基于栈式降噪自编码器的输变电设备状态数据清洗方法
|
摘要
针对当前输变电设备状态监测数据清洗过程繁琐,易造成信息丢失等问题,利用栈式降噪自编码器对"脏"数据的还原解析能力及异常状态特征提取能力,提出了一种基于栈式降噪自编码器的数据清洗方法。对设备正常工况及异常运行状态数据分别利用栈式降噪自编码器进行训练学习,获取损失函数向量,形成奇异点、缺失数据修复模型和设备异常运行状态数据降噪模型。通过核密度估计确定训练样本损失函数上限和容限时窗,根据测试数据重构误差和异常数据时长与损失函数上限和容限时窗间的关系,对"脏"数据进行分类处理。对某变压器油色谱中总烃含量及某导线温度数据进行清洗,结果表明所提方法能有效辨识奇异点、缺失信息及异常运行状态数据,并对奇异点、缺失值进行修复重构。在设备异常运行时刻,可以有效过滤干扰数据。
The condition monitoring data cleaning of power transmission and transformation equipment has some problems at present,such as loss of information,inaccuracy and complicated procedure.A data cleaning method based on stacked denoising autoencoders is proposed,which has the advantages of reconstructing noisy information and extracting features of abnormal status.The monitoring data of the equipment under normal and abnormal conditions is trained by the stacked denoising autoencoder to obtain the loss function vectors and build the outlier,missing data restoration model and abnormal status data denoising model.The upper limit of loss function and tolerant window are determined by means of kernel density estimation.By comparing reconstruction error and the lasting time of abnormal data with the upper limit of loss function and tolerant window,the dirty data is classified and cleaned by different models.The method is tested on total hydrocarbon concentration of oil chromatography data and conductor temperature data.An analysis of the examples shows that the method is able to automatically identify different types of abnormal data.Singular points and missing data are directly repaired by reconstruction.In the abnormal working condition,the denoising model can extract the actual effective information and eliminate the interference.
The condition monitoring data cleaning of power transmission and transformation equipment has some problems at present,such as loss of information,inaccuracy and complicated procedure.A data cleaning method based on stacked denoising autoencoders is proposed,which has the advantages of reconstructing noisy information and extracting features of abnormal status.The monitoring data of the equipment under normal and abnormal conditions is trained by the stacked denoising autoencoder to obtain the loss function vectors and build the outlier,missing data restoration model and abnormal status data denoising model.The upper limit of loss function and tolerant window are determined by means of kernel density estimation.By comparing reconstruction error and the lasting time of abnormal data with the upper limit of loss function and tolerant window,the dirty data is classified and cleaned by different models.The method is tested on total hydrocarbon concentration of oil chromatography data and conductor temperature data.An analysis of the examples shows that the method is able to automatically identify different types of abnormal data.Singular points and missing data are directly repaired by reconstruction.In the abnormal working condition,the denoising model can extract the actual effective information and eliminate the interference.
引文
[1]薛禹胜,赖业宁.大能源思维与大数据思维的融合:(一)大数据与电力大数据[J].电力系统自动化,2016,40(1):1-8.DOI:10.7500/AEPS20151208005.XUE Yusheng,LAI Yening.Integration of macro energy thinking and big data thinking:Part one big data and power big data[J].Automation of Electric Power Systems,2016,40(1):1-8.DOI:10.7500/AEPS20151208005.
[2]彭小圣,邓迪元,程时杰,等.面向智能电网应用的电力大数据关键技术[J].中国电机工程学报,2015,35(3):503-511.PENG Xiaosheng,DENG Diyuan,CHENG Shijie,et al.Key technologies of electric power big data and its application prospects in smart grid[J].Proceedings of the CSEE,2015,35(3):503-511.
[3]周宁慧,王彬,王治华,等.基于集合论估计的电网状态辨识:(四)离群点识别[J].电力系统自动化,2016,40(8):22-28.DOI:10.7500/AEPS20150529016.ZHOU Ninghui,WANG Bin,WANG Zhihua,et al.Power system state identification based on set theory estimation:Part four outlier identification[J].Automation of Electric Power Systems,2016,40(8):22-28.DOI:10.7500/AEPS20150529016.
[4]薛禹胜,赖业宁.大能源思维与大数据思维的融合:(二)应用及探索[J].电力系统自动化,2016,40(8):1-13.DOI:10.7500/AEPS20160311004.XUE Yusheng,LAI Yening.Integration of macro energy thinking and big data thinking:Part two applications and explorations[J].Automation of Electric Power Systems,2016,40(8):1-13.DOI:10.7500/AEPS20160311004.
[5]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.DOI:10.7500/AEPS20140111003.YAN Yingjie,SHENG Gehao,CHEN Yufeng,et al.Cleaning method for big data of power transmission and transformation equipment state based on times sequence analysis[J].Automation of Electric Power Systems,2015,39(7):138-144.DOI:10.7500/AEPS20140111003.
[6]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,2015,39(11):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,2015,39(11):3134-3140.
[7]娄建楼,胥佳,陆恒,等.基于功率曲线的风电机组数据清洗算法[J].电力系统自动化,2016,40(10):116-121.DOI:10.7500/AEPS20151014003.LOU Jianlou,XU Jia,LU Heng,et al.Wind turbine datacleaning algorithm based on power curve[J].Automation of Electric Power Systems,2016,40(10):116-121.DOI:10.7500/AEPS20151014003.
[8]YANG Xiaowei,ZHANG Guangquan,LU Jie,et al.A Kernel fuzzy c-means clustering-based fuzzy support vector machine algorithm for classification problems with outliers or noises[J].IEEE Trans on Fuzzy Systems,2011,19(1):105-115.
[9]唐懿芳,钟达夫,严小卫.基于聚类模式的数据清洗技术[J].计算机应用,2004,24(5):116-119.TANG Yifang,ZHONG Dafu,YAN Xiaowei.Data cleaning based on clustering technique[J].Computer Application,2004,24(5):116-119.
[10]樊金辉,岳昆,张骥先,等.基于D-S证据理论的不确定数据清洗[J].云南大学学报(自然科学版),2014,36(6):815-822.FAN Jinhui,YUE Kun,ZHANG Jixian,et al.Cleaning uncertain data based on the D-S evidence theory[J].Journal of Yunnan University(Natural Sciences),2014,36(6):815-822.
[11]MENG Shushu,HUANG Longting,WANG Wenqin.Tensor decomposition and PCA jointed algorithm for hyperspectral image denoising[J].IEEE Geoscience and Remote Sensing Letters,2016,13(7):897-901.
[12]VARON C,ALZATE C,SUYKENS J A K.Noise level estimation for model selection in kernel PCA denoising[J].IEEE Trans on Neural Networks and Learning Systems,2015,26(11):2650-2663.
[13]HINTON G,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313:504-507.
[14]BENGIO Y.Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-127.
[15]VINCENT P,LAROCHELLE H,BENGIO Y,et al.Extracting and composing robust features with denoising autoencoders[C]//25th International Conference on Machine Learning,June 5-9,2008,Helsinki,Finland:1096-1103.
[16]VINCENT P,LAROCHELLE H,LAJOIE I,et al.Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J].Journal of Machine Learning Research,2010,11(12):3371-3408.
[17]刘树春.基于支持向量机和深度学习的分类算法研究[D].上海:华东师范大学,2015.
[18]董其国.电力变压器故障与诊断[M].北京:中国电力出版社,2001.
[19]任丽佳.基于导线张力的动态提高输电线路输送容量技术[D].上海:上海交通大学,2008.
[2]彭小圣,邓迪元,程时杰,等.面向智能电网应用的电力大数据关键技术[J].中国电机工程学报,2015,35(3):503-511.PENG Xiaosheng,DENG Diyuan,CHENG Shijie,et al.Key technologies of electric power big data and its application prospects in smart grid[J].Proceedings of the CSEE,2015,35(3):503-511.
[3]周宁慧,王彬,王治华,等.基于集合论估计的电网状态辨识:(四)离群点识别[J].电力系统自动化,2016,40(8):22-28.DOI:10.7500/AEPS20150529016.ZHOU Ninghui,WANG Bin,WANG Zhihua,et al.Power system state identification based on set theory estimation:Part four outlier identification[J].Automation of Electric Power Systems,2016,40(8):22-28.DOI:10.7500/AEPS20150529016.
[4]薛禹胜,赖业宁.大能源思维与大数据思维的融合:(二)应用及探索[J].电力系统自动化,2016,40(8):1-13.DOI:10.7500/AEPS20160311004.XUE Yusheng,LAI Yening.Integration of macro energy thinking and big data thinking:Part two applications and explorations[J].Automation of Electric Power Systems,2016,40(8):1-13.DOI:10.7500/AEPS20160311004.
[5]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.DOI:10.7500/AEPS20140111003.YAN Yingjie,SHENG Gehao,CHEN Yufeng,et al.Cleaning method for big data of power transmission and transformation equipment state based on times sequence analysis[J].Automation of Electric Power Systems,2015,39(7):138-144.DOI:10.7500/AEPS20140111003.
[6]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,2015,39(11):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,2015,39(11):3134-3140.
[7]娄建楼,胥佳,陆恒,等.基于功率曲线的风电机组数据清洗算法[J].电力系统自动化,2016,40(10):116-121.DOI:10.7500/AEPS20151014003.LOU Jianlou,XU Jia,LU Heng,et al.Wind turbine datacleaning algorithm based on power curve[J].Automation of Electric Power Systems,2016,40(10):116-121.DOI:10.7500/AEPS20151014003.
[8]YANG Xiaowei,ZHANG Guangquan,LU Jie,et al.A Kernel fuzzy c-means clustering-based fuzzy support vector machine algorithm for classification problems with outliers or noises[J].IEEE Trans on Fuzzy Systems,2011,19(1):105-115.
[9]唐懿芳,钟达夫,严小卫.基于聚类模式的数据清洗技术[J].计算机应用,2004,24(5):116-119.TANG Yifang,ZHONG Dafu,YAN Xiaowei.Data cleaning based on clustering technique[J].Computer Application,2004,24(5):116-119.
[10]樊金辉,岳昆,张骥先,等.基于D-S证据理论的不确定数据清洗[J].云南大学学报(自然科学版),2014,36(6):815-822.FAN Jinhui,YUE Kun,ZHANG Jixian,et al.Cleaning uncertain data based on the D-S evidence theory[J].Journal of Yunnan University(Natural Sciences),2014,36(6):815-822.
[11]MENG Shushu,HUANG Longting,WANG Wenqin.Tensor decomposition and PCA jointed algorithm for hyperspectral image denoising[J].IEEE Geoscience and Remote Sensing Letters,2016,13(7):897-901.
[12]VARON C,ALZATE C,SUYKENS J A K.Noise level estimation for model selection in kernel PCA denoising[J].IEEE Trans on Neural Networks and Learning Systems,2015,26(11):2650-2663.
[13]HINTON G,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313:504-507.
[14]BENGIO Y.Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-127.
[15]VINCENT P,LAROCHELLE H,BENGIO Y,et al.Extracting and composing robust features with denoising autoencoders[C]//25th International Conference on Machine Learning,June 5-9,2008,Helsinki,Finland:1096-1103.
[16]VINCENT P,LAROCHELLE H,LAJOIE I,et al.Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J].Journal of Machine Learning Research,2010,11(12):3371-3408.
[17]刘树春.基于支持向量机和深度学习的分类算法研究[D].上海:华东师范大学,2015.
[18]董其国.电力变压器故障与诊断[M].北京:中国电力出版社,2001.
[19]任丽佳.基于导线张力的动态提高输电线路输送容量技术[D].上海:上海交通大学,2008.