林峻;严英杰;盛戈皞;江秀臣;杨祎;陈玉峰;

• 1:上海交通大学电气工程系
• 2:国网山东省电力公司电力科学研究院

摘要(Abstract)：

针对变压器设备大数据状态评估过程中存在数据缺失以及异常数据等问题,提出了一种基于关联规则分析和神经网络的数据清洗策略。首先通过关联规则挖掘,建立了衡量状态监测量间关联程度的数学模型,找出具有强关联性的时间序列。然后利用基于密度的聚类算法检测出序列中的缺失值以及异常点,提出了考虑序列关联性的清洗流程和规则,有效区分可清洗的传感器数据异常和设备状态异常。针对可清洗的数据点,利用小波神经网络模型进行缺失数据预测和错误数据修正,并动态修正小波神经网络参数和组合预测,提高了网络的清洗效率和准确率。以实际变压器设备在线监测数据为例进行测试,测试结果表明序列数据的关联性分析和小波神经网络相结合,能够有效提高变压器在线监测数据清洗的准确度。

关键词(KeyWords)： 大数据;异常检测;数据清洗;关联规则;小波神经网络

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 林峻;严英杰;盛戈皞;江秀臣;杨祎;陈玉峰;

Email:

DOI: 10.13335/j.1000-3673.pst.2017.0141

参考文献(References)：

• [1]宋亚奇,周国亮,朱永利.智能电网大数据处理技术现状与挑战[J].电网技术,2013,37(4):927-935.Song Yaqi,Zhou Guoliang,Zhu Yongli.Present status and challenges of big data processing in smart grid[J].Power System Technology,2013,37(4):927-935(in Chinese).
• [2]张文亮,刘壮志,王明俊,等.智能电网的研究进展及发展趋势[J].电网技术,2009,33(13):1-11.Zhang Wenliang,Liu Zhuangzhi,Wang Mingjun,et al.Reasearch status and development trend of smart grid[J].Power System Technology,2009,33(13):1-11(in Chinese).
• [3]李国杰,程学旗.大数据研究:未来科技及经济社会发展的重大战略领域--大数据的研究现状与科学思考[J].中国科学院院刊,2012,27(6):647-656.Li Guojie,Cheng Xueqi.Research status and scientific thinking of big data[J].Strategy&Policy Decision Research,2012,27(6):647-656(in Chinese).
• [4]刁赢龙,盛万兴,刘科研,等.大规模配电网负荷数据在线清洗与修复方法研究[J].电网技术,2015,11(39):3134-3140.Diao Yinglong,Sheng Wanxing,Liu Keyan,et al.Research on online cleaning and repair methods of large-scale distribution network load data[J].Power System Technology,2015,11(39):3134-3140(in Chinese).
• [5]陈静云,周良,丁秋林.基于改进卡尔曼滤波的RFID数据清洗方法研究[J].计算机科学,2014,41(3):202-204.Chen Jingyun,Zhou Liang,Ding Qiulin.Cleaning method research of RFID data stream based on improved kalman filter[J].Computer Science,2014,41(3):202-204(in Chinese).
• [6]封慧英,周良.基于滑动窗口的RFID自适应数据清洗算法[J].计算机与现代化,2015(1):31-36.Feng Huiying,Zhou Liang.Adaptive RFID data cleaning algorithm based on sliding-window[J].Computer and Modernization,2015(1):31-36(in Chinese).
• [7]Meng L,Yu F.RFID data cleaning based on adaptive window[C]//Future Computer and Communication(ICFCC),2010 2nd International Conference on.Wuhua,China:IEEE,2010:V1-746-V1-749.
• [8]Massawe L V,Vermaak H,Kinyua J D M.An adaptive data cleaning scheme for reducing false negative reads in RFID data streams[C]//2012 IEEE International Conference on RFID(RFID).Orlando,FL,USA:IEEE,2012:157-164.
• [9]陈旭辉,王馨,柯铭.一种改进的基于RFID中间件的冗余数据清洗算法[J].微电子学与计算机,2013,30(7):154-158.Chen Xuhui,Wang Xin,Ke Ming.An improved algorithm in redundant data cleaning based on RFID middleware[J].Microelectronics&Computer,2013,30(7):154-158(in Chinese).
• [10]Hua F,Zhao H,Zhaoyan J,et al.BBS:An effective approach for RFID data cleaning[C]//Computer Science and Network Technology(ICCSNT),2012 2nd International Conference on.Changchun,China:IEEE,2012:1626-1629.
• [11]Hu K,Li L,Hu C,et al.A dynamic path data cleaning algorithm based on constraints for RFID data cleaning[C]//Fuzzy Systems and Knowledge Discovery(FSKD),2014 11th International Conference on.Xiamen,China:IEEE,2014:537-541.
• [12]Lin S,Xie C,Tang B,et al.The data mining application in the power quality monitoring data analysis[C]//Industrial Electronics and Applications(ICIEA),2016 IEEE 11th Conference on.Hefei,China:IEEE,2016:338-342.
• [13]Chen J,Li W,Lau A,et al.Automated load curve data cleansing in power systems[J].IEEE Transactions on Smart Grid,2010,1(2):213-221.
• [14]Tao Y,Chen H.A hybrid wind power prediction method[C]//Power and Energy Society General Meeting(PESGM).Boston,MA,USA:IEEE,2016:1-5.
• [15]严英杰,盛戈皞,陈玉峰,等.基于时间序列分析的输变电设备状态大数据清洗方法[J].电力系统自动化,2015,39(7):138-144.Yan Yingjie,Sheng Gehao,Chen Yufeng,et al.Cleaning method for big data of power transmission and transformation equipment state based on time sequence analysis[J].Automation of Electric Power System,2015,39(7):138-144(in Chinese).
• [16]严英杰,盛戈皞,陈玉峰,等.基于大数据分析的输变电设备状态数据异常检测方法[J].中国电机工程学报,2015,35(1):52-59.Yan Yingjie,Sheng Gehao,Chen Yufeng,et al.A method for anomaly detection of state information of power equipment based on big data analysis[J].Proceedings of the CSEE,2015,35(1):52-59(in Chinese).
• [17]李黎,张登,谢龙君,等.采用关联规则综合分析和变权重系数的电力变压器状态评估方法[J].中国电机工程学报,2013,33(24):152-159.Li Li,Zhang Deng,Xie Longjun,et al.A condition assessment method of power transformers based on association rules and variable weight coefficients[J].Proceedings of the CSEE,2013,33(24):152-159(in Chinese).
• [18]谢龙君,李黎,程勇,等.融合集对分析和关联规则的变压器故障诊断方法[J].中国电机工程学报,2015,35(2):277-286.Xie Longjun,Li Li,Cheng Yong,et al.A fault diagnosis method of power transformers by integrated set pair analysis and association rules[J].Proceedings of the CSEE,2015,35(2):277-286(in Chinese).
• [19]王贺,胡志坚,陈珍,等.基于集合经验模态分解和小波神经网络的短期风功率组合预测[J].电工技术学报,2013,28(9):137-144.Wang He,Hu Zhijian,Chen Zhen,et al.A hybrid model for wind power forecasting based on ensemble empirical mode decomposition and wavelet neural networks[J].Transactions of China Electrotechnical Society,2013,9(28):137-144(in Chinese).
• [20]程声烽,程小华,杨露.基于改进粒子群算法的小波神经网络在变压器故障诊断中的应用[J].电力系统保护与控制,2014,42(19):37-42.Cheng Shengfeng,Cheng Xiaohua,Yang Lu.Application of wavelet neural network with improved particle swarm optimization algorithm in power[J].Power System Protection and Control,2014,42(19):37-42(in Chinese).