基于Stacking模型融合的失压故障识别算法
|
摘要
计量故障中的失压故障是目前电力计量系统常见的故障问题之一,传统的失压故障判定以终端告警为依据,判定维度单一,且终端告警存在误报、漏报的情况,导致了故障无法及时发现、无法实时处理。为了解决失压故障识别维度单一和终端漏报误报的问题,采用比较研究法,在前人使用机器学习算法解决故障识别问题的基础上,结合真实计量数据,构建失压关键指标,提出了一种基于Stacking模型融合的计量故障监测算法。经反复实例论证和理论测算,该算法相较于传统的机器学习算法,能够提升失压故障识别的效果,平均精确率0. 99以上。该种算法的提出为计量故障识别提供了一种新的解决方案,为失压故障后电量追补提供了一种依据,为提升计量系统管理水平增加了一种手段。
The fault-loss fault in the measurement fault is one of the common fault problems in the current power metering system. The traditional pressure-loss fault determination is based on1 the terminal alarm,the judgment dimension is single,and the terminal alarm has a false alarm and a false report,resulting in a fault. Unable to find in time,can't be processed in real time. In order to solve the problem of single-dimensional and terminal false-reporting of loss-of-voltage fault identification,the comparative research method is used.Based on the previous problems of using machine learning algorithms to solve fault identification problems,combined with real measurement data,the key indicators of pressure loss are constructed. A measurement fault monitoring algorithm based on stacking model fusion. Through repeated case demonstration and theoretical calculation,the algorithm can improve the effect of faultless fault recognition compared with the traditional machine learning algorithm,and the average accuracy rate is above 0. 99. The proposed algorithm provides a new solution for metering fault identification,which provides a basis for power chasing after voltage loss faults,and adds a means to improve the management level of metering systems.
The fault-loss fault in the measurement fault is one of the common fault problems in the current power metering system. The traditional pressure-loss fault determination is based on1 the terminal alarm,the judgment dimension is single,and the terminal alarm has a false alarm and a false report,resulting in a fault. Unable to find in time,can't be processed in real time. In order to solve the problem of single-dimensional and terminal false-reporting of loss-of-voltage fault identification,the comparative research method is used.Based on the previous problems of using machine learning algorithms to solve fault identification problems,combined with real measurement data,the key indicators of pressure loss are constructed. A measurement fault monitoring algorithm based on stacking model fusion. Through repeated case demonstration and theoretical calculation,the algorithm can improve the effect of faultless fault recognition compared with the traditional machine learning algorithm,and the average accuracy rate is above 0. 99. The proposed algorithm provides a new solution for metering fault identification,which provides a basis for power chasing after voltage loss faults,and adds a means to improve the management level of metering systems.
引文
[1]陈霞君,刘少凡,张济韬,等.现代电能计量系统综述[J].电工电气,2015(2):1-4.Chen Xiajun,Liu Shaofan,Zhang Jitao,et al. Review of modern e-lectric energy metering system[J]. Electrotechnics Electric,2015(2):1-4.
[2]王志刚,蔡桂华.电能计量系统发展简史[J].电子世界,2012(17):77-78.Wang Zhigang,Cai Guihua. A brief history of the development of e-lectric energy metering systems[J]. Electronics World,2012(17):77-78.
[3]葛海建.小波变换和神经网络在高压电力计量故障诊断系统中的应用研究[D].开封:河南大学,2013.
[4]赵建军,张素君.高压电力计量系统故障分析与建模[J].电测与仪表,2007,44(4):5-8.Zhao Jianjun,Zhang Sujun. Fault analysis and modeling for thehigh voltage electric power metering system[J]. Electrical Meas-urement&Instrumentation,2007,44(4):5-8.
[5]杨清河.高压电力计量系统故障分析与建模[J].通讯世界,2014(5):83-84.Yang Qinghe. Fault analysis and modeling for the high voltage electricpower metering system[J]. Telecom World,2014(5):83-84.
[6]陈劲游,彭昭煌,蔡春元.三相电能表失压故障追补电量在线计算[J].电力系统自动化,2013,37(19):100-104.Chen Jinyou,Peng Zhaohuang,Cai Chunyuan. On-line calculationof three-phase energy meter loss of voltage fault recovery[J]. Auto-mation of Electric Power Systems,2013,37(19):100-104.
[7]赵世华,桑大治.高压电力计量故障的分析与检测[J].大陆桥视野,2017(16):102.Zhao Shihua,Sang Dazhi. Analysis and detection of high voltagepower metering faults[J]. New Silk Road Horizon,2017(16):102.
[8]邓广昌,杨悦辉,李慧,等.基于萤火虫神经网络在失压故障识别中的应用[C]//2017智能电网信息化建设研讨会论文集,2017.
[9] Wolpert D H. Stacked generalization[J]. Neural Networks,1992,5(2):241-259.
[10] Breiman L. Bagging predictors[M]. Kluwer Academic Publishers,1996.
[11] Breiman L. Arcing Classifiers[J]. Annals of Statistics,1998,26(3):801-824.
[12]周星,丁立新,万润泽,等.分类器集成算法研究[J].武汉大学学报(理学版),2015(6):503-508.Zhou Xing,Ding Lixin,Wan Runze,et al. Research on classifierensemble algorithms[J]. Journal of Wuhan University(NaturalScience Edition),2015(6):503-508.
[13]张雨金,周杭霞. Stacking-SVM的短期光伏发电功率预测[J].中国计量大学学报,2018,29(2):121-127.Zhang Yujin,Zhou Hangxia. Short-term photovoltaic power forecastbased on Stacking-SVM[J]. Journal of China University of Metrol-ogy,2018,29(2):121-127.
[14]盛杰,刘岳,尹成语.基于多特征和Stacking算法的Android恶意软件检测方法[J].计算机系统应用,2018,27(2):197-201.Sheng Jie,Liu Yue,Yin Chengyu. Detection method of Androidmalware based on multi-feature and Stacking algorithm[J]. Com-puter Systems&Applications,2018,27(2):197-201.
[15]李航.统计学习方法[M].北京:清华大学出版社,2012.
[2]王志刚,蔡桂华.电能计量系统发展简史[J].电子世界,2012(17):77-78.Wang Zhigang,Cai Guihua. A brief history of the development of e-lectric energy metering systems[J]. Electronics World,2012(17):77-78.
[3]葛海建.小波变换和神经网络在高压电力计量故障诊断系统中的应用研究[D].开封:河南大学,2013.
[4]赵建军,张素君.高压电力计量系统故障分析与建模[J].电测与仪表,2007,44(4):5-8.Zhao Jianjun,Zhang Sujun. Fault analysis and modeling for thehigh voltage electric power metering system[J]. Electrical Meas-urement&Instrumentation,2007,44(4):5-8.
[5]杨清河.高压电力计量系统故障分析与建模[J].通讯世界,2014(5):83-84.Yang Qinghe. Fault analysis and modeling for the high voltage electricpower metering system[J]. Telecom World,2014(5):83-84.
[6]陈劲游,彭昭煌,蔡春元.三相电能表失压故障追补电量在线计算[J].电力系统自动化,2013,37(19):100-104.Chen Jinyou,Peng Zhaohuang,Cai Chunyuan. On-line calculationof three-phase energy meter loss of voltage fault recovery[J]. Auto-mation of Electric Power Systems,2013,37(19):100-104.
[7]赵世华,桑大治.高压电力计量故障的分析与检测[J].大陆桥视野,2017(16):102.Zhao Shihua,Sang Dazhi. Analysis and detection of high voltagepower metering faults[J]. New Silk Road Horizon,2017(16):102.
[8]邓广昌,杨悦辉,李慧,等.基于萤火虫神经网络在失压故障识别中的应用[C]//2017智能电网信息化建设研讨会论文集,2017.
[9] Wolpert D H. Stacked generalization[J]. Neural Networks,1992,5(2):241-259.
[10] Breiman L. Bagging predictors[M]. Kluwer Academic Publishers,1996.
[11] Breiman L. Arcing Classifiers[J]. Annals of Statistics,1998,26(3):801-824.
[12]周星,丁立新,万润泽,等.分类器集成算法研究[J].武汉大学学报(理学版),2015(6):503-508.Zhou Xing,Ding Lixin,Wan Runze,et al. Research on classifierensemble algorithms[J]. Journal of Wuhan University(NaturalScience Edition),2015(6):503-508.
[13]张雨金,周杭霞. Stacking-SVM的短期光伏发电功率预测[J].中国计量大学学报,2018,29(2):121-127.Zhang Yujin,Zhou Hangxia. Short-term photovoltaic power forecastbased on Stacking-SVM[J]. Journal of China University of Metrol-ogy,2018,29(2):121-127.
[14]盛杰,刘岳,尹成语.基于多特征和Stacking算法的Android恶意软件检测方法[J].计算机系统应用,2018,27(2):197-201.Sheng Jie,Liu Yue,Yin Chengyu. Detection method of Androidmalware based on multi-feature and Stacking algorithm[J]. Com-puter Systems&Applications,2018,27(2):197-201.
[15]李航.统计学习方法[M].北京:清华大学出版社,2012.