基于状态识别的经验模态分解法火电厂运行数据预处理
|
摘要
针对火电机组运行监测数据量大且复杂情况下的去噪问题,提出一种基于状态识别的改进经验模态分解去噪(SREMD)算法。该算法以经验模态分解(EMD)方法为基础,首先运用基于拉伊达(Pauta)准则的滤波方法去除显著异常数据,然后根据数据连续变化率动态识别机组运行状态,最后根据机组运行状态的稳态过程和过渡过程分别进行针对性EMD去噪,以适应火电机组的状态切换特性。将该算法用于实际机组运行数据,结果表明,本文算法有效完成了火电机组监测数据的去噪预处理,在保持信号整体趋势的基础上能达到更好的去噪效果。
The data from the operating thermal power units are very large and contains complex noise, which is hard to eliminate the noise thoroughly. To solve this problem, an improved empirical mode decomposition filtering algorithm based on the state recognition(SREMD) was proposed. On the basis of empirical mode decomposition(EMD), this SREMD algorithm firstly eliminates the significantly abnormal data by using a filtering method which is based on the Pauta criterion. Then, it recognizes the running states of the unit according to continuous change rate of the data. Finally, it performs corresponding EMD denoising according to the steady state and transition process of unit operation, to adapt to the state switching characteristics. Moreover, this algorithm was applied for actual unit operation data. The results show that, the proposed SREMD algorithm effectively completed the pre-processing of the monitoring data of thermal power units and achieved a better denoising effect on the basis of maintaining the overall trend of the signal.
The data from the operating thermal power units are very large and contains complex noise, which is hard to eliminate the noise thoroughly. To solve this problem, an improved empirical mode decomposition filtering algorithm based on the state recognition(SREMD) was proposed. On the basis of empirical mode decomposition(EMD), this SREMD algorithm firstly eliminates the significantly abnormal data by using a filtering method which is based on the Pauta criterion. Then, it recognizes the running states of the unit according to continuous change rate of the data. Finally, it performs corresponding EMD denoising according to the steady state and transition process of unit operation, to adapt to the state switching characteristics. Moreover, this algorithm was applied for actual unit operation data. The results show that, the proposed SREMD algorithm effectively completed the pre-processing of the monitoring data of thermal power units and achieved a better denoising effect on the basis of maintaining the overall trend of the signal.
引文
[1]杨世铭,陶文铨.传热学[J].4版.北京:高等教育出版社,2006:37-45.YANG Shiming,TAO Wenquan.Heat transfer[M].4th ed.Beijing:Higher Education Press,2006:37-45.
[2]陈雪.热工测量数据预处理方法研究[D].北京:华北电力大学,2014:6-9.CHEN Xue.Research on data preprocessing method for thermal parameters[D].Beijing:North China Electric Power University,2014:6-9.
[3]FAMILI A,SHEN W M,RICHARD W,et al.Data preprocessing and intelligent data analysis[J].Intelligent Data Analysis,1997,1(1):3-23.
[4]WANG C L,ZHANG C L,ZHANG P T.Denoising algorithm based on wavelet adaptive threshold[J].Physics Procedia,2012,24(1):678-685.
[5]朱龙霞,肖明美,栗涛,等.基于时间序列分析的火电机组运行优化研究[J].河北工业科技,2017(2):127-131.ZHU Longxia,XIAO Mingmei,LI Tao,et al.Research of operation optimization of thermal power unit based on time series analysis[J].Hebei Industrial Technology,2017(2):127-131.
[6]刘丽平,叶春,忻建华.电厂在线性能分析及故障诊断系统[J].热力发电,2003,32(11):76-77.LIU Liping,YE Chun,XIN Jianhua.Power plant on-line performance analysis and fault diagnosis system[J].Thermal Power Generation,2003,32(11):76-77.
[7]马海林,孙秋红,徐欣航.基于数据挖掘技术的电厂运行参数目标值优化[J].河北工业科技,2012(5):303-307.MA Hailin,SUN Qiuhong,XU Xinhang.Study on optimization of power plant running parameters based on data minning[J].Hebei Industrial Technology,2012(5):303-307.
[8]李辉,陈教超,司风琪,等.数据预处理技术在电厂运行优化系统中的应用研究[J].华东电力,2007(11):110-113.LI Hui,CHEN Jiaochao,SI Fengqi,et al.Application of data preprocessing techonlogy to power plant performance optimization systems[J].East China Electric Power,2007(11):110-113.
[9]王一蓉,王瑞杰,陈文刚,等.基于遗传优化的调控系统缺失数据填补算法[J].电力系统保护与控制,2016,44(21):182-186.WANG Yirong,WANG Ruijie,CHEN Wengang,et al.Amissing data filling algorithm for dispatching and control system based on genetic optimization[J].Power System Protection and Control,2016,44(21):182-186.
[10]史林军,周佳佳,温荣超,等.基于经验模态分解与小波分析相结合的风电功率平滑控制[J].电力系统保护与控制,2016,44(24):9-16.SHI Linjun,ZHOU Jiajia,WEN Rongchao,et al.Power smoothing control of wind power based on combination of empirical mode decomposition and wavelet analysis[J].Power System Protection and Control,2016,44(24):9-16.
[11]杨大勇,葛琪,董永超,等.基于K均值聚类的光伏电站运行状态模式识别研究[J].电力系统保护与控制,2016,44(14):25-30.YANG Dayong,GE Qi,DONG Yongchao,et al.Research on operation state pattern recognition of PV station based on the principle of K-means clustering[J].Power System Protection and Control,2016,44(14):25-30.
[12]杨雯宇.基于稳态检测的电厂数据预处理研究[D].北京:华北电力大学,2017:6-26.YANG Wenyu.Analysis on power plant data preprocessing based on steady state detection[D].Beijing:North China Electric Power University,2017:6-26.
[13]苏舟,李灿,姚李孝,等.电力负荷数据预处理研究及应用[J].电网与清洁能源,2017,33(5):40-43.SU Zhou,LI Can,YAO Lixiao,et al.Research and application of pretreatment of electrical load data[J].Power System and Clean Energy,2017,33(5):40-43.
[14]刘福国,王学同,苏相河,等.基于系统测量冗余的电厂异常运行数据检测与校正[J].中国电机工程学报,2003(7):204-207.LIU Fuguo,WANG Xuetong,SU Xianghe,et al.Detection and correction on the abnormal operation data based on measurement in a power plant[J].Proceedings of the CSEE,2003(7):204-207.
[15]GUMBELL E J.Statistics of extremes[J].Applied Ocean Research,1958,43(1):1-30.
[16]ZHAO J,ZHANG G,LA SCALA M,et al.Multistage phasor-aided bad data detection and identification[C].IEEE Power&Energy Society General Meeting,2015(GHTCE).
[17]HUANG N E.Review of empirical mode decomposition analysis[J].Proceedings of SPIE,2001(4391):71-79.
[18]REHMAN N,MANDIC D P.Multivariate empirical mode decomposition[J].Proceedings Mathematical Physical&Engineering Sciences,2010,466(2117):1291-1302.
[19]HUANG N E,SHEN Z,LONG S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings Mathematical Physical&Engineering Sciences,1998,454(1971):903-995.
[20]刘霞,黄阳,黄敬,等.基于经验模态分解(EMD)的小波熵阈值地震信号去噪[J].吉林大学学报(地球科学版),2016,46(1):262-269.LIU Xia,HUANG Yang,HUANG Jing,et al.Wavelet entropy threshold seismic signal denoising based on empirical mode decomposition(EMD)[J].Journal of Jilin University(Earth Science Edition),2016,46(1):262-269.
[21]陶珂,朱建军.多指标融合的小波去噪最佳分解尺度选择方法[J].测绘学报,2012,41(5):749-755.TAO Ke,ZHU Jianjun.A hybrid indicator for determining the best decomposition scale of wavelet denoising[J].Chinese Journal of Chemical Engineering,2012,41(5):749-755.
[22]VOLKER D.Rhythm and speech rate:a variation coefficient forΔe[J].Language and Language-Processing,2006(1):231-241.
[2]陈雪.热工测量数据预处理方法研究[D].北京:华北电力大学,2014:6-9.CHEN Xue.Research on data preprocessing method for thermal parameters[D].Beijing:North China Electric Power University,2014:6-9.
[3]FAMILI A,SHEN W M,RICHARD W,et al.Data preprocessing and intelligent data analysis[J].Intelligent Data Analysis,1997,1(1):3-23.
[4]WANG C L,ZHANG C L,ZHANG P T.Denoising algorithm based on wavelet adaptive threshold[J].Physics Procedia,2012,24(1):678-685.
[5]朱龙霞,肖明美,栗涛,等.基于时间序列分析的火电机组运行优化研究[J].河北工业科技,2017(2):127-131.ZHU Longxia,XIAO Mingmei,LI Tao,et al.Research of operation optimization of thermal power unit based on time series analysis[J].Hebei Industrial Technology,2017(2):127-131.
[6]刘丽平,叶春,忻建华.电厂在线性能分析及故障诊断系统[J].热力发电,2003,32(11):76-77.LIU Liping,YE Chun,XIN Jianhua.Power plant on-line performance analysis and fault diagnosis system[J].Thermal Power Generation,2003,32(11):76-77.
[7]马海林,孙秋红,徐欣航.基于数据挖掘技术的电厂运行参数目标值优化[J].河北工业科技,2012(5):303-307.MA Hailin,SUN Qiuhong,XU Xinhang.Study on optimization of power plant running parameters based on data minning[J].Hebei Industrial Technology,2012(5):303-307.
[8]李辉,陈教超,司风琪,等.数据预处理技术在电厂运行优化系统中的应用研究[J].华东电力,2007(11):110-113.LI Hui,CHEN Jiaochao,SI Fengqi,et al.Application of data preprocessing techonlogy to power plant performance optimization systems[J].East China Electric Power,2007(11):110-113.
[9]王一蓉,王瑞杰,陈文刚,等.基于遗传优化的调控系统缺失数据填补算法[J].电力系统保护与控制,2016,44(21):182-186.WANG Yirong,WANG Ruijie,CHEN Wengang,et al.Amissing data filling algorithm for dispatching and control system based on genetic optimization[J].Power System Protection and Control,2016,44(21):182-186.
[10]史林军,周佳佳,温荣超,等.基于经验模态分解与小波分析相结合的风电功率平滑控制[J].电力系统保护与控制,2016,44(24):9-16.SHI Linjun,ZHOU Jiajia,WEN Rongchao,et al.Power smoothing control of wind power based on combination of empirical mode decomposition and wavelet analysis[J].Power System Protection and Control,2016,44(24):9-16.
[11]杨大勇,葛琪,董永超,等.基于K均值聚类的光伏电站运行状态模式识别研究[J].电力系统保护与控制,2016,44(14):25-30.YANG Dayong,GE Qi,DONG Yongchao,et al.Research on operation state pattern recognition of PV station based on the principle of K-means clustering[J].Power System Protection and Control,2016,44(14):25-30.
[12]杨雯宇.基于稳态检测的电厂数据预处理研究[D].北京:华北电力大学,2017:6-26.YANG Wenyu.Analysis on power plant data preprocessing based on steady state detection[D].Beijing:North China Electric Power University,2017:6-26.
[13]苏舟,李灿,姚李孝,等.电力负荷数据预处理研究及应用[J].电网与清洁能源,2017,33(5):40-43.SU Zhou,LI Can,YAO Lixiao,et al.Research and application of pretreatment of electrical load data[J].Power System and Clean Energy,2017,33(5):40-43.
[14]刘福国,王学同,苏相河,等.基于系统测量冗余的电厂异常运行数据检测与校正[J].中国电机工程学报,2003(7):204-207.LIU Fuguo,WANG Xuetong,SU Xianghe,et al.Detection and correction on the abnormal operation data based on measurement in a power plant[J].Proceedings of the CSEE,2003(7):204-207.
[15]GUMBELL E J.Statistics of extremes[J].Applied Ocean Research,1958,43(1):1-30.
[16]ZHAO J,ZHANG G,LA SCALA M,et al.Multistage phasor-aided bad data detection and identification[C].IEEE Power&Energy Society General Meeting,2015(GHTCE).
[17]HUANG N E.Review of empirical mode decomposition analysis[J].Proceedings of SPIE,2001(4391):71-79.
[18]REHMAN N,MANDIC D P.Multivariate empirical mode decomposition[J].Proceedings Mathematical Physical&Engineering Sciences,2010,466(2117):1291-1302.
[19]HUANG N E,SHEN Z,LONG S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings Mathematical Physical&Engineering Sciences,1998,454(1971):903-995.
[20]刘霞,黄阳,黄敬,等.基于经验模态分解(EMD)的小波熵阈值地震信号去噪[J].吉林大学学报(地球科学版),2016,46(1):262-269.LIU Xia,HUANG Yang,HUANG Jing,et al.Wavelet entropy threshold seismic signal denoising based on empirical mode decomposition(EMD)[J].Journal of Jilin University(Earth Science Edition),2016,46(1):262-269.
[21]陶珂,朱建军.多指标融合的小波去噪最佳分解尺度选择方法[J].测绘学报,2012,41(5):749-755.TAO Ke,ZHU Jianjun.A hybrid indicator for determining the best decomposition scale of wavelet denoising[J].Chinese Journal of Chemical Engineering,2012,41(5):749-755.
[22]VOLKER D.Rhythm and speech rate:a variation coefficient forΔe[J].Language and Language-Processing,2006(1):231-241.