测量种类及例行试验数据量不足的问题,建立了一种基于并行化大数据流及迁移学习的配电变压器故障在线辨识-诊断模型。首先,分析配变在线监测量在故障辨识中的可行性,基于此提出配变故障在线辨识的主要指标;其次,提出基于ARIMA预测技术的配变故障在线辨识方法,建立了基于大数据流的配变故障在线辨识模型,并利用Storm平台完成配变故障的并行化在线辨识,辨识出存在故障隐患的配变作为待诊断配变;再次,构建配变故障诊断指标体系,利用迁移学习算法TrAdaBoost从大量配变中提取有效故障信息,辅助待诊断配变进行故障诊断,建立了基于迁移学习的配变故障诊断模型,并在Storm平台上完成配变故障的并行化诊断;最后,根据配变故障数据进行算例分析,仿真结果表明,所建模型故障诊断精确性高达97%,能够实现配变故障的实时辨识与诊断。
Aiming at the problem of calculation speed of on-line fault diagnosis for distribution transformer, and the shortage of on-line monitoring type and routine test data,we establish an on-line fault diagnosis model of distribution transformer based on parallel big data stream and transfer learning. Firstly, the fault identification feasibility based on the present on-line monitoring data of distribution transformer is analyzed, and the main indicators of on-line fault identification are proposed. Secondly, the on-line fault identification method based on ARIMA is proposed, on this basis, the on-line fault identification model of distribution transformer based on big data stream is established, and the distribution transformers that possess hidden fault are selected, which would be diagnosed further. In order to improve the efficiency,the model is completed on a Storm platform in parallel form. Then, the distribution transformer fault diagnosis index system is constructed. In order to achieve the fault diagnosis of the above selected distribution transformers, the effective fault information from other distribution transformers is extracted using the transfer learning algorithm TrAdaBoost,which is used as auxiliary data for the fault diagnosis tool training of the distribution transformer to be diagnosed. Meanwhile, the model is completed on the Storm platform to improve the efficiency. Finally, based on the distribution transformer fault data, the distribution transformer fault diagnosis is simulated.The results show that the fault diagnosis accuracy reaches 97%, and real-time identification and diagnosis can be realized.
Aiming at the problem of calculation speed of on-line fault diagnosis for distribution transformer, and the shortage of on-line monitoring type and routine test data,we establish an on-line fault diagnosis model of distribution transformer based on parallel big data stream and transfer learning. Firstly, the fault identification feasibility based on the present on-line monitoring data of distribution transformer is analyzed, and the main indicators of on-line fault identification are proposed. Secondly, the on-line fault identification method based on ARIMA is proposed, on this basis, the on-line fault identification model of distribution transformer based on big data stream is established, and the distribution transformers that possess hidden fault are selected, which would be diagnosed further. In order to improve the efficiency,the model is completed on a Storm platform in parallel form. Then, the distribution transformer fault diagnosis index system is constructed. In order to achieve the fault diagnosis of the above selected distribution transformers, the effective fault information from other distribution transformers is extracted using the transfer learning algorithm TrAdaBoost,which is used as auxiliary data for the fault diagnosis tool training of the distribution transformer to be diagnosed. Meanwhile, the model is completed on the Storm platform to improve the efficiency. Finally, based on the distribution transformer fault data, the distribution transformer fault diagnosis is simulated.The results show that the fault diagnosis accuracy reaches 97%, and real-time identification and diagnosis can be realized.
引文
[1]JEONG S C,KIM J W,PARK P G,et al.A pattern-based fault classification algorithm for distribution transformers[J].IEEE Transactions on Power Delivery,2005,20(4):2483-2492.
[2]FARAG A S,MOHANDES M,AL-SHAIKH A.Diagnosing failed distribution transformers using neural networks[J].IEEE Transactions on Power Delivery,2001,16(4):631-636.
[3]吴广宁,袁海满,高波,等.基于特征评估与核主元分析的电力变压器故障诊断[J].高电压技术,2017,43(8):2533-2540.WU Guangning,YUAN Haiman,GAO Bo,et al.Fault diagnosis of power transformer based on feature evaluation and kernel principal component analysis[J].High Voltage Engineering,2017,43(8):2533-2540.
[4]汪可,李金忠,张书琦,等.变压器故障诊断用油中溶解气体新特征参量[J].中国电机工程学报,2016,36(23):6570-6578.WANG Ke,LI Jinzhong,ZHANG Shuqi,et al.New features derived from dissolved gas analysis for fault diagnosis of power transformers[J].Proceedings of the CSEE,2016,36(23):6570-6578.
[5]沈煜,阮羚,谢齐家,等.采用甚宽带脉冲电流法的变压器局部放电检测技术现场应用[J].高电压技术,2011,37(4):937-943.SHEN Yu,RUAN Ling,XIE Qijia,et al.On-site application of partial detection of transformer using very wide bandwidth pulse current method[J].High Voltage Engineering,2011,37(4):937-943.
[6]王有元,周立玮,梁玄鸿,等,基于关联规则分析的电力变压器故障马尔科夫预测模型[J].高电压技术,2018,44(4):1051-1058.WANG Youyuan,ZHOU Liwei,LIANG Xuanhong,et al.Markov forecasting model of power transformer fault based on association rules analysis[J].High Voltage Engineering,2018,44(4):1051-1058.
[7]梁永亮,李可军,牛林,等.一种优化特征选择-快速相关向量机变压器故障诊断方法[J].电网技术,2013,37(11):3262-3267.LIANG Yongliang,LI Kejun,NIU Lin,et al.A transformer diagnosis method based on optimized feature selection methods and fast relevance vector machine[J].Power System Technology,2013,37(11):3262-3267.
[8]孙鹏,耿苏杰,王秀利.基于时效评分函数和贝叶斯概率的电力变压器状态实时评估[J].高电压技术,2018,44(4):1069-1077.SUN Peng,GENG Sujie,WANG Xiuli.Real-time condition assessment of power transformers based on time-effect core function and Bayesian probability[J].High Voltage Engineering,2018,44(4):1069-1077.
[9]张哲,赵文清,朱永利,等.基于支持向量回归的电力变压器状态评估[J].电力自动化设备,2010,30(4):81-84.ZHANG Zhe,ZHAO Wenqing,ZHU Yongli,et al.Power transformer condition evaluation based on support vector regression[J].Electric Power Automation Equipment,2010,30(4):81-84.
[10]王德文,刘晓建.基于MapReduce的电力设备并行故障诊断方法[J].电力自动化设备,2014,34(10):116-120.WANG Dewen,LIU Xiaojian.Parallel fault diagnosis based on MapReduce for electric power equipments[J].Electric Power Automation Equipment,2014,34(10):116-120.
[11]郝思鹏,张济韬,张仰飞,等.融合在线监测数据的变压器状态评估[J].电力自动化设备,2017,37(11):176-181.HAO Sipeng,ZHANG Jitao,ZHANG Yangfei,et al.State evaluation of transformer based on information fusion of on-line monitoring data[J].Electric Power Automation Equipment,2017,37(11):176-181.
[12]孙鹏,黄绪勇,耿苏杰,等.基于实时监测和例行试验数据的电力变压器状态动态评估方法[J].电力自动化设备,2018,38(3):210-217.SUN Peng,HUANG Xuyong,GENG Sujie,et al.Dynamic assessment of power transformer status based on realtime monitoring and experimental data[J].Electric Power Automation Equipment,2018,38(3):210-217.
[13]杨志淳,沈煜,杨帆,等.考虑多元因素态势演变的配电变压器迁移学习故障诊断模型[J].电工技术学报,2019,34(7):1505-1515.YANG Zhichun,SHEN Yu,YANG Fan,et al.A transfer learning fault diagnosis model of distribution transformer considering multi-factor situation evolution[J].Transactions of China Electrotechnical Society,2019,34(7):1505-1515.
[14]赵必厦,程丽明.从零开始学Storm[M].北京:清华大学出版社,2014.ZHAO Bixia,CHENG Liming.Learn Storm from scratch[M].Beijing,China:Tsinghua University Press,2014.
[15]陈民铀,王明林,郑杰,等.计及不对称负荷的配电变压器短路电抗在线检测方法[J].高电压技术,2015,41(3):881-886.CHEN Minyou,WANG Minglin,ZHENG Jie,et al.On-line detection of short-circuit reactance of distribution transformers considering the condition of asymmetric load[J].High Voltage Engineering,2015,41(3):881-886.
[16]陈民铀,李霞,王平,等.配电变压器短路和开路损耗在线测量系统[J].电机与控制学报,2012,16(3):36-41.CHEN Minyou,LI Xia,WANG Ping,et al.System of online measuring short-circuit loss and open-circuit loss of distribution transformer[J].Electric Machines and Control,2012,16(3):36-41.
[17]曾刚远.测量短路电抗是判断变压器绕组变形的有效方法[J].变压器,1998,35(8):13-17.ZENG Gangyuan.Measuring the short-circuit reactance-an effective method for judging the deformation of transformers windings[J].Transformer,1998,35(8):13-17.
[18]王世阁.从变压器事故实例看短路试验的必要性[J].变压器,1998,35(1):17-20.WANG Shige.Necessity explanation of short-circuit test for transformer by examples of transformer faults[J].Transformer,1998,35(1):17-20.
[19]岳地松.浅谈配电变压器故障的原因及防范措施[J].变压器,2008,45(12):64-67.YUE Disong.Brief discussion on fault reason of distribution transformer and protective measure[J].Transformer,2008,45(12):64-67.
[20]黄新波,李弘博,朱永灿,等.基于时间序列分析与卡尔曼滤波的输电线路覆冰短期预测[J].高电压技术,2017,43(6):205-211.HUANG Xinbo,LI Hongbo,ZHU Yongcan,et al.Short-term forecast for transmission line icing by time series analysis and Kalman filtering[J].High Voltage Engineering,2017,43(6):205-211.
[21]腾腾,赵治华.电磁发射系统监测量预测方法[J].电工技术学报,2018,33(22):5233-5243.TENG Teng,ZHAO Zhihua.The prediction method of monitoring quantities of electromagnetic emission system[J].Transactions of China Electrotechnical Society,2018,33(22):5233-5243.
[22]BHATIA A,VASWANI G.Big data-a review[J].International Journal of Engineering Science and Research Technology,2013,2(8):2102-2106.
[23]王国胤,刘群,于洪,等.大数据挖掘及应用[M].北京:清华大学出版社,2017.WANG Guoyin,LIU Qun,YU Hong,et al.Big data mining and application[M].Beijing,China:Tsinghua University Press,2017.
[24]国家能源局.配电变压器运行规程[S].北京:中国电力出版社,2009.National Energy Administration.Regulations for distribution transformers operation[S].Beijing,China:China Electric Power Press,2009.
[25]国家能源局.变压器油中溶解气体分析和判断导则[S].北京:中国电力出版社,2014.National Energy Administration.Guidelines for analysis and judgment of dissolved gases in transformer oil[S].Beijing,China:China Electric Power Press,2014.
[26]国家质量监督检验检疫总局.油浸式电力变压器技术参数和要求[S].北京:中国电力出版社,2015.State Administration of Quality Supervision,Inspection and Quarantine,National Standardization Management Committee.Technical parameters and requirements for oil-immersed power transformers[S].Beijing,China:China Electric Power Press,2015.
[27]李恩文,王力农,宋斌,等.基于改进模糊聚类算法的变压器油色谱分析[J].电工技术学报,2018,33(19):4594-4602.LI Enwen,WANG Linong,SONG Bin,et al.Analysis of transformer oil chromatography based on improved fuzzy clustering algorithm[J].Transactions of China Electrotechnical Society,2018,33(19):4594-4602.
[28]殷振滔.随机缺失值填补及其效果研究-基于面板数据因子分析方法[D].上海:上海师范大学,2018.YIN Zhentao.Stochastic missing value filling and its effect--based on panel data factor analysis method[D].Shanghai,China:Shanghai Normal University,2018.
[29]韩富尧,刘亚伟.基于计量经济-灰色理论的多变量电力负荷预测方法[J].电气技术,2017,18(7):37-40.HAN Fuyao,LIU Yawei.Multivariate power load forecasting method based on econometrics and grey theory[J].Electrical Engineering,2017,18(7):37-40.
[30]王森,薛永端,仉志华,等.基于黄金分割法优选的中长期负荷变权组合预测[J].电测与仪表,2015,53(3):85-92.WANG Sen.XUE Yongrui,ZHANG Zhihua,et al.Variable weight combination method for mid-long term load forecasting based on golden section algorithm[J].Electrical Measurement&Instrumentation,2015,53(3):85-92.
[2]FARAG A S,MOHANDES M,AL-SHAIKH A.Diagnosing failed distribution transformers using neural networks[J].IEEE Transactions on Power Delivery,2001,16(4):631-636.
[3]吴广宁,袁海满,高波,等.基于特征评估与核主元分析的电力变压器故障诊断[J].高电压技术,2017,43(8):2533-2540.WU Guangning,YUAN Haiman,GAO Bo,et al.Fault diagnosis of power transformer based on feature evaluation and kernel principal component analysis[J].High Voltage Engineering,2017,43(8):2533-2540.
[4]汪可,李金忠,张书琦,等.变压器故障诊断用油中溶解气体新特征参量[J].中国电机工程学报,2016,36(23):6570-6578.WANG Ke,LI Jinzhong,ZHANG Shuqi,et al.New features derived from dissolved gas analysis for fault diagnosis of power transformers[J].Proceedings of the CSEE,2016,36(23):6570-6578.
[5]沈煜,阮羚,谢齐家,等.采用甚宽带脉冲电流法的变压器局部放电检测技术现场应用[J].高电压技术,2011,37(4):937-943.SHEN Yu,RUAN Ling,XIE Qijia,et al.On-site application of partial detection of transformer using very wide bandwidth pulse current method[J].High Voltage Engineering,2011,37(4):937-943.
[6]王有元,周立玮,梁玄鸿,等,基于关联规则分析的电力变压器故障马尔科夫预测模型[J].高电压技术,2018,44(4):1051-1058.WANG Youyuan,ZHOU Liwei,LIANG Xuanhong,et al.Markov forecasting model of power transformer fault based on association rules analysis[J].High Voltage Engineering,2018,44(4):1051-1058.
[7]梁永亮,李可军,牛林,等.一种优化特征选择-快速相关向量机变压器故障诊断方法[J].电网技术,2013,37(11):3262-3267.LIANG Yongliang,LI Kejun,NIU Lin,et al.A transformer diagnosis method based on optimized feature selection methods and fast relevance vector machine[J].Power System Technology,2013,37(11):3262-3267.
[8]孙鹏,耿苏杰,王秀利.基于时效评分函数和贝叶斯概率的电力变压器状态实时评估[J].高电压技术,2018,44(4):1069-1077.SUN Peng,GENG Sujie,WANG Xiuli.Real-time condition assessment of power transformers based on time-effect core function and Bayesian probability[J].High Voltage Engineering,2018,44(4):1069-1077.
[9]张哲,赵文清,朱永利,等.基于支持向量回归的电力变压器状态评估[J].电力自动化设备,2010,30(4):81-84.ZHANG Zhe,ZHAO Wenqing,ZHU Yongli,et al.Power transformer condition evaluation based on support vector regression[J].Electric Power Automation Equipment,2010,30(4):81-84.
[10]王德文,刘晓建.基于MapReduce的电力设备并行故障诊断方法[J].电力自动化设备,2014,34(10):116-120.WANG Dewen,LIU Xiaojian.Parallel fault diagnosis based on MapReduce for electric power equipments[J].Electric Power Automation Equipment,2014,34(10):116-120.
[11]郝思鹏,张济韬,张仰飞,等.融合在线监测数据的变压器状态评估[J].电力自动化设备,2017,37(11):176-181.HAO Sipeng,ZHANG Jitao,ZHANG Yangfei,et al.State evaluation of transformer based on information fusion of on-line monitoring data[J].Electric Power Automation Equipment,2017,37(11):176-181.
[12]孙鹏,黄绪勇,耿苏杰,等.基于实时监测和例行试验数据的电力变压器状态动态评估方法[J].电力自动化设备,2018,38(3):210-217.SUN Peng,HUANG Xuyong,GENG Sujie,et al.Dynamic assessment of power transformer status based on realtime monitoring and experimental data[J].Electric Power Automation Equipment,2018,38(3):210-217.
[13]杨志淳,沈煜,杨帆,等.考虑多元因素态势演变的配电变压器迁移学习故障诊断模型[J].电工技术学报,2019,34(7):1505-1515.YANG Zhichun,SHEN Yu,YANG Fan,et al.A transfer learning fault diagnosis model of distribution transformer considering multi-factor situation evolution[J].Transactions of China Electrotechnical Society,2019,34(7):1505-1515.
[14]赵必厦,程丽明.从零开始学Storm[M].北京:清华大学出版社,2014.ZHAO Bixia,CHENG Liming.Learn Storm from scratch[M].Beijing,China:Tsinghua University Press,2014.
[15]陈民铀,王明林,郑杰,等.计及不对称负荷的配电变压器短路电抗在线检测方法[J].高电压技术,2015,41(3):881-886.CHEN Minyou,WANG Minglin,ZHENG Jie,et al.On-line detection of short-circuit reactance of distribution transformers considering the condition of asymmetric load[J].High Voltage Engineering,2015,41(3):881-886.
[16]陈民铀,李霞,王平,等.配电变压器短路和开路损耗在线测量系统[J].电机与控制学报,2012,16(3):36-41.CHEN Minyou,LI Xia,WANG Ping,et al.System of online measuring short-circuit loss and open-circuit loss of distribution transformer[J].Electric Machines and Control,2012,16(3):36-41.
[17]曾刚远.测量短路电抗是判断变压器绕组变形的有效方法[J].变压器,1998,35(8):13-17.ZENG Gangyuan.Measuring the short-circuit reactance-an effective method for judging the deformation of transformers windings[J].Transformer,1998,35(8):13-17.
[18]王世阁.从变压器事故实例看短路试验的必要性[J].变压器,1998,35(1):17-20.WANG Shige.Necessity explanation of short-circuit test for transformer by examples of transformer faults[J].Transformer,1998,35(1):17-20.
[19]岳地松.浅谈配电变压器故障的原因及防范措施[J].变压器,2008,45(12):64-67.YUE Disong.Brief discussion on fault reason of distribution transformer and protective measure[J].Transformer,2008,45(12):64-67.
[20]黄新波,李弘博,朱永灿,等.基于时间序列分析与卡尔曼滤波的输电线路覆冰短期预测[J].高电压技术,2017,43(6):205-211.HUANG Xinbo,LI Hongbo,ZHU Yongcan,et al.Short-term forecast for transmission line icing by time series analysis and Kalman filtering[J].High Voltage Engineering,2017,43(6):205-211.
[21]腾腾,赵治华.电磁发射系统监测量预测方法[J].电工技术学报,2018,33(22):5233-5243.TENG Teng,ZHAO Zhihua.The prediction method of monitoring quantities of electromagnetic emission system[J].Transactions of China Electrotechnical Society,2018,33(22):5233-5243.
[22]BHATIA A,VASWANI G.Big data-a review[J].International Journal of Engineering Science and Research Technology,2013,2(8):2102-2106.
[23]王国胤,刘群,于洪,等.大数据挖掘及应用[M].北京:清华大学出版社,2017.WANG Guoyin,LIU Qun,YU Hong,et al.Big data mining and application[M].Beijing,China:Tsinghua University Press,2017.
[24]国家能源局.配电变压器运行规程[S].北京:中国电力出版社,2009.National Energy Administration.Regulations for distribution transformers operation[S].Beijing,China:China Electric Power Press,2009.
[25]国家能源局.变压器油中溶解气体分析和判断导则[S].北京:中国电力出版社,2014.National Energy Administration.Guidelines for analysis and judgment of dissolved gases in transformer oil[S].Beijing,China:China Electric Power Press,2014.
[26]国家质量监督检验检疫总局.油浸式电力变压器技术参数和要求[S].北京:中国电力出版社,2015.State Administration of Quality Supervision,Inspection and Quarantine,National Standardization Management Committee.Technical parameters and requirements for oil-immersed power transformers[S].Beijing,China:China Electric Power Press,2015.
[27]李恩文,王力农,宋斌,等.基于改进模糊聚类算法的变压器油色谱分析[J].电工技术学报,2018,33(19):4594-4602.LI Enwen,WANG Linong,SONG Bin,et al.Analysis of transformer oil chromatography based on improved fuzzy clustering algorithm[J].Transactions of China Electrotechnical Society,2018,33(19):4594-4602.
[28]殷振滔.随机缺失值填补及其效果研究-基于面板数据因子分析方法[D].上海:上海师范大学,2018.YIN Zhentao.Stochastic missing value filling and its effect--based on panel data factor analysis method[D].Shanghai,China:Shanghai Normal University,2018.
[29]韩富尧,刘亚伟.基于计量经济-灰色理论的多变量电力负荷预测方法[J].电气技术,2017,18(7):37-40.HAN Fuyao,LIU Yawei.Multivariate power load forecasting method based on econometrics and grey theory[J].Electrical Engineering,2017,18(7):37-40.
[30]王森,薛永端,仉志华,等.基于黄金分割法优选的中长期负荷变权组合预测[J].电测与仪表,2015,53(3):85-92.WANG Sen.XUE Yongrui,ZHANG Zhihua,et al.Variable weight combination method for mid-long term load forecasting based on golden section algorithm[J].Electrical Measurement&Instrumentation,2015,53(3):85-92.