基于数据挖掘的电力设备运维与决策分析方法
|
摘要
电力设备的运维管理主要包括设备的故障分析、主动预警和差异化运维.在面对电网运行过程中多时间尺度、多时空维度的海量数据背景下,文中将数据挖掘技术应用到电力设备的运行管理上.文中利用K-means聚类算法挖掘历史运行数据信息,进行单维状态量故障特征提取;利用Apriori算法挖掘不同故障模式下关联规则,建立关键性能矩阵,借助高维随机矩阵理论分析设备故障的时空特性;利用D-S证据理论对单维与多维诊断结果进行信息合成,获得设备故障的诊断判据.同时,综合考虑系统运行状态和电力用户差异性,建立设备健康度指数以及重要度指数,显著降低设备运维决策风险.仿真案例证明了本文方法的有效性.
The operation and maintenance management of the power equipment(PE) mainly includes fault analysis, active early-warning and differentiated operation and maintenance. In the context of massive data with multiple time scales and multiple time and space dimensions in the process of grid operation, data mining technology was applied for PE operation and maintenance management. The one-dimensional fault feature was extracted from fault information by K-means clustering algorithm. Then, Apriori algorithm was employed to mine association rules of different failure modes and establish key performance matrix. The spatial-temporal characteristics were analyzed based on high-dimensional random matrix theory(RMT). Afterwards, one-dimensional and multi-dimensional fault features were combined based on D-S evidence theory so that the fault diagnosis criteria of PE was obtained. At the same time, comprehensively considering the PE operating state and the variation for power users, health index and importance index of equipment were established, which could help to significantly reduce the decision-making risk of PE operation and maintenance. The result of simulation proves the effectiveness of the proposed method.
The operation and maintenance management of the power equipment(PE) mainly includes fault analysis, active early-warning and differentiated operation and maintenance. In the context of massive data with multiple time scales and multiple time and space dimensions in the process of grid operation, data mining technology was applied for PE operation and maintenance management. The one-dimensional fault feature was extracted from fault information by K-means clustering algorithm. Then, Apriori algorithm was employed to mine association rules of different failure modes and establish key performance matrix. The spatial-temporal characteristics were analyzed based on high-dimensional random matrix theory(RMT). Afterwards, one-dimensional and multi-dimensional fault features were combined based on D-S evidence theory so that the fault diagnosis criteria of PE was obtained. At the same time, comprehensively considering the PE operating state and the variation for power users, health index and importance index of equipment were established, which could help to significantly reduce the decision-making risk of PE operation and maintenance. The result of simulation proves the effectiveness of the proposed method.
引文
[1] LI C,TANG Z,ZHENG Z.Recent progress and future perspective on condition monitoring and diagnostic techniques for power equipments in China [C]//International Conference on Condition Monitoring and Diagnosis.Beijing,China:IEEE,2008:1- 6
[2] 江秀臣,盛戈皞.电力设备状态大数据分析的研究和应用 [J].高电压技术,2018,44(04):1041- 1050.JIANG Xiuchen,SHENG Gehao.Research and application of big data analysis of power equipment condition [J].High Voltage Engineering,2018,44(04):1041- 1050.
[3] 费思源.大数据技术在配电网中的应用综述 [J].中国电机工程学报,2018,38(01):85- 96;345.FEI Siyuan.Overview of application of big data technology in power distribution system [J].Proceedings of the CSEE,2018,38(01):85- 96;345.
[4] 刘科研,盛万兴,张东霞,等.智能配电网大数据应用需求和场景分析研究 [J].中国电机工程学报,2015,35(02):287- 293.LIU Ke-yan,SHENG Wan-xing,ZHANG Dong-xia,et al.Big data application requirements and scenario analysis in smart distribution network [J].Proceedings of the CSEE,2015,35(02):287- 293.
[5] 赵庆周,李勇,田世明,等.基于智能配电网大数据分析的状态监测与故障处理方法 [J].电网技术,2016,40(03):774- 780.ZHAO Qing-zhou,LI Yong,TIAN Shi-ming,et al.A state estimation and fault processing method based on big data analysis of smart distribution network [J].Power System Technology,2016,40(03):774- 780.
[6] 黄大荣,陈长沙,孙国玺,等.电力变压器故障的客观熵权识别及诊断方法 [J].电力系统自动化,2017,41(12):206- 211.HUANG Da-rong,CHEN Chang-sha,SUN Guo-xi,et al.Recognition and diagnosis method of objective entropy weight for power transformer fault [J].Automation of Electric Power System,2017,41(12):206- 211.
[7] PIASSON Diego,BíSCARO André A P,LE?O Fábio B,et al.A new approach for reliability-centered maintenance programs in electric power distribution systems based on a multi-objective genetic algorithm [J].Electric Power Systems Research,2016,137:41- 50.
[8] YSSAAD B,ABENE A.Rational reliability centered maintenance optimization for power distribution systems [J].International Journal of Electrical Power & Energy Systems,2015,73:350- 360.
[9] 栗然,王飞飞,李增辉.基于风险评估的配电网检修决策优化 [J].电力自动化设备,2013,33(11):1- 8.LI Ran,WANG Fei-fei,LI Zeng-hui.Maintenance decision making optimization based on risk assessment for distribution system [J].Electric Power Automation Equipment,2013,33(11):1- 8.
[10] 史常凯,宁昕,孙智涛,等.基于设备实时健康指数的配电网风险量化评估 [J].高电压技术,2018,44(02):534- 540.SHI Chang-kai,NING Xin,SUN Zhi-tao,et al.Quantitative risk assessment of distribution network based on real-time health index of equipment [J].High Voltage Engineering,2018,44(02):534- 540.
[11] 黄曌,汪沨,谭阳红,等.基于健康度和重要度的配电网运行风险评估方法 [J].电力自动化设备,2016,36(06):136- 141.HUANG Zhao,WANG Feng,TAN Yang-hong,et al.Ope-rational risk assessment based on health and importance indexes for distribution network [J].Electric Power Automation Equipment,2016,36(06):136- 141
[12] ZHANG Zheng-jun,ZHU Yao-qin.Estimating the image segmentation number via the entropy gap statistic [C]//2009 Second International Conference on Information and Computing Science.[S.l.]:IEEE Computer Society,2009:14- 16.
[13] 严英杰,盛戈皞,王辉,等.基于高维随机矩阵大数据分析模型的输变电设备关键性能评估方法 [J].中国电机工程学报,2016,36(02):435- 445.YAN Ying-jie,SHENG Ge-gao,WANG Hui,et al.The key state assessment method of power transmission equipment using big data analyzing model based on large dimensional random matrix [J].Proceedings of the CSEE,2016,36(02):435- 445.
[14] CHAWLA N V ,BOWYER K W ,HALL L O ,et al.SMOTE:synthetic minority over-sampling technique [J].Journal of Artificial Intelligence Research,2002,16(1):321- 357.
[15] DOOSTAN M ,CHOWDHURY B H .Power distribution system fault cause analysis by using association rule mining [J].Electric Power Systems Research,2017,152:140- 147.
[16] 刘威,张东霞,丁玉成,等.基于随机矩阵理论与熵理论的电网薄弱环节辨识方法 [J].中国电机工程学报,2017,37(20):5893- 5901.LIU Wei,ZHANG Dong-xia,DING Yun-cheng,et al.Power grid vulnerability identification methods based on random matrix theory and entropy theory [J].Proceedings of the CSEE,2017,37(20):5893- 5901.
[17] 李文立,郭凯红.D-S证据理论合成规则及冲突问题 [J].系统工程理论与实践,2010,30(08):1422- 1432.LI Wen-li,GUO Kai-hong.Combination rules of D-S evidence theory and conflict problem [J].Systems Engineering-Theory & Practice,2010,30(08):1422- 1432.
[2] 江秀臣,盛戈皞.电力设备状态大数据分析的研究和应用 [J].高电压技术,2018,44(04):1041- 1050.JIANG Xiuchen,SHENG Gehao.Research and application of big data analysis of power equipment condition [J].High Voltage Engineering,2018,44(04):1041- 1050.
[3] 费思源.大数据技术在配电网中的应用综述 [J].中国电机工程学报,2018,38(01):85- 96;345.FEI Siyuan.Overview of application of big data technology in power distribution system [J].Proceedings of the CSEE,2018,38(01):85- 96;345.
[4] 刘科研,盛万兴,张东霞,等.智能配电网大数据应用需求和场景分析研究 [J].中国电机工程学报,2015,35(02):287- 293.LIU Ke-yan,SHENG Wan-xing,ZHANG Dong-xia,et al.Big data application requirements and scenario analysis in smart distribution network [J].Proceedings of the CSEE,2015,35(02):287- 293.
[5] 赵庆周,李勇,田世明,等.基于智能配电网大数据分析的状态监测与故障处理方法 [J].电网技术,2016,40(03):774- 780.ZHAO Qing-zhou,LI Yong,TIAN Shi-ming,et al.A state estimation and fault processing method based on big data analysis of smart distribution network [J].Power System Technology,2016,40(03):774- 780.
[6] 黄大荣,陈长沙,孙国玺,等.电力变压器故障的客观熵权识别及诊断方法 [J].电力系统自动化,2017,41(12):206- 211.HUANG Da-rong,CHEN Chang-sha,SUN Guo-xi,et al.Recognition and diagnosis method of objective entropy weight for power transformer fault [J].Automation of Electric Power System,2017,41(12):206- 211.
[7] PIASSON Diego,BíSCARO André A P,LE?O Fábio B,et al.A new approach for reliability-centered maintenance programs in electric power distribution systems based on a multi-objective genetic algorithm [J].Electric Power Systems Research,2016,137:41- 50.
[8] YSSAAD B,ABENE A.Rational reliability centered maintenance optimization for power distribution systems [J].International Journal of Electrical Power & Energy Systems,2015,73:350- 360.
[9] 栗然,王飞飞,李增辉.基于风险评估的配电网检修决策优化 [J].电力自动化设备,2013,33(11):1- 8.LI Ran,WANG Fei-fei,LI Zeng-hui.Maintenance decision making optimization based on risk assessment for distribution system [J].Electric Power Automation Equipment,2013,33(11):1- 8.
[10] 史常凯,宁昕,孙智涛,等.基于设备实时健康指数的配电网风险量化评估 [J].高电压技术,2018,44(02):534- 540.SHI Chang-kai,NING Xin,SUN Zhi-tao,et al.Quantitative risk assessment of distribution network based on real-time health index of equipment [J].High Voltage Engineering,2018,44(02):534- 540.
[11] 黄曌,汪沨,谭阳红,等.基于健康度和重要度的配电网运行风险评估方法 [J].电力自动化设备,2016,36(06):136- 141.HUANG Zhao,WANG Feng,TAN Yang-hong,et al.Ope-rational risk assessment based on health and importance indexes for distribution network [J].Electric Power Automation Equipment,2016,36(06):136- 141
[12] ZHANG Zheng-jun,ZHU Yao-qin.Estimating the image segmentation number via the entropy gap statistic [C]//2009 Second International Conference on Information and Computing Science.[S.l.]:IEEE Computer Society,2009:14- 16.
[13] 严英杰,盛戈皞,王辉,等.基于高维随机矩阵大数据分析模型的输变电设备关键性能评估方法 [J].中国电机工程学报,2016,36(02):435- 445.YAN Ying-jie,SHENG Ge-gao,WANG Hui,et al.The key state assessment method of power transmission equipment using big data analyzing model based on large dimensional random matrix [J].Proceedings of the CSEE,2016,36(02):435- 445.
[14] CHAWLA N V ,BOWYER K W ,HALL L O ,et al.SMOTE:synthetic minority over-sampling technique [J].Journal of Artificial Intelligence Research,2002,16(1):321- 357.
[15] DOOSTAN M ,CHOWDHURY B H .Power distribution system fault cause analysis by using association rule mining [J].Electric Power Systems Research,2017,152:140- 147.
[16] 刘威,张东霞,丁玉成,等.基于随机矩阵理论与熵理论的电网薄弱环节辨识方法 [J].中国电机工程学报,2017,37(20):5893- 5901.LIU Wei,ZHANG Dong-xia,DING Yun-cheng,et al.Power grid vulnerability identification methods based on random matrix theory and entropy theory [J].Proceedings of the CSEE,2017,37(20):5893- 5901.
[17] 李文立,郭凯红.D-S证据理论合成规则及冲突问题 [J].系统工程理论与实践,2010,30(08):1422- 1432.LI Wen-li,GUO Kai-hong.Combination rules of D-S evidence theory and conflict problem [J].Systems Engineering-Theory & Practice,2010,30(08):1422- 1432.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |