基于大数据的多尺度状态监测方法及应用
|
摘要
现代化工业系统结构复杂、集成度高,对设备的安全性、可靠性提出了更高的要求,状态监测技术愈发受到重视。随着信息化的深入,信息系统数据仓库中大数据的存在为基于数据驱动的状态监测方法提供了良好的平台。论文研究了一类复杂多尺度系统的状态监测问题,其状态参数随时间的流逝缓慢变化并在主导尺度上具有单调增的特性,针对这类系统提出了一种状态监测方法—以大数据为基础,运用多尺度分析方法,构建状态监测参数反映设备的状态。论文主要研究内容和研究成果包括：
1.分析了现代工业生产过程大数据的特点。随着检测技术的进步,生产过程产生的数据己不仅仅具有海量性这一传统认知特征,声音、图像等非结构化数据的引入使数据内涵更加丰富。此外以小波变换为代表的时频分析技术的成熟,数据多尺度特性日益受到重视,对大数据进行多尺度分析能够更好的提取数据关联规则、寻找变量间联系、克服传统数据处理无法兼顾整体趋势分析及局部波动相似性分析的不足。
2.提出了尺度熵与尺度(?)的概念,利用尺度熵与尺度(?)反映变量的多尺度特性,探索变量在不同尺度上的分布及其随时间变化的规律,并以此为基础描述了研究对象的数学特性,限定了论文提出算法的适用范围。
3.提出了一种基于大数据的多尺度状态监测方法。由于现代化工业系统具有结构复杂、设备众多的特点,采用传统方法难以达到复杂系统状态监测的要求。因此论文将多种算法有机结合,提出了一种适用于状态参数随时间的流逝变化、主导尺度上具有单调增特性的复杂多尺度系统的状态监测方法。算法在传统的基于模型的状态监测方法基础上,改进了以下环节：
(1)将系统运行过程分为动态工况与稳态工况,分别建立动态工况基准模型与稳态工况基准模型,而后将基准模型的预测值与实际值比较构成动态残差与稳态残差,并对二者进行信息融合获得残差的最优估计,在一定程度上克服了系统动态过程建模精度低对状态监测结果的影响；
(2)针对大数据的海量性,引入信息粒化将残差的串行处理转化为信息粒的并行处理,极大提高了计算效率,降低了计算时间；
(3)利用对象的多尺度特性对融合残差进行多尺度分析,从不同尺度提取信息并构造状态监测函数,滤除未建模因素等噪声干扰,反映对象运行状态。
4.以电厂磨煤机磨辊磨损程度的状态监测以及超超临界机组辐射受热面灰污程度的状态监测为例,介绍了基于大数据的多尺度状态监测算法应用过程。通过对为期两年的65万组数据分析,构建了磨煤机磨辊磨损指数,较好的反映了其磨损状况。辐射受热面灰污指数的构建为吹灰优化提供了依据。仿真验证表明论文提出的算法能够有效构造状态监测参数,并为控制优化、设备预知维修等提供技术依据。
The modern industrial system has the characteristics of complex structure and high integration, which presents higher challenge on the equipment security and reliability. Therefore, condition monitoring technology has attracted more and more attention. With the development of information technology, big data in database provides an ideal platform for data-driven condition monitoring methods. In this paper, a condition monitoring method is proposed for complex multi-scale systems in which the state parameters change slowly and cumulatively on dominant scale in the long term. Based on big data, condition monitoring parameters are constructed to reflect the equipment state using multi-scale analysis. The main contributions of this dissertation can be summarized as followings:
1. The characteristics of big data in modern industrial system are analyzed. With the development of measurement technology, the characteristics of big data represent more than just the volume. Sound, images and other unstructured data generated by productive processes enrich the connotation of data. As the time-frequency analysis technology matures, for instance, multi-scale analysis, which has received increasing attention. Multi-scale analysis can extract association rules, discover association between variables, and overcome the weakness of traditional data processing method which cannot balance overall trend and local similarity fluctuations.
2. Scale entropy and scale exergy are proposed to reflect the system's multi-scale characteristics. The distribution law of variables on different scales is explored. Then based on scale entropy and scale exergy, the mathematical description of research subjects is put forward to restrict the application scope of the method proposed by the paper.
3. A multi-scale condition monitoring method based on big data was proposed. As the complex structures and numbers of devices are growing in modern industrial systems, requirement of condition monitoring cannot be achieved by using single traditional methods. Based on the research of different disciplines and combining algorithms, this paper presents a new condition monitoring method for the systems, in which the state parameters change slowly and cumulatively on dominant scale in the long term. The traditional model-based condition monitoring algorithm can be improved through this novel method in the aspects:
(1) The systems state is divided into dynamic and steady state. The reference models are established respectively. Then, fusion residual error is obtained by fusing dynamic residual error and stead-state residual error. Thus the influence of the inaccurate dynamic state reference model can be overcome to some extent;
(2) Information granulation is applied to handle with the volume data. Thus the processing of residual error can be transformed from serial into parallel, which greatly improves the computational efficiency and reduces computing time-consuming;
(3) Based on the multi-scale nature of processes, multi-scale analysis is applied to fusion residual error. Noise such as unmolded factors can be eliminated and condition monitoring parameter is constructed by extracted information from different scales.
4. The condition monitoring of milling roller abrasion characteristics and ash deposition detection of radiant heating surface are taken as examples to show the computational process of multi-scale condition monitoring algorithm based on big data. Abrasion index is constructed to reflect the abrasion characteristics based on the analysis of six hundred and fifty thousand data samples. Ash deposition index provide a solution to the problem of condition monitoring on deposition of water cooling wall. The algorithm presented in the paper can construct condition monitoring parameters effectively, which provides a technical basis for the control optimization and equipment predictive maintenance.
1.分析了现代工业生产过程大数据的特点。随着检测技术的进步,生产过程产生的数据己不仅仅具有海量性这一传统认知特征,声音、图像等非结构化数据的引入使数据内涵更加丰富。此外以小波变换为代表的时频分析技术的成熟,数据多尺度特性日益受到重视,对大数据进行多尺度分析能够更好的提取数据关联规则、寻找变量间联系、克服传统数据处理无法兼顾整体趋势分析及局部波动相似性分析的不足。
2.提出了尺度熵与尺度(?)的概念,利用尺度熵与尺度(?)反映变量的多尺度特性,探索变量在不同尺度上的分布及其随时间变化的规律,并以此为基础描述了研究对象的数学特性,限定了论文提出算法的适用范围。
3.提出了一种基于大数据的多尺度状态监测方法。由于现代化工业系统具有结构复杂、设备众多的特点,采用传统方法难以达到复杂系统状态监测的要求。因此论文将多种算法有机结合,提出了一种适用于状态参数随时间的流逝变化、主导尺度上具有单调增特性的复杂多尺度系统的状态监测方法。算法在传统的基于模型的状态监测方法基础上,改进了以下环节：
(1)将系统运行过程分为动态工况与稳态工况,分别建立动态工况基准模型与稳态工况基准模型,而后将基准模型的预测值与实际值比较构成动态残差与稳态残差,并对二者进行信息融合获得残差的最优估计,在一定程度上克服了系统动态过程建模精度低对状态监测结果的影响；
(2)针对大数据的海量性,引入信息粒化将残差的串行处理转化为信息粒的并行处理,极大提高了计算效率,降低了计算时间；
(3)利用对象的多尺度特性对融合残差进行多尺度分析,从不同尺度提取信息并构造状态监测函数,滤除未建模因素等噪声干扰,反映对象运行状态。
4.以电厂磨煤机磨辊磨损程度的状态监测以及超超临界机组辐射受热面灰污程度的状态监测为例,介绍了基于大数据的多尺度状态监测算法应用过程。通过对为期两年的65万组数据分析,构建了磨煤机磨辊磨损指数,较好的反映了其磨损状况。辐射受热面灰污指数的构建为吹灰优化提供了依据。仿真验证表明论文提出的算法能够有效构造状态监测参数,并为控制优化、设备预知维修等提供技术依据。
The modern industrial system has the characteristics of complex structure and high integration, which presents higher challenge on the equipment security and reliability. Therefore, condition monitoring technology has attracted more and more attention. With the development of information technology, big data in database provides an ideal platform for data-driven condition monitoring methods. In this paper, a condition monitoring method is proposed for complex multi-scale systems in which the state parameters change slowly and cumulatively on dominant scale in the long term. Based on big data, condition monitoring parameters are constructed to reflect the equipment state using multi-scale analysis. The main contributions of this dissertation can be summarized as followings:
1. The characteristics of big data in modern industrial system are analyzed. With the development of measurement technology, the characteristics of big data represent more than just the volume. Sound, images and other unstructured data generated by productive processes enrich the connotation of data. As the time-frequency analysis technology matures, for instance, multi-scale analysis, which has received increasing attention. Multi-scale analysis can extract association rules, discover association between variables, and overcome the weakness of traditional data processing method which cannot balance overall trend and local similarity fluctuations.
2. Scale entropy and scale exergy are proposed to reflect the system's multi-scale characteristics. The distribution law of variables on different scales is explored. Then based on scale entropy and scale exergy, the mathematical description of research subjects is put forward to restrict the application scope of the method proposed by the paper.
3. A multi-scale condition monitoring method based on big data was proposed. As the complex structures and numbers of devices are growing in modern industrial systems, requirement of condition monitoring cannot be achieved by using single traditional methods. Based on the research of different disciplines and combining algorithms, this paper presents a new condition monitoring method for the systems, in which the state parameters change slowly and cumulatively on dominant scale in the long term. The traditional model-based condition monitoring algorithm can be improved through this novel method in the aspects:
(1) The systems state is divided into dynamic and steady state. The reference models are established respectively. Then, fusion residual error is obtained by fusing dynamic residual error and stead-state residual error. Thus the influence of the inaccurate dynamic state reference model can be overcome to some extent;
(2) Information granulation is applied to handle with the volume data. Thus the processing of residual error can be transformed from serial into parallel, which greatly improves the computational efficiency and reduces computing time-consuming;
(3) Based on the multi-scale nature of processes, multi-scale analysis is applied to fusion residual error. Noise such as unmolded factors can be eliminated and condition monitoring parameter is constructed by extracted information from different scales.
4. The condition monitoring of milling roller abrasion characteristics and ash deposition detection of radiant heating surface are taken as examples to show the computational process of multi-scale condition monitoring algorithm based on big data. Abrasion index is constructed to reflect the abrasion characteristics based on the analysis of six hundred and fifty thousand data samples. Ash deposition index provide a solution to the problem of condition monitoring on deposition of water cooling wall. The algorithm presented in the paper can construct condition monitoring parameters effectively, which provides a technical basis for the control optimization and equipment predictive maintenance.
引文
[1]鲁帆.基于协整理论的复杂动态工程系统状态监测方法应用研究[D].南京：南京航空航天大学,2010
[2]刘鑫屏.热力发电过程建模与状态参数检测研究[D].北京：华北电力大学(北京),2010
[3]国务院.全民所有制工业交通企业设备管理条例[M].1987
[4]国家经济贸易委员会.“九五”全国设备管理工作纲要[M].1996
[5]Hopkins Brian, Evelson Boris. Expand Your Digital Horizon With Big Data[R]. New York:Forrester Research,2011
[6]Naisbitt John. Megatrends[M]. New York:Warner Books,1982:150-155
[7]周津慧.重大设备状态检测与寿命预测方法研究[D].西安：西安电子科技大学,2006
[8]王钊.应用于机械设备状态监测的无线传感器网络研究[D].太原：太原理工大学,2010
[9]程道文,李鑫,向鹏.脉冲中字煤质取样分析仪[P].中国专利：CN201828425U,2011-05-11
[10]史元超.基于新型传感器的交通状态获取技术的研究[D].北京：北京交通大学,2009
[11]Xiaosong Sun. Small Structure State Detection with Fiber-optic Sensors and Neural Network[C]. Knowledge Discovery and Data Mining,2009. WKDD 2009. Second International Workshop on,2009
[12]Cohen K., Leshem A.. Energy-Efficient Detection in Wireless Sensor Networks Using Likelihood Ratio and Channel State Information[J]. Selected Areas in Communications, IEEE Journal on,2011,29(8):1671-1683
[13]Joseph C, Naoum H, Boukadoum M, et al. Integrated solid-state optoelectronic sensor system for biochemical detection and quantification[C]. Semiconductor Device Research Symposium,2007 International,2007
[14]Ebert V, Fernholz T, Giesemann C, et al. Simultaneous diode-laser-based in situ detection of multiple species and temperature in a gas-fired power plant[C].28th International Symposium on Combustion, July 30,2000-August 4,2000, Edinburgh, United kingdom,2000
[15]Bramanti M, Salerno E. A, Tonazzini A, et al. An acoustic pyrometer system for tomographic thermal imaging in power plant boilers[J]. IEEE Transactions on Instrumentation and Measurement,1996,45(1):159-167
[16]于达仁,郭钰锋,王晓娟,等.计及回热器蓄热效应的汽轮机动态模型[J].中国电机工程学报,2005(14)：84-88
[17]郭钰锋,赵晓敏,于达仁,等.用于汽轮机甩负荷动态计算的数学模型[J].汽轮机技术,2006(02)：104-107+140
[18]于达仁,郭钰锋.电网一次调频能力的在线估计[J].中国电机工程学报,2004(03)：77-81
[19]倪维斗,徐向东,李政.热动力系统建模与控制的若干问题[M].北京：科学出版社,1996：15-18
[20]倪维斗,夏朝阳,王民汉.循环流化床锅炉状态监测与故障诊断专家系统(CFBBEXPTS)的推理控制机制[J].动力工程,1998(03)：2-9+88
[21]乔宗良.锅炉灰污监测和吹灰优化系统的研究与开发[D].南京：东南大学,2006
[22]朱予东.基于熵产分析及数值模拟的锅炉优化吹灰的研究[D].保定：华北电力大学(河北),2008
[23]刘定坡.燃煤电站锅炉灰污在线监测与优化吹灰系统研究[D].武汉：华中科技大学,2005
[24]陈明.燃煤电站锅炉对流受热面积灰、结渣在线监测与优化吹灰系统研究[D].武汉：华中科技大学,2004
[25]S John W. Intelligent clean on Lambton unit3[R]. Bethlehem, Lehigh University Energy Research Center Research Report,2003
[26]Zhou Guian, Si Jennie, W.Taft Cyrus. Modeling and Simulation of C-E Deep Bowl Pulverizer[J]. IEEE TRANSACTIONS ON ENERGY CONVERSION, 2000,15(3):312-322
[27]潘晶雯.MPS-190型中速磨煤机磨辊磨损特性及过程仿真的初步研究[D].北京：华北电力大学(北京),2009
[28]卫平宝.基于数据融合的设备参数劣化分析与状态评价[D].保定：华北电力大学(河北),2006
[29]朱红路,刘吉臻,常太华,等.用LMS算法构造电站燃料增益信号及热量信号[J].热能动力工程,2010(05)：552-556+579
[30]朱红路.热工信号自适应滤波及其在建模与控制中的应用[D].北京：华北电力大学(北京),2010
[31]刘吉臻,朱红路,常太华,等.基于最小均方自适应滤波器的热工过程建模方法[J].中国电机工程学报,2010(05)：107-112
[32]常太华,江清潘,朱红路.一种基于RLS算法的热工过程在线建模方法[J].电站系统工程,2009(06)：24-26+30
[33]苗世洪,王少荣,刘沛,等.基于GPS的电网状态监测系统的设计与实现[J].电力系统自动化,2000(12)：52-54
[34]韦洁,张和生,贾利民.面向状态监测的改进主元分析方法[J].电子测量与仪器学报,2009(07)：51-55
[35]韦洁.基于主元分析的电机状态监测方法的研究[D].北京：北京交通大学,2009
[36]李本威,高国胜,胡国才,等.涡轴发动机状态监测系统的研究[J].燃气涡轮试验与研究,2002(01)：42-46
[37]Alkaya A., Eker I.. A new threshold algorithm based PCA method for fault detection in transient state processes[C]. Electrical and Electronics Engineering (ELECO),2011 7th International Conference on,2011
[38]Djemili I, Aitouche A, Cocquempot V. Adaptive observer for Intake leakage detection in diesel engines described by Takagi-Sugeno model[C]. Control & Automation (MED),2011 19th Mediterranean Conference,2011
[39]Simani S, Diversi R, Soverini U. Identification of residual generators for fault detection of linear dynamic models[C]. Decision and Control,,2005 and 2005 European Control Conference. CDC-ECC'05.44th IEEE Conference,2005
[40]Simani S. Fuzzy Model Identification of a Sugar Cane Crushing Process for Fault Diagnosis Application[C]. Decision and Control,2005 and 2005 European Control Conference. CDC-ECC'05.44th IEEE Conference,2005
[41]Simani S. Identification and fault diagnosis of a simulated model of an industrial gas turbine[J]. Industrial Informatics, IEEE Transactions,2005, 1(3):202-216
[42]Nozari H. A, Banadaki H. D., Shoorehdeli M. A, et al. Model-based Fault Detection and Isolation Using Neural Networks:An Industrial Gas Turbine Case Study[C]. Systems Engineering (ICSEng),2011 21st International Conference,2011
[43]Baldi P, Castaldi P, Simani S, et al. Fault diagnosis and control reconfiguration for satellite reaction wheels[C]. Control and Fault-Tolerant Systems (SysTol), 2010 Conference,2010
[44]潘楠,伍星,迟毅林,等.基于频域盲解卷积的机械设备状态监测与故障诊断[J].振动与冲击,2012(12)：34-41
[45]M Knaak, D Filbert. Acoustical semi-blind source separation for machine monitoring. International Conference on Digital Signal Processing.2001: 159-162
[46]Bin Zhang, Khawaja T, Patrick R, et al. Blind Deconvolution Denoising for Helicopter Vibration Signals[J]. Mechatronics, IEEE/ASME Transactions, 2008,13(5):558-565
[47]Bin Zhang, Khawaja T, Patrick R, et al. Application of Blind Deconvolution Denoising in Failure Prognosis[J]. Instrumentation and Measurement, IEEE Transactions,2009,58(2):303-310
[48]Yang Huan, Liu Yibing, An Hongwen, et al. Turbine vibration source separation based on Independent Component Analysis[C]. Mechatronics and Automation (ICMA),2010 International Conference,2010
[49]Yan Keguo, Liu Yibing, Xu Hong, et al. Source identification of turbine vibration based on Independent Component Analysis with virtual signal channels[C]. Industrial Electronics and Applications,2009, ICIEA 2009,4th IEEE Conference,2009
[50]李郝林.磨削状态监测中频域特征参数计算区域的确定[J].工具技术,2006(10)：75-76
[51]李海涛,王成国.基于轨道车辆频域模型的二系垂向悬挂元件状态监测[J].铁道机车车辆,2008(02)：1-5
[52]严可国,柳亦兵,徐鸿,等.基于双谱分析的大型汽轮机振动故障特性提取[J].中国电机工程学报,2010(02)：98-103
[53]柳亦兵,周雁冰,辛卫东,等.直驱风电机组轴承故障的双谱特征分析与诊断[C].第三十届中国控制会议,中国山东烟台,2011
[54]金岩.基于小波变换与独立分量分析的内燃机振声特性研究[D].杭州：浙江大学,2007
[55]杨涛.基于小波分时尺度矩特征的多状态信息融合振动故障诊断和预测方法研究[D].武汉：华中科技大学,2009
[56]张庆华,王太勇.时频分析方法在往复机械振动特征提取中的应用[J].机械设计与制造工程,2002(04)：16-17
[57]Ling Xiang, Guiji Tang, Yongli Zhu. Vibration Signal Analysis of Rotor System Based on Time-Frequency Attributes[C]. Young Computer Scientists,2008, ICYCS 2008, The 9th International Conference for,2008
[58]Lv Xin, Hou Zhuo, Wang Liguo, et al. Submersible motor rotor bars broken fault analysis based on HHT[C]. Power Electronics and Motion Control Conference (IPEMC),2012 7th International,2012
[59]Paraskevas I, Prekas K, Potirakis S. M, et al. On the use of time-frequency distributions for the power quality problem of harmonics[C]. Power Generation, Transmission, Distribution and Energy Conversion (MedPower 2010),7th Mediterranean Conference and Exhibition on,2010
[60]Soo-Hwan Cho, Gilsoo Jang, Sae-Hyuk Kwon. Time-Frequency Analysis of Power-Quality Disturbances via the Gabor & Wigner Transform[J]. Power Delivery, IEEE Transactions,2010,25(1):494-499
[61]Moin Siddiqui K, Giri V. K. Broken rotor bar fault detection in induction motors using Wavelet Transform[C]. Computing, Electronics and Electrical Technologies (ICCEET),2012 International Conference,2012
[62]Kechida R, Menacer A. DWT wavelet transform for the rotor bars faults detection in induction motor[C]. Electric Power and Energy Conversion Systems (EPECS),2011 2nd International Conference,2011
[63]Mehrjou M. R, Mariun N, Marhaban M. H, et al. Evaluation of Fourier and wavelet analysis for efficient recognition of broken rotor bar in squirrel-cage induction machine[C]. Power and Energy (PECon),2010 IEEE International Conference on,2010
[64]Rajagopalan S, Restrepo J. A, Aller J. M, et al. Selecting time-frequency representations for detecting rotor faults in BLDC motors operating under rapidly varying operating conditions[C]. Industrial Electronics Society,2005, IECON 2005,31st Annual Conference of IEEE,2005
[65]Rajagopalan S, Restrepo J. A, Aller J. M, et al. Wigner-Ville distributions for detection of rotor faults in brushless DC (BLDC) motors operating under non-stationary conditions[C]. Diagnostics for Electric Machines, Power Electronics and Drives,2005, SDEMPED 2005,5th IEEE International Symposium on,2005
[66]蒋宗礼.人工神经网络导论[M].北京：高等教育出版社,2001：70-71
[67]徐伟燕.智能神经网络在大型风电场短期功率预测中的应用[D].北京：北京交通大学,2012
[68]胡良谋,曹可强,徐浩军,等.支持向量机故障诊断及控制技术[M].北京： 国防工业出版社,2011：55-56
[69]杜京义,侯媛彬.基于核方法的故障诊断理论及其方法的研究[M].北京：北京大学出版社,2010：158-159
[70]张淑宁,王福利,何大阔,等.在线鲁棒最小二乘支持向量机回归建模[J].控制理论与应用,2011(11)：1601-1606
[71]司刚全,娄勇,张寅松.一种鲁棒最小二乘支持向量机及其在软测量中的应用[J].西安交通大学学报,2012(08)：1-8
[72]李静,王京,杨磊,等.热处理炉钢板温度的自适应混沌粒子群算法-最小二乘支持向量机优化预报算法[J].控制理论与应用,28(12)：1825-1830
[73]胡广书.数字信号处理导论[M].北京：清华大学出版社,2005：55-60
[74]李登峰,杨晓慧.小波基础理论和应用实例[M].北京：高等教育出版社,2010：200-201
[75]Daubechies. Ten Lectures on Wavelets[M]. Philadelphia:Society for Industrial and Applied Mathematics,1992:195-200
[76]张彬,杨风暴.小波分析方法及其应用[M].北京：国防工业出版社,2011：200-220
[77]张卉.基于分形与小波理论的特征提取方法研究与应用[D].武汉：武汉理工大学,2008
[78]张志强,姚志远.时频分析及其应用[J].华东船舶工业学院学报(自然科学版),2002(04)：48-52
[79]朱启兵.基于小波理论的非平稳信号特征提取与智能诊断方法研究[D].沈阳：东北大学,2006
[80]邹红星,周小波,李衍达.时频分析：回溯与前瞻[J].电子学报,2000(09)：78-84
[81]R.E.kalman. A new approach to linear filtering and prediction probles[J]. Journal of basic engineering,1960,82:35-45
[82]朱志宇.粒子滤波算法及其应用[M].北京：科学出版社,2010：120-150
[83]韩崇昭,朱红艳,段战胜.多源信息融合(第二版)[M].北京：清华大学出版社,2010：200-220
[84]Linoff Gordon S, Berry Michael J. Data Mining Techniques:For Marketing, Sales, and Customer Relationship Management [M]. New York:John Wiley & Sons,2011:20-22
[85]Han Jiawei, Kamber Micheline, Pei Jian. Data Mining:Concepts and Techniques[M]. Amsterdam:Elsevier,2011:78-99
[86]Witten Ian H., Frank Eibe, Hall Mark A.. Data Mining:Practical Machine Learning Tools and Techniques[M]. Amsterdam:Elsevier,2011:121-134
[87]Han Jiawei, Kamber Micheline.数据挖掘概念与技术[M].北京：机械工业出版社,2008：100-105
[88]Arratia Oscar, Obaya Rafael, Sansaturio M. Eugenia. Applications of the exponential ordering in the study of almost-periodic delayed Hopfield neural networks[J]. Physica D:Nonlinear Phenomena,2012,241(18):1551-1566
[89]Ding Yuting, Jiang Weihua, Yu Pei. Bifurcation analysis in a recurrent neural network model with delays[J]. Communications in Nonlinear Science and Numerical Simulation,2013,18(2):351-372
[90]Shu-Lin Wu, Ke-Lin Li, Jin-Shan Zhang. Exponential stability of discrete-time neural networks with delay and impulses[J]. Applied Mathematics and Computation,2012,218(12):6972-6986
[91]Liu Bingwen. Global exponential stability for BAM neural networks with time-varying delays in the leakage terms[J]. Nonlinear Analysis:Real World Applications,2013,14(1):559-566
[92]苗夺谦,李德毅,张燕平,等.不确定性与粒计算[M].北京：科学出版社,2011：20-22
[93]苗夺谦,刘清龙,林早阳,等.粒计算：过去、现在与展望[M].北京：科学出版社,2007：60-65
[94]王超,陈刚,李冰,等.660 Mw机组hp碗式中速磨煤机状态检修的研究[J].电站系统工程,2006(04)：27-29
[95]杨雁梅.电站磨煤机状态监测与故障诊断的研究[D].北京：北京交通大学,2008
[96]王磊.火电厂设备运行状态评价方法研究及实现[D].武汉：华中科技大学,2004
[97]张小桃,倪维斗,李政,等.基于现场数据的中速磨煤机动态建模研究[J].热能动力工程,2004(06)：614-616+633-659
[98]王超.燃煤电厂制粉系统hp983碗式中速磨煤机状态检修的研究[D].武汉：华中科技大学,2007
[99]J Sligar N, G Callcott T, M Stewart I. Evaluation of classification and grinding of coal in a medium speed mill[C]. EFCE Working Party of Comminution and Classification.1975, Nuremberg:587-599.
[100]郝祖龙,刘吉臻,常太华,等.基于小波变换的热工信号多尺度相关性分 析[J].中国电机工程学报,2010,30(14)：109-114
[101]刘继伟,曾德良,蒋欣军,等.基于小波变换的磨煤机磨辊磨损趋势分量提取[J].华北电力大学学报(自然科学版),2011,38(02)：37-42
[102]叶江明.电厂锅炉原理及设备[M].北京：中国电力出版社,2004：89-95
[103]黄新元.电站锅炉运行与燃烧调整[M].北京：中国电力出版社,2007：78-80
[104]朱予东,阎维平,高正阳,等.600mw机组锅炉对流受热面污染状况实验与吹灰优化[J].动力工程,2005,25(02)：196-200
[105]杜庆军.电站锅炉吹灰优化系统的研究与应用[D].北京：华北电力大学2009
[106]蓝晓村.电站锅炉灰污监测与吹灰优化的应用研究[D].南京：东南大学2005
[107]张春丽.电站锅炉吹灰优化系统的研究与开发[D].北京：华北电力大学2007
[108]Piboontum S. J, Swift S. M, Conrad R. S. Boiler modeling optimizes sootblowing[J]. Power,2005,149(8):34-37
[109]Piboontum S. J, Swift S. M, Conrad R. S. Boiler modeling optimizes sootblowing[J]. Power,2005,149(8):34-37
[110]Kalisz Sylwester, Pronobis Marek. Investigations on fouling rate in convective bundles of coal-fired boilers in relation to optimization of sootblower operation[J]. Fuel,2005,84(7-8):927-937
[111]Erkki Valimaki, Keijo Salmenoja. Measured data for sootblowing optimization[C].2004 TAPPI Fall Technical Conference:Engineering and Pulping, October 31,2004-November 3,2004, Atlanta, GA, United states, 2004
[112]Erkki Valimaki, Keijo Salmenoja. New tools for sootblowing optimization studies[C]. Asian Paper-New Applied Technology Conference, April 27,2004-April 29,2004, Suntec, Singapore,2004
[113]Sarunac Nenad, Sale John W, Bian Xiadong, et al. Sootblowing optimization for opacity control[C]. EPA-DOE-EPRI-A and WMA Power Plant Air Pollutant Control Mega Symposium 2006, August 28,2006-August 31,2006, Baltimore, MD, United states,2006
[2]刘鑫屏.热力发电过程建模与状态参数检测研究[D].北京：华北电力大学(北京),2010
[3]国务院.全民所有制工业交通企业设备管理条例[M].1987
[4]国家经济贸易委员会.“九五”全国设备管理工作纲要[M].1996
[5]Hopkins Brian, Evelson Boris. Expand Your Digital Horizon With Big Data[R]. New York:Forrester Research,2011
[6]Naisbitt John. Megatrends[M]. New York:Warner Books,1982:150-155
[7]周津慧.重大设备状态检测与寿命预测方法研究[D].西安：西安电子科技大学,2006
[8]王钊.应用于机械设备状态监测的无线传感器网络研究[D].太原：太原理工大学,2010
[9]程道文,李鑫,向鹏.脉冲中字煤质取样分析仪[P].中国专利：CN201828425U,2011-05-11
[10]史元超.基于新型传感器的交通状态获取技术的研究[D].北京：北京交通大学,2009
[11]Xiaosong Sun. Small Structure State Detection with Fiber-optic Sensors and Neural Network[C]. Knowledge Discovery and Data Mining,2009. WKDD 2009. Second International Workshop on,2009
[12]Cohen K., Leshem A.. Energy-Efficient Detection in Wireless Sensor Networks Using Likelihood Ratio and Channel State Information[J]. Selected Areas in Communications, IEEE Journal on,2011,29(8):1671-1683
[13]Joseph C, Naoum H, Boukadoum M, et al. Integrated solid-state optoelectronic sensor system for biochemical detection and quantification[C]. Semiconductor Device Research Symposium,2007 International,2007
[14]Ebert V, Fernholz T, Giesemann C, et al. Simultaneous diode-laser-based in situ detection of multiple species and temperature in a gas-fired power plant[C].28th International Symposium on Combustion, July 30,2000-August 4,2000, Edinburgh, United kingdom,2000
[15]Bramanti M, Salerno E. A, Tonazzini A, et al. An acoustic pyrometer system for tomographic thermal imaging in power plant boilers[J]. IEEE Transactions on Instrumentation and Measurement,1996,45(1):159-167
[16]于达仁,郭钰锋,王晓娟,等.计及回热器蓄热效应的汽轮机动态模型[J].中国电机工程学报,2005(14)：84-88
[17]郭钰锋,赵晓敏,于达仁,等.用于汽轮机甩负荷动态计算的数学模型[J].汽轮机技术,2006(02)：104-107+140
[18]于达仁,郭钰锋.电网一次调频能力的在线估计[J].中国电机工程学报,2004(03)：77-81
[19]倪维斗,徐向东,李政.热动力系统建模与控制的若干问题[M].北京：科学出版社,1996：15-18
[20]倪维斗,夏朝阳,王民汉.循环流化床锅炉状态监测与故障诊断专家系统(CFBBEXPTS)的推理控制机制[J].动力工程,1998(03)：2-9+88
[21]乔宗良.锅炉灰污监测和吹灰优化系统的研究与开发[D].南京：东南大学,2006
[22]朱予东.基于熵产分析及数值模拟的锅炉优化吹灰的研究[D].保定：华北电力大学(河北),2008
[23]刘定坡.燃煤电站锅炉灰污在线监测与优化吹灰系统研究[D].武汉：华中科技大学,2005
[24]陈明.燃煤电站锅炉对流受热面积灰、结渣在线监测与优化吹灰系统研究[D].武汉：华中科技大学,2004
[25]S John W. Intelligent clean on Lambton unit3[R]. Bethlehem, Lehigh University Energy Research Center Research Report,2003
[26]Zhou Guian, Si Jennie, W.Taft Cyrus. Modeling and Simulation of C-E Deep Bowl Pulverizer[J]. IEEE TRANSACTIONS ON ENERGY CONVERSION, 2000,15(3):312-322
[27]潘晶雯.MPS-190型中速磨煤机磨辊磨损特性及过程仿真的初步研究[D].北京：华北电力大学(北京),2009
[28]卫平宝.基于数据融合的设备参数劣化分析与状态评价[D].保定：华北电力大学(河北),2006
[29]朱红路,刘吉臻,常太华,等.用LMS算法构造电站燃料增益信号及热量信号[J].热能动力工程,2010(05)：552-556+579
[30]朱红路.热工信号自适应滤波及其在建模与控制中的应用[D].北京：华北电力大学(北京),2010
[31]刘吉臻,朱红路,常太华,等.基于最小均方自适应滤波器的热工过程建模方法[J].中国电机工程学报,2010(05)：107-112
[32]常太华,江清潘,朱红路.一种基于RLS算法的热工过程在线建模方法[J].电站系统工程,2009(06)：24-26+30
[33]苗世洪,王少荣,刘沛,等.基于GPS的电网状态监测系统的设计与实现[J].电力系统自动化,2000(12)：52-54
[34]韦洁,张和生,贾利民.面向状态监测的改进主元分析方法[J].电子测量与仪器学报,2009(07)：51-55
[35]韦洁.基于主元分析的电机状态监测方法的研究[D].北京：北京交通大学,2009
[36]李本威,高国胜,胡国才,等.涡轴发动机状态监测系统的研究[J].燃气涡轮试验与研究,2002(01)：42-46
[37]Alkaya A., Eker I.. A new threshold algorithm based PCA method for fault detection in transient state processes[C]. Electrical and Electronics Engineering (ELECO),2011 7th International Conference on,2011
[38]Djemili I, Aitouche A, Cocquempot V. Adaptive observer for Intake leakage detection in diesel engines described by Takagi-Sugeno model[C]. Control & Automation (MED),2011 19th Mediterranean Conference,2011
[39]Simani S, Diversi R, Soverini U. Identification of residual generators for fault detection of linear dynamic models[C]. Decision and Control,,2005 and 2005 European Control Conference. CDC-ECC'05.44th IEEE Conference,2005
[40]Simani S. Fuzzy Model Identification of a Sugar Cane Crushing Process for Fault Diagnosis Application[C]. Decision and Control,2005 and 2005 European Control Conference. CDC-ECC'05.44th IEEE Conference,2005
[41]Simani S. Identification and fault diagnosis of a simulated model of an industrial gas turbine[J]. Industrial Informatics, IEEE Transactions,2005, 1(3):202-216
[42]Nozari H. A, Banadaki H. D., Shoorehdeli M. A, et al. Model-based Fault Detection and Isolation Using Neural Networks:An Industrial Gas Turbine Case Study[C]. Systems Engineering (ICSEng),2011 21st International Conference,2011
[43]Baldi P, Castaldi P, Simani S, et al. Fault diagnosis and control reconfiguration for satellite reaction wheels[C]. Control and Fault-Tolerant Systems (SysTol), 2010 Conference,2010
[44]潘楠,伍星,迟毅林,等.基于频域盲解卷积的机械设备状态监测与故障诊断[J].振动与冲击,2012(12)：34-41
[45]M Knaak, D Filbert. Acoustical semi-blind source separation for machine monitoring. International Conference on Digital Signal Processing.2001: 159-162
[46]Bin Zhang, Khawaja T, Patrick R, et al. Blind Deconvolution Denoising for Helicopter Vibration Signals[J]. Mechatronics, IEEE/ASME Transactions, 2008,13(5):558-565
[47]Bin Zhang, Khawaja T, Patrick R, et al. Application of Blind Deconvolution Denoising in Failure Prognosis[J]. Instrumentation and Measurement, IEEE Transactions,2009,58(2):303-310
[48]Yang Huan, Liu Yibing, An Hongwen, et al. Turbine vibration source separation based on Independent Component Analysis[C]. Mechatronics and Automation (ICMA),2010 International Conference,2010
[49]Yan Keguo, Liu Yibing, Xu Hong, et al. Source identification of turbine vibration based on Independent Component Analysis with virtual signal channels[C]. Industrial Electronics and Applications,2009, ICIEA 2009,4th IEEE Conference,2009
[50]李郝林.磨削状态监测中频域特征参数计算区域的确定[J].工具技术,2006(10)：75-76
[51]李海涛,王成国.基于轨道车辆频域模型的二系垂向悬挂元件状态监测[J].铁道机车车辆,2008(02)：1-5
[52]严可国,柳亦兵,徐鸿,等.基于双谱分析的大型汽轮机振动故障特性提取[J].中国电机工程学报,2010(02)：98-103
[53]柳亦兵,周雁冰,辛卫东,等.直驱风电机组轴承故障的双谱特征分析与诊断[C].第三十届中国控制会议,中国山东烟台,2011
[54]金岩.基于小波变换与独立分量分析的内燃机振声特性研究[D].杭州：浙江大学,2007
[55]杨涛.基于小波分时尺度矩特征的多状态信息融合振动故障诊断和预测方法研究[D].武汉：华中科技大学,2009
[56]张庆华,王太勇.时频分析方法在往复机械振动特征提取中的应用[J].机械设计与制造工程,2002(04)：16-17
[57]Ling Xiang, Guiji Tang, Yongli Zhu. Vibration Signal Analysis of Rotor System Based on Time-Frequency Attributes[C]. Young Computer Scientists,2008, ICYCS 2008, The 9th International Conference for,2008
[58]Lv Xin, Hou Zhuo, Wang Liguo, et al. Submersible motor rotor bars broken fault analysis based on HHT[C]. Power Electronics and Motion Control Conference (IPEMC),2012 7th International,2012
[59]Paraskevas I, Prekas K, Potirakis S. M, et al. On the use of time-frequency distributions for the power quality problem of harmonics[C]. Power Generation, Transmission, Distribution and Energy Conversion (MedPower 2010),7th Mediterranean Conference and Exhibition on,2010
[60]Soo-Hwan Cho, Gilsoo Jang, Sae-Hyuk Kwon. Time-Frequency Analysis of Power-Quality Disturbances via the Gabor & Wigner Transform[J]. Power Delivery, IEEE Transactions,2010,25(1):494-499
[61]Moin Siddiqui K, Giri V. K. Broken rotor bar fault detection in induction motors using Wavelet Transform[C]. Computing, Electronics and Electrical Technologies (ICCEET),2012 International Conference,2012
[62]Kechida R, Menacer A. DWT wavelet transform for the rotor bars faults detection in induction motor[C]. Electric Power and Energy Conversion Systems (EPECS),2011 2nd International Conference,2011
[63]Mehrjou M. R, Mariun N, Marhaban M. H, et al. Evaluation of Fourier and wavelet analysis for efficient recognition of broken rotor bar in squirrel-cage induction machine[C]. Power and Energy (PECon),2010 IEEE International Conference on,2010
[64]Rajagopalan S, Restrepo J. A, Aller J. M, et al. Selecting time-frequency representations for detecting rotor faults in BLDC motors operating under rapidly varying operating conditions[C]. Industrial Electronics Society,2005, IECON 2005,31st Annual Conference of IEEE,2005
[65]Rajagopalan S, Restrepo J. A, Aller J. M, et al. Wigner-Ville distributions for detection of rotor faults in brushless DC (BLDC) motors operating under non-stationary conditions[C]. Diagnostics for Electric Machines, Power Electronics and Drives,2005, SDEMPED 2005,5th IEEE International Symposium on,2005
[66]蒋宗礼.人工神经网络导论[M].北京：高等教育出版社,2001：70-71
[67]徐伟燕.智能神经网络在大型风电场短期功率预测中的应用[D].北京：北京交通大学,2012
[68]胡良谋,曹可强,徐浩军,等.支持向量机故障诊断及控制技术[M].北京： 国防工业出版社,2011：55-56
[69]杜京义,侯媛彬.基于核方法的故障诊断理论及其方法的研究[M].北京：北京大学出版社,2010：158-159
[70]张淑宁,王福利,何大阔,等.在线鲁棒最小二乘支持向量机回归建模[J].控制理论与应用,2011(11)：1601-1606
[71]司刚全,娄勇,张寅松.一种鲁棒最小二乘支持向量机及其在软测量中的应用[J].西安交通大学学报,2012(08)：1-8
[72]李静,王京,杨磊,等.热处理炉钢板温度的自适应混沌粒子群算法-最小二乘支持向量机优化预报算法[J].控制理论与应用,28(12)：1825-1830
[73]胡广书.数字信号处理导论[M].北京：清华大学出版社,2005：55-60
[74]李登峰,杨晓慧.小波基础理论和应用实例[M].北京：高等教育出版社,2010：200-201
[75]Daubechies. Ten Lectures on Wavelets[M]. Philadelphia:Society for Industrial and Applied Mathematics,1992:195-200
[76]张彬,杨风暴.小波分析方法及其应用[M].北京：国防工业出版社,2011：200-220
[77]张卉.基于分形与小波理论的特征提取方法研究与应用[D].武汉：武汉理工大学,2008
[78]张志强,姚志远.时频分析及其应用[J].华东船舶工业学院学报(自然科学版),2002(04)：48-52
[79]朱启兵.基于小波理论的非平稳信号特征提取与智能诊断方法研究[D].沈阳：东北大学,2006
[80]邹红星,周小波,李衍达.时频分析：回溯与前瞻[J].电子学报,2000(09)：78-84
[81]R.E.kalman. A new approach to linear filtering and prediction probles[J]. Journal of basic engineering,1960,82:35-45
[82]朱志宇.粒子滤波算法及其应用[M].北京：科学出版社,2010：120-150
[83]韩崇昭,朱红艳,段战胜.多源信息融合(第二版)[M].北京：清华大学出版社,2010：200-220
[84]Linoff Gordon S, Berry Michael J. Data Mining Techniques:For Marketing, Sales, and Customer Relationship Management [M]. New York:John Wiley & Sons,2011:20-22
[85]Han Jiawei, Kamber Micheline, Pei Jian. Data Mining:Concepts and Techniques[M]. Amsterdam:Elsevier,2011:78-99
[86]Witten Ian H., Frank Eibe, Hall Mark A.. Data Mining:Practical Machine Learning Tools and Techniques[M]. Amsterdam:Elsevier,2011:121-134
[87]Han Jiawei, Kamber Micheline.数据挖掘概念与技术[M].北京：机械工业出版社,2008：100-105
[88]Arratia Oscar, Obaya Rafael, Sansaturio M. Eugenia. Applications of the exponential ordering in the study of almost-periodic delayed Hopfield neural networks[J]. Physica D:Nonlinear Phenomena,2012,241(18):1551-1566
[89]Ding Yuting, Jiang Weihua, Yu Pei. Bifurcation analysis in a recurrent neural network model with delays[J]. Communications in Nonlinear Science and Numerical Simulation,2013,18(2):351-372
[90]Shu-Lin Wu, Ke-Lin Li, Jin-Shan Zhang. Exponential stability of discrete-time neural networks with delay and impulses[J]. Applied Mathematics and Computation,2012,218(12):6972-6986
[91]Liu Bingwen. Global exponential stability for BAM neural networks with time-varying delays in the leakage terms[J]. Nonlinear Analysis:Real World Applications,2013,14(1):559-566
[92]苗夺谦,李德毅,张燕平,等.不确定性与粒计算[M].北京：科学出版社,2011：20-22
[93]苗夺谦,刘清龙,林早阳,等.粒计算：过去、现在与展望[M].北京：科学出版社,2007：60-65
[94]王超,陈刚,李冰,等.660 Mw机组hp碗式中速磨煤机状态检修的研究[J].电站系统工程,2006(04)：27-29
[95]杨雁梅.电站磨煤机状态监测与故障诊断的研究[D].北京：北京交通大学,2008
[96]王磊.火电厂设备运行状态评价方法研究及实现[D].武汉：华中科技大学,2004
[97]张小桃,倪维斗,李政,等.基于现场数据的中速磨煤机动态建模研究[J].热能动力工程,2004(06)：614-616+633-659
[98]王超.燃煤电厂制粉系统hp983碗式中速磨煤机状态检修的研究[D].武汉：华中科技大学,2007
[99]J Sligar N, G Callcott T, M Stewart I. Evaluation of classification and grinding of coal in a medium speed mill[C]. EFCE Working Party of Comminution and Classification.1975, Nuremberg:587-599.
[100]郝祖龙,刘吉臻,常太华,等.基于小波变换的热工信号多尺度相关性分 析[J].中国电机工程学报,2010,30(14)：109-114
[101]刘继伟,曾德良,蒋欣军,等.基于小波变换的磨煤机磨辊磨损趋势分量提取[J].华北电力大学学报(自然科学版),2011,38(02)：37-42
[102]叶江明.电厂锅炉原理及设备[M].北京：中国电力出版社,2004：89-95
[103]黄新元.电站锅炉运行与燃烧调整[M].北京：中国电力出版社,2007：78-80
[104]朱予东,阎维平,高正阳,等.600mw机组锅炉对流受热面污染状况实验与吹灰优化[J].动力工程,2005,25(02)：196-200
[105]杜庆军.电站锅炉吹灰优化系统的研究与应用[D].北京：华北电力大学2009
[106]蓝晓村.电站锅炉灰污监测与吹灰优化的应用研究[D].南京：东南大学2005
[107]张春丽.电站锅炉吹灰优化系统的研究与开发[D].北京：华北电力大学2007
[108]Piboontum S. J, Swift S. M, Conrad R. S. Boiler modeling optimizes sootblowing[J]. Power,2005,149(8):34-37
[109]Piboontum S. J, Swift S. M, Conrad R. S. Boiler modeling optimizes sootblowing[J]. Power,2005,149(8):34-37
[110]Kalisz Sylwester, Pronobis Marek. Investigations on fouling rate in convective bundles of coal-fired boilers in relation to optimization of sootblower operation[J]. Fuel,2005,84(7-8):927-937
[111]Erkki Valimaki, Keijo Salmenoja. Measured data for sootblowing optimization[C].2004 TAPPI Fall Technical Conference:Engineering and Pulping, October 31,2004-November 3,2004, Atlanta, GA, United states, 2004
[112]Erkki Valimaki, Keijo Salmenoja. New tools for sootblowing optimization studies[C]. Asian Paper-New Applied Technology Conference, April 27,2004-April 29,2004, Suntec, Singapore,2004
[113]Sarunac Nenad, Sale John W, Bian Xiadong, et al. Sootblowing optimization for opacity control[C]. EPA-DOE-EPRI-A and WMA Power Plant Air Pollutant Control Mega Symposium 2006, August 28,2006-August 31,2006, Baltimore, MD, United states,2006