基于PLS的建模与控制技术在热工过程中的应用研究
|
摘要
工业过程控制是通过对生产过程的描述、仿真、设计、控制和管理等方面问题的研究,以改善工艺操作、提高自动化水平、优化生产过程、加强生产管理为手段,最终达到提高生产效益、降低能源损耗、控制有害物排放等目标。目前,随着过程控制技术、计算机技术和其它相关技术的飞速发展,使我们更广泛地获得了过程中产生的大量数据。如果能有效地分析这些信息,就能为我们进一步控制目标的实现提供有益帮助。同时也存在过程变量众多、且具有高度非线性和时变性等难以克服的困难。本文以多变量统计过程控制和数据挖掘为理论,深入地研究了基于部分最小二乘(PLS)和相关方法,并将该方法引入到热工过程控制软测量建模及自适应控制中。论文的主要工作内容和研究成果包括:
将PLS算法和多元回归以及主元回归方法进行比较,验证了当数据存在相关性时,PLS算法和主元回归能够很好地解决相关性问题,然后通过一个简单的例子进行了验证。并进一步概要地推导出PLS算法具有更好的拟合性能的结论。
研究了递推PLS及其改进算法。以高斯核函数来处理数据的非线性,用聚类方法来自动选择高斯函数的参数,采用递推PLS来调整和更新模型。这样得到的模型即具有较好的非线性处理能力,又能随着工况的改变更新模型以适应过程的变化。针对火电厂辐射受热面污染形成机理不明晰、非线性强且有较大的时间间隔等难题,应用所提出的算法建立电站辐射受热面污染预测模型,并且通过实验检验了模型的有效性。
在递推PLS的基础上引入折息因子,得到了折息递推最小二乘算法(DRPLS)。并进一步与动态矩阵预测控制算法相结合,提出基于折息递推最小二乘的自适应控制算法。因为受各种因素影响,模型参数是时变的,通过DRPLS,对模型进行修正可以提高其精度。并应用该方法对某电厂主汽温控制进行了仿真试验,取得了较好的效果。
基于Mercer理论对核偏PLS引进了支持向量机来处理内部非线性问题。这样不仅考虑了数据外部的非线性关系,也考虑了输入和输出之间内部的非线性关系,从而使所提出的算法较之一般的非线性PLS算法有更强的非线性处理能力。将该方法应用于火电厂烟气飞灰含碳量软测量模型的建立,并通过实验验证了该算法具有较好的实用价值。
Industry process control is to mend techniques manipulation, improve automation degree, optimize production process and enhance production manage through studying on description, stimulation, design, control and manage of production process. Finally, it can achieve the object which improve production efficiency, reduce source consume and control deleterious substance release. Now, following the fast improving of process control and computer technique and so on, we can get more data come from production. If the information can be full extracted and analyzed, it may give us useful help to more control production. However, there are many difficult problems such as a great deal of process variable and nonlinear and time-varying of process. The dissertation deeply studied partial Least Squares method and applied it into soft measure modeling and adaptive control of thermal process control. The main contributions of this dissertation can be summarized as followings:
By comparing PLS and mult-irecursive least-square with principal component recursive algorithm, the validity which PLS and principal component recursive algorithm effectively deals with relativity problems when data has relativity is tested. Experiments results show that PLS possess better fitting property.
Recursive PLS and its improved methods are investigated. A new recursive Nonlinear PLS is proposed which deal with nonlinear problem with Guess kernel function and update model by recursive PLS. The model obtained by this method have better nonlinear manage ability and update model to fit process variety following condition. Radiation heat-receiving side and pollute side of thermal power plant have difficulty problems of dimness mechanism, strongly nonlinear and big time space. Power station forecasting model is building using proposed algorithm. Experiments verify its effect.
Discount recursive PLS (DRPLS) is obtained by using discount factor based on recursive PLS. Moreover, combining DRPLS with dynamic matrix forecasting control algorithm, an adaptive control algorithm based on discount recursive least-square is proposed. Because of factor effect, model parameter is time-varying which can be improved precision by update model with DRPLS. The simulation experiments on superheated steam temperature control of power plant verify its effect convenient.
Kernel nonlinear partial least square algorithm based on Mercer theory namely KPLS-LSSVM is proposed. Considering the nonlinear relation is not only being data outside but also being inside data between input and output, the method has more strong process ability than normal nonlinear PLS. The method was applied in building carbon content in fly ash soft measure model of thermal power plant. Experiment verify its effect and convenient.
将PLS算法和多元回归以及主元回归方法进行比较,验证了当数据存在相关性时,PLS算法和主元回归能够很好地解决相关性问题,然后通过一个简单的例子进行了验证。并进一步概要地推导出PLS算法具有更好的拟合性能的结论。
研究了递推PLS及其改进算法。以高斯核函数来处理数据的非线性,用聚类方法来自动选择高斯函数的参数,采用递推PLS来调整和更新模型。这样得到的模型即具有较好的非线性处理能力,又能随着工况的改变更新模型以适应过程的变化。针对火电厂辐射受热面污染形成机理不明晰、非线性强且有较大的时间间隔等难题,应用所提出的算法建立电站辐射受热面污染预测模型,并且通过实验检验了模型的有效性。
在递推PLS的基础上引入折息因子,得到了折息递推最小二乘算法(DRPLS)。并进一步与动态矩阵预测控制算法相结合,提出基于折息递推最小二乘的自适应控制算法。因为受各种因素影响,模型参数是时变的,通过DRPLS,对模型进行修正可以提高其精度。并应用该方法对某电厂主汽温控制进行了仿真试验,取得了较好的效果。
基于Mercer理论对核偏PLS引进了支持向量机来处理内部非线性问题。这样不仅考虑了数据外部的非线性关系,也考虑了输入和输出之间内部的非线性关系,从而使所提出的算法较之一般的非线性PLS算法有更强的非线性处理能力。将该方法应用于火电厂烟气飞灰含碳量软测量模型的建立,并通过实验验证了该算法具有较好的实用价值。
Industry process control is to mend techniques manipulation, improve automation degree, optimize production process and enhance production manage through studying on description, stimulation, design, control and manage of production process. Finally, it can achieve the object which improve production efficiency, reduce source consume and control deleterious substance release. Now, following the fast improving of process control and computer technique and so on, we can get more data come from production. If the information can be full extracted and analyzed, it may give us useful help to more control production. However, there are many difficult problems such as a great deal of process variable and nonlinear and time-varying of process. The dissertation deeply studied partial Least Squares method and applied it into soft measure modeling and adaptive control of thermal process control. The main contributions of this dissertation can be summarized as followings:
By comparing PLS and mult-irecursive least-square with principal component recursive algorithm, the validity which PLS and principal component recursive algorithm effectively deals with relativity problems when data has relativity is tested. Experiments results show that PLS possess better fitting property.
Recursive PLS and its improved methods are investigated. A new recursive Nonlinear PLS is proposed which deal with nonlinear problem with Guess kernel function and update model by recursive PLS. The model obtained by this method have better nonlinear manage ability and update model to fit process variety following condition. Radiation heat-receiving side and pollute side of thermal power plant have difficulty problems of dimness mechanism, strongly nonlinear and big time space. Power station forecasting model is building using proposed algorithm. Experiments verify its effect.
Discount recursive PLS (DRPLS) is obtained by using discount factor based on recursive PLS. Moreover, combining DRPLS with dynamic matrix forecasting control algorithm, an adaptive control algorithm based on discount recursive least-square is proposed. Because of factor effect, model parameter is time-varying which can be improved precision by update model with DRPLS. The simulation experiments on superheated steam temperature control of power plant verify its effect convenient.
Kernel nonlinear partial least square algorithm based on Mercer theory namely KPLS-LSSVM is proposed. Considering the nonlinear relation is not only being data outside but also being inside data between input and output, the method has more strong process ability than normal nonlinear PLS. The method was applied in building carbon content in fly ash soft measure model of thermal power plant. Experiment verify its effect and convenient.
引文
[1]朱法华,王圣,郑有飞.火电NOx排放现状与预测及控制对策[J].能源环境保护,2004,18(1):1-5.
[2]阎世辉.我国燃煤电厂二氧化硫减排技术经济分析[J].环境保护, 2003, (4): 46-48.
[3]王志轩.我国火电厂污染控制现状与"十五"计划的目标、措施[J].环境保护, 2003, (4): 49-51.
[4]赵洁,赵锦洋.火电结构优化和技术升级研究的回顾与展望[M].北京:中国电力出版社, 2005: 16-19.
[5]吕太,罗伟民,王雷,等.国内燃煤电厂烟气脱硫现状与展望[J] .东北电力学院学报,2000,20(2):68-74.
[6]高亹.我国电力工业的展望[J].东南大学学报,2005,35(1):159-165.
[7]王新新.中国的能源安全与能源战略选择[J].北京:中国科技论坛,2007,1:51.
[8]崔民选.2007年能源蓝皮书[M].北京:社会科学文献出版社, 2007:266-273
[9] Luo R F, Shao H H, Zhang Z J. Fuzzy-neural-net-Based inferential Control for a High-purity Distillation Column [J]. Control Eng Practice, 1995, 3(1):31-41.
[10]王树青.先进控制技术及应用[M].北京:化学工业出版社,2000:15-18,31
[11]于静江,周春晖.过程控制中的软测量技术[J] .控制理论与应用,1996,13(2):137-144
[12]俞金寿,刘爱伦,张克进.软测量技术及其在石油化工中的应用[M].北京:化学工业出版社,2000:170-188
[13]刘瑞兰,苏宏业,褚健.PLS回归软测量方法在催化重整稳定油组分估计中的应用[J].化工自动化及仪表,2002,29(5):44-47
[14]吴朝辉,刘爱伦.基于小波变换的信号消噪及其在软测量中的应用[J].自动化仪表,2003,24(2):8-10
[15] Sungyong Park,Han Chenghun.A Nonlinear Soft Sensor Based on Multiv ariate Smoothing Procedure for Quality Estimation in Distillation Columns [J].Computers and Chemical Eng,2000,(24):871-877
[16]王树青.先进控制技术及应用[M] .北京:化学工业出版社,2000:45-58
[17]俞金寿,张爱伦.软测量技术及其应用[J].世界仪表及自动化,1997,1 (2):18-20.
[18] M.Karmy, K.Warwick. System Identification Using Partial Least Squares[J].IEE proc Control Theory Appl,1995,142(3):233-239.
[19] Tham M T. Soft Sensors Process Estimation and Inferential Control [J]. Process Control, 1991,(1):3-14.
[20] Huni K.J, Sbarbaro D, et al. Neural Networks for Control System-A Survey[J], Automatic, 1992, 26(6):1083-1112.
[21] Spieker A, Najim K,et al,. Neural Networks Synthesis for Themal Process[J]. Proc Cont, 1993,3(4):233-239.
[22] Delgado A,Kambhampati C,Warwick K.Dynamic Recurrent Neural Network for System Identification and Control[J].AICHE, 1995 ,(142):307-314.
[23]李富春.基于数据的软测量建模方法及其应用的研究[D].北京:清华大学博士学位论文,2004:
[24] Vapnik V, Golowich S, Smola A.Support vector method for function approximation regression estimation and signal processing[M].MIT Press: Cambridge,MA,1997:281-287.
[25] Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[26] Christine P, Mark J W, Ming T T. A Fast Procedure for the Training of Neural Networks[J].Proc contr,1992, 2(4):205-213.
[27] Kramer M. A,. Nonlinear Principle Component Analysis Using Auto-associative Neural Networks [J]. AIChE, 1991, 37(1):233-243.
[28]张湜,陈士贤,张中秋.化工过程半经验模型的求取及回归方法和ANN方法的联合应用[J].石油化工自动化,1999,36(5):26-29.
[29]张杰,阳宪惠.多变量统计过程控制[M].北京:化学工业出版社,2000:
[30]王惠文.偏最小二乘回归方法及其应用[M].北京:国防工业出版社,1999:
[31] Wold H.Nonlinear estimation by iterative least squares procedures[M].New York:John Wiley & Sons,1996:108-154.
[32] Geladi P, Kowalski B R. Partial least squares regression a tutorial[J]. Analytica Chimica Acta,1986,(185):1-17
[33] Lorber A, Wangen L E,Kowalski B R.A theoretical foundation for the PLS algorithm [J].Chemometrics,1987,(1):19-31
[34] Kaspar M, Ray W H.Partial least squares modeling as successive singular value decompositions[J].Computers Chem Engng,1993,(17): 985~989
[35] Helland I S.On the structure of partial least squares regression [J].Comm Statist, Simulation Comput,1988,(17):581-607.
[36] de Jong S. PLS fits closer than PCR[J].Chemometrics,1993,(18):551-557.
[37] Astrom, Eykhoof. System identification a survey [J]. Automatica,1971, 7(2):123-162.
[38] Haber R., Parameter identification of nonlinear dynamic systems based on correlation functions[A]. In:5th IFAC-Aymp On Identification and system parameter Wstimation, Darmstadt,1979:515-522.
[39] Ljung L, Convergence analysis of parametric identification methods[J]. IEEE Transactions of Automatic Control, 1978,(1):770-783.
[40] Ljung L, T Soderstrom.Theory and Practice of Recursive Identification[M]. Cambridge: MIT Press, 1983:
[41] McAuley K B, MacGregor J F. On-line inference of polymer properties in an industrial polyethylene reactor [J]. AIChE J, 1991, 37(6):825-835
[42] Marquardt. Ridge regression in practice [J].The American Statistician,1975,(29):3-19.
[43] Wold S, Kettaneh Wold N, Skagerberg B.Nonlinear PLS modeling [J]. Chemomet Intell Lab Syst,1989,( 7):53-65.
[44] Berglund A, Wold S. INLR, implicit non-linear latent variable regression[J]. Chemometrics, 1997, (11): 141-156
[45] Frank. A nonlinear PLS model [J]. Chemomet Intel Lab Syst, 1990, (8): 109-119
[46] Wold S. Non-linear partial least squares modeling. II spline inner function[J]. Chemomet Intell Lab Syst, 1992,(14):71-84
[47] Baffi G, Martin E B, Morris A J. Non-linear projection to latent structures revisited: the quadratic PLS algorithm[J]. Computers Chem Engng, 1999a, (23): 395-411
[48] Qin S J, McAvoy T J. Nonlinear PLS Modeling Using Neural Network[J]. Computers Chem Engng, 1992, 16(4): 379-391
[49] Wilson D J H, Irwin G W, Lightbody G. Nonlinear PLS modeling using radial basis functions [C]. In:Proceedings of the American Control Conference, Albuquerque, New Mexico, 1997:
[50] Wilson D J H, Irwin G W, Lightbody G. Neural networks and multivariate SPC[C]. Proceedings of the IEE Colloquium on Fault Diagnosis in Process Systems, 1997,(5): 1-5
[51] Baffi G, Martin E B, Morris A J. Non-linear projection to latent structures revisited: the neural network PLS algorithm[J]. Computers Chem Engng, 1999b, (23): 1293-1307
[52] Min K G, Han I, Han C. Iterative error-based nonlinear PLS method of nonlinear chemical process modeling[J]. Journal of Chemical Engineering of Japan, 2002, 35(7): 613-625
[53] Li T, Mei H, Cong P. Combining nonlinear PLS with the numeric generic algorithm for QSAR[J]. Chemomet Intell Lab Syst, 1999, (45): 177-184
[54] Bang Y H, Yoo C K, Lee I B. Nonlinear PLS modeling with fuzzy inference system[J]. Chemomet Intell Lab Syst, 2003, (64): 137-155
[55] Holcomb T R, Morari M. PLS neural networks[J]. Computers Chem Engng, 1992, 16(4): 393-411
[56] Malthouse E C, Tamhane A C, Mah R S H. Non-linear partial least squares[J]. Computers Chem Engng, 1997,(21): 875-890
[57] S. Lakshminarayanan, Sirish L. Shah , K. Nandakumar. Modeling and control of multivariable processes: dynamic PLS approach. AIChE Journal,1997,43(9):2307-2322
[58] Wold. S, Geladi, P. Multi-way principal component analysis and PLS analysis[J]. Chemometrics, 1987,(1): 41-56
[59] Wold S. Exponentially weighted moving principal components analysis and projection to latent structures[J]. Chemomet Intel Lab Sys, 1994, (23): 149-161
[60] Helland K, Berntsen H E, Borgen O S, Martens H. Recursive algorithm for partial least squares regression[J]. Chemomet Intell Lab Sys, 1992,(14): 129-137
[61] Qin S J. Recursive PLS algorithms for adaptive data modeling[J]. Computers Chem Engng,1998, 22(4): 503-514
[62] Dayal B S, MacGregor J F. Improved PLS algorithms[J] Chemometrics, 1997b, (11): 73~85
[63] Dayal B S, MacGregor J F. Recursive exponentially weighted PLS and its application to adaptive control and prediction[J]. Process Control, 1997a, 7(3): 169-179
[64] Lindgren F, Geladi P, Wold S. The kernel algorithm for PLS[J] Chemometrics, 1993, (7): 45-59
[65] de Jong S, Ter Braak C J F. Modified kernel algorithm[J] Chemometrics, 1994, (8): 169
[66] Hoskuldsson. PLS regression methods [J]. Chemometrics, 1988, (2): 211-228
[67] Durand J F. Local polynomial additive regression through PLS and splines PLSS [J]. Chemometrics and Intelligent Laboratory Systems, 2001,(58): 235-246
[68]孟洁,王惠文,黄海军等.基于核函数变换的PLS回归的非线性结构分析[J].系统工程,2004,22(10):93-97
[69]梁林,李富春,王桂增.非线性递推部分最小二乘及其应用[J].系统仿真学报,2001,(13):119-122
[70]岑可法等.锅炉和热交换器的积灰、结渣、磨损和腐蚀的防止原理与计算[M].北京:水利电力出版社, 1994:
[71] D. Q. Kern and R. E. Season. Surface Fouling: How to Limit[J]. Br Chem,1959, 55(6):71-73
[72] N Epstein.Thinking about Heat Transfer Fouling: A 5*5 Matrix[J]. Heat Transfer Engineering, 1983, (41):43-56.
[73] J D Pinheiro, D Kakac et al,. Fouling of Heat Transfer Surface in Heat Exchangers: Thermal-Hydraulic Fundamentals and Design [M]. Hemisphere: New York,1981:1013-1035.
[74]叶光华.污染指数试验研究及其对反渗透系统影响分析[J].热电技术, 2003,(1):45-48
[75]周昊,孙平等.燃烧器下摆时冷灰斗内结渣的试验和数值模拟[J].中国电机工程学报,2000,(5):139-142
[76]张忠孝.用模糊数学方法对锅炉结渣特性的研究[J].中国电机工程学报,2000, (10): 64-66.
[77] Couch, G. Understanding Slagging and Fouling in PF Combustion[R]. London: IEA Coal Research, 1994:
[78] Srinivasachar. S, Senior. C. L, Helble. J. J, Moore. J. W. A Fundamental Approach to the Prediction of Coal Ash Deposit Formation in Combustion System[C].In:Twenty-fourth Symposium international on Combustion, 1992:1179-1187.
[79] Zygarlicke. C. J., Ramanatham. M., Erickson. T. A. Fly Ash Particle Size Distribution and Composition Experimental and Phenomenological Approach [A].In:Benson lorganic Transformation and Ash Deposition during Combustion[C], Engineering Foundation Press, 1992,(1):525-544
[80] Rechards. G. H., Slater. P. N., Harb. J. N., Simulation of Ash Deposit Growth in a Pulverized Coal-Fired Pilot Scale Reactor [J]. Energy & Fuels, 1993, (7):774-781
[81] Erickson. T. A., Allan. S. E, Mccollor. D. P., Hurley. J. P. Modeling of Fouling and Slagging in Coal Fired Utility Boiler [J]. Fuel Processing Technology,1995,(44):155-171
[82]陈宝康.电站锅炉受热面污染监测及优化吹灰的理论与实验研究[D].保定:华北电力大学博士学位论文,2004:
[83] Yori, L.G., Dams, .H., Kleppe, J.A., Acoustic pyrmeter: picture windows to boiler performance[J]. Power, 1991,135(8):65-67
[84] Bretz, E. A., Infra-red sensor detects fouling[J]. maintains efficiency Power,1989, 133(8):84-85
[85] Pavinski. D., Romero. C., et al.Approach to boiler sootblowing for optimizing NOx and heat rate[J]. Instrumentation, Control, and Automation in the Power Industry, 1996,36(6): 155-162
[86] Afgan. N.H., He, X., et al. Knowledge based system for fouling assessment of power plant boiler[J]. Heat and Technology, 1999,17(1):63-70
[87] Cortes. C., Bella. O., Valero. A. Ash fouling monitoring and sootblowing optimization in a pulverized coal-fired utility boiler[C].In: proc 10th Inter Pittsburgh Coal Conf, Pittsburgh, PA, USA:1993:703-708.
[88] N Afgan, M G Carvalho, P Coelho. Concept of Expert System for Boiler Fouling Assessment [J].Applied Thermal Engineering,1996,16(10): 835-844.
[89] M Bangham, J Patton.Intelligent controller for optimized sootblowing :Phase II Results[C].In:EPRI Heat Rate Conference,1998: 21-30.
[90] Richard E.Thompson, et al. A Fouling Monitor Alarm To Prevent Forced Outages[C]. In:International Joint Power Generation Conference and Exposition and the International Conference on Power Engineering,USA: 1999:25-28.
[91]程伟良.管式换热器积灰监测模型的研究[J].现代电力,1999,16(3):52-57.
[92]王广军,栾秀春.基于人工神经网络的电站锅炉受热面污染部位诊断[J].锅炉技术,2000,31(11):28-32.
[93]武彬,沈幼庭.基于模糊神经网络的锅炉受热面积灰监测[J].发电设备, 1999,(3):29-34.
[94]王建国,徐志明.空气预热器积灰在线监测模型[J].电机工程学报, 2000,(7):37-39
[95]阎维平,梁秀俊等.300MW燃煤电站锅炉积灰结渣计算机在线监测与优化吹灰[J].电机工程学报, 2000, (9):84-88.
[96]陈宝康,阎维平,李霄飞.基于神经网络的电站锅炉辐射受热面污染监测[J].动力工程,2002,23(5):2660-2664.
[97]阎维平,陈宝康,梁秀俊等.电站锅炉回转式空气预热器积灰监测模型的研究[J].动力工程,2003,22(2):1708-1710.
[98]陈宝康,阎维平,朱予东等.燃煤电站锅炉对流受热面灰污层增长预测模型的研究[J].华北电力大学学报,2004,31(2):32-35.
[99] Qin S J. Recursive PLS Algorithms for Adaptive Data Modeling[J].Computers Chem Engng,1998,(22):503-514
[100] Helland K, Berntsen H E, Borgen O S. Recursive Algorithm for Partial Least Squares Regression[J].Chemometrics Intell Lab Syst,1992,(14):129.
[101]方崇智,萧德云.过程辨识[M].北京:清华大学出版社,1988:
[102]宋凯,王海清,李平.折息递推PLS算法及其在橡胶混炼质量控制中的应用[J].化工学报,2004,55(6):942-946.
[103]舒迪前.预测控制系统及其应用[M].北京:机械工业出版社,1998:
[104]席裕庚,厉隽怿.一类工业过程预测控制的闭环分析[J].自动化学报, 1995,21(1):1-8
[105]杨景祺,戈黎红,凌荣生.超临界参数机组控制系统的特点及其控制策略[J].中国动力工程学报,2005,25(2):221-225
[106]张玉铎,王满稼.热工自动控制系[M].北京:水利水电出版社,1984:
[107]张铁军,吕剑虹,于开江.热工过程模糊决策预测控制的应用研究[J].中国电机工程学报, 2004, 24(6):179-184.
[108]雎刚,韦红旗,陈绍炳,等.单元机组负荷多变量模型预测控制[J].中国电机工程学报, 2002,22(4):144-148.
[109]翟军勇,费树岷.基于在线学习的多模型自适应控制[J].电机工程学报,2005,25(9):80-83.
[110]张铁军,吕剑虹,华志刚.机炉协调系统的模糊增益调度预测控制[J].中国电机工程学报,2005,25(4):159-165
[111]范永胜,徐治皋,陈来九.基于动态特性机理分析的锅炉过热汽温自适应模糊控制系统研究[J].中国电机工程学报, 1997,17(1):23-28
[112] Vapnik V N. The Nature of statistical Learning Theory[M].New York: Springer-Verlag, 1995:
[113] Müller K-R ,Mika S ,Ratsch G, et al . An introduction to kernel based learning algorithms[J].IEEE transactions on neural networks,2001,12 (2) :181-202
[114] Scholkopf B , Smola A, Muller K R.Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J]. Neural Computation, 1998,(1):1299-1319
[115] Rosipal R , Trejo L J ,Matt hews B ,et al . Nonlinear Kernel Based Chemomet ric Tools : a Machine Learning Approach[C]. In: Proceedings of 3rd International Symposium on PLS and Related Methods ,Lisbon ,Portugal 2003:249-260.
[116] Rosipal R ,Leonard J T. Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space1Journal of Machine Learning Research ,2001 , (2) :97-123
[117]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].北京:科学出版社,2004:
[118] Mercer J. Functions of positive and negative type and their connection with the theory of integral equation[J ]. Philosophical Transactions of the Royal Society of London :A,1909, (209):415-446
[119] Evgeniou T, Pontil M, Poggio T. A unified framework for regularization networks and support vector machines[R]. Technical Report CBCL paper #171/AI Momo#1654: Massachusetts Institute of Technology, 1999:
[120] Wahba G. Spline models for observational data [C].In:Paper Regional Conference Series in Mathematics 59,Philadelpha:Society for industrial and Applied Mathematics, 1990:
[121] Wahba G. Support vector machines, reproducing kernel Hilbert spaces and the randomized GACV [C]. In: Advances in kernel Methods-Support Vector Learning, MIT Press, 1999:69-88
[122] Boser B E, Guyon I M, Vapnik V. A training algorithm for optimal margin classifiers[A]. In: Proceedings of the 5th Annual ACM workshop on computational learning Theory[C], Pittsbrugh, PA, July ACM Press, 1992: 144-152
[123] Roman Rosipal, Leonard Trejo, Bryan Matthews. Kernel PLS-SVC for linear and nonlinear classification[C]. In: Proc of the 20th Int Conf on Machine Learning,Washington, 2003:640-647.
[124] Suykens J A K, Vandewalle J. Least Squares Support Vector Machine Classifiers [J]. Neural Processing Letters, 1999, 9(3):293-300.
[125] Bai Yifeng, Xiao Jan, Yu Long. Kernel Partial Least-Squares Regression[A]. In: 2006 International Joint Conference on Neural Networks[C], Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada, 2006:1231-1238.
[126] Baerker M, Rayens W. A partial least squares paradigm for discrimination[J].Chemometrics, 2003, (17):166-173.
[127]左志雄,向军,叶永松,等.大型锅炉氮氧化物排放特性试验研究[J].华中电力, 2001, 14(5):9-11
[128]周昊,朱洪波,曾庭华,等.大型四角切圆燃烧锅炉NOx排放特性的神经网络模型[J].中国电机工程学报, 2002, 22(1):33-37
[129]王春林,周昊,周樟华等.基于支持向量机的大型电厂锅炉飞灰含碳量建模[J].中国电机工程学报, 2002, 25(20):72-76
[130]周昊,朱洪波,曾庭华,等.基于人工神经网络的大型电厂锅炉飞灰含碳量建模[J].中国电机工程学报, 2002, 22(6):96-100
[2]阎世辉.我国燃煤电厂二氧化硫减排技术经济分析[J].环境保护, 2003, (4): 46-48.
[3]王志轩.我国火电厂污染控制现状与"十五"计划的目标、措施[J].环境保护, 2003, (4): 49-51.
[4]赵洁,赵锦洋.火电结构优化和技术升级研究的回顾与展望[M].北京:中国电力出版社, 2005: 16-19.
[5]吕太,罗伟民,王雷,等.国内燃煤电厂烟气脱硫现状与展望[J] .东北电力学院学报,2000,20(2):68-74.
[6]高亹.我国电力工业的展望[J].东南大学学报,2005,35(1):159-165.
[7]王新新.中国的能源安全与能源战略选择[J].北京:中国科技论坛,2007,1:51.
[8]崔民选.2007年能源蓝皮书[M].北京:社会科学文献出版社, 2007:266-273
[9] Luo R F, Shao H H, Zhang Z J. Fuzzy-neural-net-Based inferential Control for a High-purity Distillation Column [J]. Control Eng Practice, 1995, 3(1):31-41.
[10]王树青.先进控制技术及应用[M].北京:化学工业出版社,2000:15-18,31
[11]于静江,周春晖.过程控制中的软测量技术[J] .控制理论与应用,1996,13(2):137-144
[12]俞金寿,刘爱伦,张克进.软测量技术及其在石油化工中的应用[M].北京:化学工业出版社,2000:170-188
[13]刘瑞兰,苏宏业,褚健.PLS回归软测量方法在催化重整稳定油组分估计中的应用[J].化工自动化及仪表,2002,29(5):44-47
[14]吴朝辉,刘爱伦.基于小波变换的信号消噪及其在软测量中的应用[J].自动化仪表,2003,24(2):8-10
[15] Sungyong Park,Han Chenghun.A Nonlinear Soft Sensor Based on Multiv ariate Smoothing Procedure for Quality Estimation in Distillation Columns [J].Computers and Chemical Eng,2000,(24):871-877
[16]王树青.先进控制技术及应用[M] .北京:化学工业出版社,2000:45-58
[17]俞金寿,张爱伦.软测量技术及其应用[J].世界仪表及自动化,1997,1 (2):18-20.
[18] M.Karmy, K.Warwick. System Identification Using Partial Least Squares[J].IEE proc Control Theory Appl,1995,142(3):233-239.
[19] Tham M T. Soft Sensors Process Estimation and Inferential Control [J]. Process Control, 1991,(1):3-14.
[20] Huni K.J, Sbarbaro D, et al. Neural Networks for Control System-A Survey[J], Automatic, 1992, 26(6):1083-1112.
[21] Spieker A, Najim K,et al,. Neural Networks Synthesis for Themal Process[J]. Proc Cont, 1993,3(4):233-239.
[22] Delgado A,Kambhampati C,Warwick K.Dynamic Recurrent Neural Network for System Identification and Control[J].AICHE, 1995 ,(142):307-314.
[23]李富春.基于数据的软测量建模方法及其应用的研究[D].北京:清华大学博士学位论文,2004:
[24] Vapnik V, Golowich S, Smola A.Support vector method for function approximation regression estimation and signal processing[M].MIT Press: Cambridge,MA,1997:281-287.
[25] Suykens J A K, Vandewalle J. Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[26] Christine P, Mark J W, Ming T T. A Fast Procedure for the Training of Neural Networks[J].Proc contr,1992, 2(4):205-213.
[27] Kramer M. A,. Nonlinear Principle Component Analysis Using Auto-associative Neural Networks [J]. AIChE, 1991, 37(1):233-243.
[28]张湜,陈士贤,张中秋.化工过程半经验模型的求取及回归方法和ANN方法的联合应用[J].石油化工自动化,1999,36(5):26-29.
[29]张杰,阳宪惠.多变量统计过程控制[M].北京:化学工业出版社,2000:
[30]王惠文.偏最小二乘回归方法及其应用[M].北京:国防工业出版社,1999:
[31] Wold H.Nonlinear estimation by iterative least squares procedures[M].New York:John Wiley & Sons,1996:108-154.
[32] Geladi P, Kowalski B R. Partial least squares regression a tutorial[J]. Analytica Chimica Acta,1986,(185):1-17
[33] Lorber A, Wangen L E,Kowalski B R.A theoretical foundation for the PLS algorithm [J].Chemometrics,1987,(1):19-31
[34] Kaspar M, Ray W H.Partial least squares modeling as successive singular value decompositions[J].Computers Chem Engng,1993,(17): 985~989
[35] Helland I S.On the structure of partial least squares regression [J].Comm Statist, Simulation Comput,1988,(17):581-607.
[36] de Jong S. PLS fits closer than PCR[J].Chemometrics,1993,(18):551-557.
[37] Astrom, Eykhoof. System identification a survey [J]. Automatica,1971, 7(2):123-162.
[38] Haber R., Parameter identification of nonlinear dynamic systems based on correlation functions[A]. In:5th IFAC-Aymp On Identification and system parameter Wstimation, Darmstadt,1979:515-522.
[39] Ljung L, Convergence analysis of parametric identification methods[J]. IEEE Transactions of Automatic Control, 1978,(1):770-783.
[40] Ljung L, T Soderstrom.Theory and Practice of Recursive Identification[M]. Cambridge: MIT Press, 1983:
[41] McAuley K B, MacGregor J F. On-line inference of polymer properties in an industrial polyethylene reactor [J]. AIChE J, 1991, 37(6):825-835
[42] Marquardt. Ridge regression in practice [J].The American Statistician,1975,(29):3-19.
[43] Wold S, Kettaneh Wold N, Skagerberg B.Nonlinear PLS modeling [J]. Chemomet Intell Lab Syst,1989,( 7):53-65.
[44] Berglund A, Wold S. INLR, implicit non-linear latent variable regression[J]. Chemometrics, 1997, (11): 141-156
[45] Frank. A nonlinear PLS model [J]. Chemomet Intel Lab Syst, 1990, (8): 109-119
[46] Wold S. Non-linear partial least squares modeling. II spline inner function[J]. Chemomet Intell Lab Syst, 1992,(14):71-84
[47] Baffi G, Martin E B, Morris A J. Non-linear projection to latent structures revisited: the quadratic PLS algorithm[J]. Computers Chem Engng, 1999a, (23): 395-411
[48] Qin S J, McAvoy T J. Nonlinear PLS Modeling Using Neural Network[J]. Computers Chem Engng, 1992, 16(4): 379-391
[49] Wilson D J H, Irwin G W, Lightbody G. Nonlinear PLS modeling using radial basis functions [C]. In:Proceedings of the American Control Conference, Albuquerque, New Mexico, 1997:
[50] Wilson D J H, Irwin G W, Lightbody G. Neural networks and multivariate SPC[C]. Proceedings of the IEE Colloquium on Fault Diagnosis in Process Systems, 1997,(5): 1-5
[51] Baffi G, Martin E B, Morris A J. Non-linear projection to latent structures revisited: the neural network PLS algorithm[J]. Computers Chem Engng, 1999b, (23): 1293-1307
[52] Min K G, Han I, Han C. Iterative error-based nonlinear PLS method of nonlinear chemical process modeling[J]. Journal of Chemical Engineering of Japan, 2002, 35(7): 613-625
[53] Li T, Mei H, Cong P. Combining nonlinear PLS with the numeric generic algorithm for QSAR[J]. Chemomet Intell Lab Syst, 1999, (45): 177-184
[54] Bang Y H, Yoo C K, Lee I B. Nonlinear PLS modeling with fuzzy inference system[J]. Chemomet Intell Lab Syst, 2003, (64): 137-155
[55] Holcomb T R, Morari M. PLS neural networks[J]. Computers Chem Engng, 1992, 16(4): 393-411
[56] Malthouse E C, Tamhane A C, Mah R S H. Non-linear partial least squares[J]. Computers Chem Engng, 1997,(21): 875-890
[57] S. Lakshminarayanan, Sirish L. Shah , K. Nandakumar. Modeling and control of multivariable processes: dynamic PLS approach. AIChE Journal,1997,43(9):2307-2322
[58] Wold. S, Geladi, P. Multi-way principal component analysis and PLS analysis[J]. Chemometrics, 1987,(1): 41-56
[59] Wold S. Exponentially weighted moving principal components analysis and projection to latent structures[J]. Chemomet Intel Lab Sys, 1994, (23): 149-161
[60] Helland K, Berntsen H E, Borgen O S, Martens H. Recursive algorithm for partial least squares regression[J]. Chemomet Intell Lab Sys, 1992,(14): 129-137
[61] Qin S J. Recursive PLS algorithms for adaptive data modeling[J]. Computers Chem Engng,1998, 22(4): 503-514
[62] Dayal B S, MacGregor J F. Improved PLS algorithms[J] Chemometrics, 1997b, (11): 73~85
[63] Dayal B S, MacGregor J F. Recursive exponentially weighted PLS and its application to adaptive control and prediction[J]. Process Control, 1997a, 7(3): 169-179
[64] Lindgren F, Geladi P, Wold S. The kernel algorithm for PLS[J] Chemometrics, 1993, (7): 45-59
[65] de Jong S, Ter Braak C J F. Modified kernel algorithm[J] Chemometrics, 1994, (8): 169
[66] Hoskuldsson. PLS regression methods [J]. Chemometrics, 1988, (2): 211-228
[67] Durand J F. Local polynomial additive regression through PLS and splines PLSS [J]. Chemometrics and Intelligent Laboratory Systems, 2001,(58): 235-246
[68]孟洁,王惠文,黄海军等.基于核函数变换的PLS回归的非线性结构分析[J].系统工程,2004,22(10):93-97
[69]梁林,李富春,王桂增.非线性递推部分最小二乘及其应用[J].系统仿真学报,2001,(13):119-122
[70]岑可法等.锅炉和热交换器的积灰、结渣、磨损和腐蚀的防止原理与计算[M].北京:水利电力出版社, 1994:
[71] D. Q. Kern and R. E. Season. Surface Fouling: How to Limit[J]. Br Chem,1959, 55(6):71-73
[72] N Epstein.Thinking about Heat Transfer Fouling: A 5*5 Matrix[J]. Heat Transfer Engineering, 1983, (41):43-56.
[73] J D Pinheiro, D Kakac et al,. Fouling of Heat Transfer Surface in Heat Exchangers: Thermal-Hydraulic Fundamentals and Design [M]. Hemisphere: New York,1981:1013-1035.
[74]叶光华.污染指数试验研究及其对反渗透系统影响分析[J].热电技术, 2003,(1):45-48
[75]周昊,孙平等.燃烧器下摆时冷灰斗内结渣的试验和数值模拟[J].中国电机工程学报,2000,(5):139-142
[76]张忠孝.用模糊数学方法对锅炉结渣特性的研究[J].中国电机工程学报,2000, (10): 64-66.
[77] Couch, G. Understanding Slagging and Fouling in PF Combustion[R]. London: IEA Coal Research, 1994:
[78] Srinivasachar. S, Senior. C. L, Helble. J. J, Moore. J. W. A Fundamental Approach to the Prediction of Coal Ash Deposit Formation in Combustion System[C].In:Twenty-fourth Symposium international on Combustion, 1992:1179-1187.
[79] Zygarlicke. C. J., Ramanatham. M., Erickson. T. A. Fly Ash Particle Size Distribution and Composition Experimental and Phenomenological Approach [A].In:Benson lorganic Transformation and Ash Deposition during Combustion[C], Engineering Foundation Press, 1992,(1):525-544
[80] Rechards. G. H., Slater. P. N., Harb. J. N., Simulation of Ash Deposit Growth in a Pulverized Coal-Fired Pilot Scale Reactor [J]. Energy & Fuels, 1993, (7):774-781
[81] Erickson. T. A., Allan. S. E, Mccollor. D. P., Hurley. J. P. Modeling of Fouling and Slagging in Coal Fired Utility Boiler [J]. Fuel Processing Technology,1995,(44):155-171
[82]陈宝康.电站锅炉受热面污染监测及优化吹灰的理论与实验研究[D].保定:华北电力大学博士学位论文,2004:
[83] Yori, L.G., Dams, .H., Kleppe, J.A., Acoustic pyrmeter: picture windows to boiler performance[J]. Power, 1991,135(8):65-67
[84] Bretz, E. A., Infra-red sensor detects fouling[J]. maintains efficiency Power,1989, 133(8):84-85
[85] Pavinski. D., Romero. C., et al.Approach to boiler sootblowing for optimizing NOx and heat rate[J]. Instrumentation, Control, and Automation in the Power Industry, 1996,36(6): 155-162
[86] Afgan. N.H., He, X., et al. Knowledge based system for fouling assessment of power plant boiler[J]. Heat and Technology, 1999,17(1):63-70
[87] Cortes. C., Bella. O., Valero. A. Ash fouling monitoring and sootblowing optimization in a pulverized coal-fired utility boiler[C].In: proc 10th Inter Pittsburgh Coal Conf, Pittsburgh, PA, USA:1993:703-708.
[88] N Afgan, M G Carvalho, P Coelho. Concept of Expert System for Boiler Fouling Assessment [J].Applied Thermal Engineering,1996,16(10): 835-844.
[89] M Bangham, J Patton.Intelligent controller for optimized sootblowing :Phase II Results[C].In:EPRI Heat Rate Conference,1998: 21-30.
[90] Richard E.Thompson, et al. A Fouling Monitor Alarm To Prevent Forced Outages[C]. In:International Joint Power Generation Conference and Exposition and the International Conference on Power Engineering,USA: 1999:25-28.
[91]程伟良.管式换热器积灰监测模型的研究[J].现代电力,1999,16(3):52-57.
[92]王广军,栾秀春.基于人工神经网络的电站锅炉受热面污染部位诊断[J].锅炉技术,2000,31(11):28-32.
[93]武彬,沈幼庭.基于模糊神经网络的锅炉受热面积灰监测[J].发电设备, 1999,(3):29-34.
[94]王建国,徐志明.空气预热器积灰在线监测模型[J].电机工程学报, 2000,(7):37-39
[95]阎维平,梁秀俊等.300MW燃煤电站锅炉积灰结渣计算机在线监测与优化吹灰[J].电机工程学报, 2000, (9):84-88.
[96]陈宝康,阎维平,李霄飞.基于神经网络的电站锅炉辐射受热面污染监测[J].动力工程,2002,23(5):2660-2664.
[97]阎维平,陈宝康,梁秀俊等.电站锅炉回转式空气预热器积灰监测模型的研究[J].动力工程,2003,22(2):1708-1710.
[98]陈宝康,阎维平,朱予东等.燃煤电站锅炉对流受热面灰污层增长预测模型的研究[J].华北电力大学学报,2004,31(2):32-35.
[99] Qin S J. Recursive PLS Algorithms for Adaptive Data Modeling[J].Computers Chem Engng,1998,(22):503-514
[100] Helland K, Berntsen H E, Borgen O S. Recursive Algorithm for Partial Least Squares Regression[J].Chemometrics Intell Lab Syst,1992,(14):129.
[101]方崇智,萧德云.过程辨识[M].北京:清华大学出版社,1988:
[102]宋凯,王海清,李平.折息递推PLS算法及其在橡胶混炼质量控制中的应用[J].化工学报,2004,55(6):942-946.
[103]舒迪前.预测控制系统及其应用[M].北京:机械工业出版社,1998:
[104]席裕庚,厉隽怿.一类工业过程预测控制的闭环分析[J].自动化学报, 1995,21(1):1-8
[105]杨景祺,戈黎红,凌荣生.超临界参数机组控制系统的特点及其控制策略[J].中国动力工程学报,2005,25(2):221-225
[106]张玉铎,王满稼.热工自动控制系[M].北京:水利水电出版社,1984:
[107]张铁军,吕剑虹,于开江.热工过程模糊决策预测控制的应用研究[J].中国电机工程学报, 2004, 24(6):179-184.
[108]雎刚,韦红旗,陈绍炳,等.单元机组负荷多变量模型预测控制[J].中国电机工程学报, 2002,22(4):144-148.
[109]翟军勇,费树岷.基于在线学习的多模型自适应控制[J].电机工程学报,2005,25(9):80-83.
[110]张铁军,吕剑虹,华志刚.机炉协调系统的模糊增益调度预测控制[J].中国电机工程学报,2005,25(4):159-165
[111]范永胜,徐治皋,陈来九.基于动态特性机理分析的锅炉过热汽温自适应模糊控制系统研究[J].中国电机工程学报, 1997,17(1):23-28
[112] Vapnik V N. The Nature of statistical Learning Theory[M].New York: Springer-Verlag, 1995:
[113] Müller K-R ,Mika S ,Ratsch G, et al . An introduction to kernel based learning algorithms[J].IEEE transactions on neural networks,2001,12 (2) :181-202
[114] Scholkopf B , Smola A, Muller K R.Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J]. Neural Computation, 1998,(1):1299-1319
[115] Rosipal R , Trejo L J ,Matt hews B ,et al . Nonlinear Kernel Based Chemomet ric Tools : a Machine Learning Approach[C]. In: Proceedings of 3rd International Symposium on PLS and Related Methods ,Lisbon ,Portugal 2003:249-260.
[116] Rosipal R ,Leonard J T. Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space1Journal of Machine Learning Research ,2001 , (2) :97-123
[117]邓乃扬,田英杰.数据挖掘中的新方法-支持向量机[M].北京:科学出版社,2004:
[118] Mercer J. Functions of positive and negative type and their connection with the theory of integral equation[J ]. Philosophical Transactions of the Royal Society of London :A,1909, (209):415-446
[119] Evgeniou T, Pontil M, Poggio T. A unified framework for regularization networks and support vector machines[R]. Technical Report CBCL paper #171/AI Momo#1654: Massachusetts Institute of Technology, 1999:
[120] Wahba G. Spline models for observational data [C].In:Paper Regional Conference Series in Mathematics 59,Philadelpha:Society for industrial and Applied Mathematics, 1990:
[121] Wahba G. Support vector machines, reproducing kernel Hilbert spaces and the randomized GACV [C]. In: Advances in kernel Methods-Support Vector Learning, MIT Press, 1999:69-88
[122] Boser B E, Guyon I M, Vapnik V. A training algorithm for optimal margin classifiers[A]. In: Proceedings of the 5th Annual ACM workshop on computational learning Theory[C], Pittsbrugh, PA, July ACM Press, 1992: 144-152
[123] Roman Rosipal, Leonard Trejo, Bryan Matthews. Kernel PLS-SVC for linear and nonlinear classification[C]. In: Proc of the 20th Int Conf on Machine Learning,Washington, 2003:640-647.
[124] Suykens J A K, Vandewalle J. Least Squares Support Vector Machine Classifiers [J]. Neural Processing Letters, 1999, 9(3):293-300.
[125] Bai Yifeng, Xiao Jan, Yu Long. Kernel Partial Least-Squares Regression[A]. In: 2006 International Joint Conference on Neural Networks[C], Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada, 2006:1231-1238.
[126] Baerker M, Rayens W. A partial least squares paradigm for discrimination[J].Chemometrics, 2003, (17):166-173.
[127]左志雄,向军,叶永松,等.大型锅炉氮氧化物排放特性试验研究[J].华中电力, 2001, 14(5):9-11
[128]周昊,朱洪波,曾庭华,等.大型四角切圆燃烧锅炉NOx排放特性的神经网络模型[J].中国电机工程学报, 2002, 22(1):33-37
[129]王春林,周昊,周樟华等.基于支持向量机的大型电厂锅炉飞灰含碳量建模[J].中国电机工程学报, 2002, 25(20):72-76
[130]周昊,朱洪波,曾庭华,等.基于人工神经网络的大型电厂锅炉飞灰含碳量建模[J].中国电机工程学报, 2002, 22(6):96-100