火电厂热工参数软测量关键技术和方法研究
|
摘要
我国火力发电的能源利用率相对较低,主要影响因素之一是许多重要的技术参数和经济参数难以在线实时测量,如与锅炉效率密切相关的烟气含氧量、飞灰含碳量、球磨机负荷等热工参数。软测量技术是解决这些参数测量问题的有效方法之一,它利用一些易于测量的变量通过在线分析来估计这些不可测或难测变量。
本文围绕热工参数软测量的几个关键技术问题,展开了以下研究:
1.全面分析火电厂监测对象及热工参数的特点,讨论影响热工参数软测量精度的主要因素为:数据预处理、辅助变量选取、建模算法、模型结构。
2.从数据预处理及辅助变量选取两个关键技术问题出发,研究提高火电厂热工参数软测量精度和可行性的方法:数据预处理方面,充分考虑现场数据的误差分析与处理;辅助变量选取方面,引入灰色理论进行优化选取,提高模型的精度和可行性。
3.建模算法支持向量机,其自身参数对建模精度有很大影响。本文提出基于训练数据的参数自适应支持向量回归建模方法,减少参数选择过程中的人为因素影响和精度不确定性问题。使用实际现场数据对烟气含氧量进行软测量建模,验证了该方法的有效性。
4.将具有快速收敛特性的序列最小优化(SMO)算法与粒子群(PSO)算法相结合,提出PSO-SMO软测量建模方法,以基于训练数据得到的算法参数为初始值,应用双层优化方法进一步优化,提高建模精度及模型收敛速度。
5.针对火电厂热工参数监测的实时性要求,将以上所提出的建模算法在典型的DCS现场控制站硬件配置条件下和在QNX实时操作系统环境中编程实现。应用现场数据进行建模,实际运行结果满足工业现场的要求,具有很好的工程实践意义。
6.为使软测量模型能够更好地适应现场工况变化和测量对象的动态特性,对软测量模型的结构进行研究,提出多模型动态软测量建模方法。应用火电厂多工况历史数据,建立基于多支持向量机模型(M-SMO)的烟气含氧量和飞灰含碳量软测量模型,结果表明多模型建模方法能够满足热工过程变工况条件下的精度要求。
The energy utilization efficiency of thermal power generation is relatively low,one of the main influence factors is that lots of important technical parameters and economic parameters are difficult to be real-time measured online,such as oxygen content in flue gas,carbon content in fly ash,ball mill load and other thermal parameters related to boiler efficiency closely.Soft sensor technology is one of the effective ways to solve the problem of measuring these parameters,utilizing some parameters liable to be measured through on-line analysis to estimate these variables unable or difficult to be measured.
The following researches are expanded focusing on several key technical problems of soft sensor for thermal parameters:
1.This paper comprehensively analyses the characteristics of monitoring objects and thermal parameters in power plant as well as discusses main factors which affect the accuracy of soft sensor for thermal parameters.The results of the discussion were summarized as follows:data preprocessing,auxiliary variables selection,modeling algorithm and model structure.
2.Two key technical problems are put forward-data preprocessing and auxiliary variables selection.This paper researches on the methods of improving the accuracy and feasibility of soft sensor for thermal parameters in power plant:adequately considering the error analysis and processing of field data in one aspect of data preprocessing;introducing grey theory to make optimal selection in order to improve the accuracy and feasibility of the models in another aspect of auxiliary variables selection.
3.Modeling algorithm-supports vector machine-and its own parameters have a great impact on modeling accuracy.This paper presents a modeling method of parameter self-adaptive support vector machine based on training data which can reduce the impact of human factors and uncertainty of the accuracy in the process of parameter selection.The method has been applied to soft sensor modeling of oxygen content in flue gas using actual field data and its effectiveness is proved.
4.Combining the sequential minimal optimization(SMO) algorithm that has the characteristics of fast convergence with particle swarm optimization(PSO) algorithm,the modeling method of soft sensor based on PSO-SMO algorithm is proposed in this paper.The new model gets the algorithm parameters used as initial values from training data,using double-layer optimization method to get further optimization,thus improves modeling accuracy and convergence speed of the model.
5.According to the real-time requirements of thermal parameter monitoring in power plant,the modeling algorithm mentioned above is realized by programming under the conditions of typical hardware configuration of a distributed control unit in DCS and in the environment of real-time operating system of QNX.Modeling with field data,actual results meet the requirements of the industrial field,with great engineering practice significance.
6.To adapt better to the changes of field conditions and dynamic characteristics of measure object,this paper studies on the structure of soft sensor model and puts forward the modeling method of multi-model dynamic soft sensor.The method has been applied to soft sensor modeling of oxygen content in flue gas and carbon content in fly ash based on M-SMO with historical data under multiple load conditions in power plant.The result indicates that multi-model modeling method can meet the requirements of accuracy under variable conditions in the thermal process.
本文围绕热工参数软测量的几个关键技术问题,展开了以下研究:
1.全面分析火电厂监测对象及热工参数的特点,讨论影响热工参数软测量精度的主要因素为:数据预处理、辅助变量选取、建模算法、模型结构。
2.从数据预处理及辅助变量选取两个关键技术问题出发,研究提高火电厂热工参数软测量精度和可行性的方法:数据预处理方面,充分考虑现场数据的误差分析与处理;辅助变量选取方面,引入灰色理论进行优化选取,提高模型的精度和可行性。
3.建模算法支持向量机,其自身参数对建模精度有很大影响。本文提出基于训练数据的参数自适应支持向量回归建模方法,减少参数选择过程中的人为因素影响和精度不确定性问题。使用实际现场数据对烟气含氧量进行软测量建模,验证了该方法的有效性。
4.将具有快速收敛特性的序列最小优化(SMO)算法与粒子群(PSO)算法相结合,提出PSO-SMO软测量建模方法,以基于训练数据得到的算法参数为初始值,应用双层优化方法进一步优化,提高建模精度及模型收敛速度。
5.针对火电厂热工参数监测的实时性要求,将以上所提出的建模算法在典型的DCS现场控制站硬件配置条件下和在QNX实时操作系统环境中编程实现。应用现场数据进行建模,实际运行结果满足工业现场的要求,具有很好的工程实践意义。
6.为使软测量模型能够更好地适应现场工况变化和测量对象的动态特性,对软测量模型的结构进行研究,提出多模型动态软测量建模方法。应用火电厂多工况历史数据,建立基于多支持向量机模型(M-SMO)的烟气含氧量和飞灰含碳量软测量模型,结果表明多模型建模方法能够满足热工过程变工况条件下的精度要求。
The energy utilization efficiency of thermal power generation is relatively low,one of the main influence factors is that lots of important technical parameters and economic parameters are difficult to be real-time measured online,such as oxygen content in flue gas,carbon content in fly ash,ball mill load and other thermal parameters related to boiler efficiency closely.Soft sensor technology is one of the effective ways to solve the problem of measuring these parameters,utilizing some parameters liable to be measured through on-line analysis to estimate these variables unable or difficult to be measured.
The following researches are expanded focusing on several key technical problems of soft sensor for thermal parameters:
1.This paper comprehensively analyses the characteristics of monitoring objects and thermal parameters in power plant as well as discusses main factors which affect the accuracy of soft sensor for thermal parameters.The results of the discussion were summarized as follows:data preprocessing,auxiliary variables selection,modeling algorithm and model structure.
2.Two key technical problems are put forward-data preprocessing and auxiliary variables selection.This paper researches on the methods of improving the accuracy and feasibility of soft sensor for thermal parameters in power plant:adequately considering the error analysis and processing of field data in one aspect of data preprocessing;introducing grey theory to make optimal selection in order to improve the accuracy and feasibility of the models in another aspect of auxiliary variables selection.
3.Modeling algorithm-supports vector machine-and its own parameters have a great impact on modeling accuracy.This paper presents a modeling method of parameter self-adaptive support vector machine based on training data which can reduce the impact of human factors and uncertainty of the accuracy in the process of parameter selection.The method has been applied to soft sensor modeling of oxygen content in flue gas using actual field data and its effectiveness is proved.
4.Combining the sequential minimal optimization(SMO) algorithm that has the characteristics of fast convergence with particle swarm optimization(PSO) algorithm,the modeling method of soft sensor based on PSO-SMO algorithm is proposed in this paper.The new model gets the algorithm parameters used as initial values from training data,using double-layer optimization method to get further optimization,thus improves modeling accuracy and convergence speed of the model.
5.According to the real-time requirements of thermal parameter monitoring in power plant,the modeling algorithm mentioned above is realized by programming under the conditions of typical hardware configuration of a distributed control unit in DCS and in the environment of real-time operating system of QNX.Modeling with field data,actual results meet the requirements of the industrial field,with great engineering practice significance.
6.To adapt better to the changes of field conditions and dynamic characteristics of measure object,this paper studies on the structure of soft sensor model and puts forward the modeling method of multi-model dynamic soft sensor.The method has been applied to soft sensor modeling of oxygen content in flue gas and carbon content in fly ash based on M-SMO with historical data under multiple load conditions in power plant.The result indicates that multi-model modeling method can meet the requirements of accuracy under variable conditions in the thermal process.
引文
[1]李海青,黄志尧,等.软测量技术原理及应用.北京:化学工业出版社,2000.
[2]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.北京:化学工业出版社,2000.
[3]汪东生,邵惠鹤.通用软测量软件包的开发与应用.化工自动化及仪表.2000,27(2):34-36.
[4]王剑东,王东风,韩璞.软测量技术及其在电厂热工过程中的应用.电站系统工程,2002,18(5):49-51.
[5]王跃宣,苏宏业,牟盛静,褚健.组件化软测量软件包的开发与应用.化工自动化及仪表.2003,30(3):43-46.
[6]Solihin M,Wahyudi D.Development of soft sensor for sensodess automatic gantry crane using RBF neural networks.Cybernetics and Intelligent Systems,2006,7(9):1-6.
[7]Arthur K.Robust soft sensors on integration of genetic programming analytical neural networks and support vector machines Evolutionary Computation.Proceedings of the 2002 Congress on Volume:1,12-17 May 2002:896-901.
[8]Meng E.Fuzzy neural networks based quality prediction system for sintering process.IEEE Trans.On Fuzzy Systems,2002,8(3):314-324.
[9]Nybom H,Kortelainen J,Jakobsson J.Freeness soft sensor in TMP-refining.Control Systems 2004 Conference,2004:227-311.
[10]Badhe Y,Tambe S,Kulkarni D.Soft-sensor development for fed-batch bioreactors using support vector regression.Biochemical Engineering Journal,2006,27(3):225-239.
[11]韩璞,王东风,翟永杰.基于神经网络的火电厂烟气含氧量软测量.信息与控制,2001,30(2):189-192.
[12]赵征.基于数据融合的氧量软测量技术的研究[硕士学位论文].保定:华北电力大学,2004.
[13]熊志化,邵惠鹤,张卫庆.基于支持向量机的火电厂烟气含氧量软测量.测控技术,2004,23(8):15-16.
[14]卢勇,徐向东.烟气含氧量软测量新方法研究.热能动力工程,2002,17(102):614-617,655.
[15]王东风,宋之平.基于神经元网络的制粉系统球磨机负荷软测量.中国电机工程学报,2001,21(12):97-99,104.
[16]王立志,翟永杰,于鹏娟,等.软测量技术在电厂锅炉监视及调整系统中的应用.电站系统工程,2005,21(3):55-26,59.
[17]Sarkar P,Gupta S K.Steady state simulation of continuous-flow stirred-tank slurry propylene polymerization reactors.Polymer Engineering and Science,1992,32(11):732-742.
[18]Sarkar P,Gupta S.Dynamic simulation of propylene polymerization in continuous flow stirred tank reactors.Polymer Engineering and Science,1993,33(6):368-374.
[19]McAuley B,Macgregor F.On-line inference of polymer properties in an industrial polyethylene reactor.AIChE Journal,1991,37(6):825-835.
[20]Sato C,Ohtani T,Nishitani H.Modeling simulation and nonlinear control of a gas -phase polymedzation process.Computers Chem.Engng,2000,24(2-7):945-951.
[21]王建国,彭雅轩,徐志明,等.电站锅炉省煤器积灰状态在线软测量方法.仪表技术与传感器.2005(3):24-25.
[22]金林,沈炯.乏气送粉锅炉煤粉浓度软测量技术及仿真研究.热能动力工程,2001,16(92):175-178,225.
[23]Wold S,Trygg J,Berglund A,Antti H.Some recent developments in PLS modeling,Chemometrics and Intelligent Laboratory Systems,2001,58:131-150.
[24]Geladi P,Kowalski B.Partial Least Squares Regression(PLS):A Tutorial,Analytical Chemical Acta,1986,185(1):1-17.
[25]Wold S,Kettaneh-Wold N.Nonlinear PLS Modeling,Chemometrics and Intelligent Laboratory Systems,1989,7:53-65.
[26]Hoskuldsson A.PLS Regression Methods,Journal of Chemomtrics,1988,(2):211-228.
[27]Mejdell T,Skogestad S.Estimation of distillation composition from multiple temperature measurements using partial least squares regression.Ind.Eng.Chem.Res.1991,30:2543-2555.
[28]MacGregor J,Jaeckle C,Kiparissides C.Process monitoring and diagnosis by multiblock PLS methods.AIChE Journal,1994,40(5):826-838.
[29]Piovoso J,Kosanovch A.Application of multivariate statistical methods to process monitoring and controller design.Int.J.Control,1994,59(3):743-756.
[30]Tham T,Montague G,Morris A.Soft-sensors for process estimation and inferential control.J.Process Control,1991,1(1):3-14.
[31]Guilandoust M T,Morris A J,Tham M T.Adaptive inferential control.IEE Proceedings-D,1987,134(3):171-179.
[32]Guilandoust M T,Mords A J,Tham M T.An adaptive estimation algorithm for nferential eontrol.Ind.Eng.Chem.Res.,1988,27:1658-1664.
[33]Quintero-Marmol E,Luyben W L,Georgakis C.Application of an extended Luenberger observer to the control of multicomponent batch distillation.Ind.Eng.Chem.Res.,1991,30(8):1870-1880.
[34]Bhat N V,McAvoy T J.Use of neural nets for dynamic modeling and control of chemical process system.Computers Chem.Engng,2000,14(4-5):573-583.
[35]Pollard J F,Broussard M R,Garrison D B.Analysis of contrasting neural network with small-world network.Computers Chem.Engng,2008,16(4):57-60.
[36]Ydstie B E.Foreeasting and control using adaptive connectionist networks.Computers Chem.Engng.,1990,14(4-5):583-599.
[37]Ressom H.Soft-Sensing Using Recurrent Neural Networks.Proceedings of the 1998IEEE ISIC/CIRA/ISAS Joint Conference,Gaithersburg,MD.September,1998:342-347.
[38]Yoo C K,Lee I B.Soft Sensor and Adaptive Model-based Dissolved Oxygen Control for Biological Wastewater Treatment Processes.Environmental Engineering Science,2004,21(3):331-340.
[39]McLoone S,Irwin C.Nonlinear optimization of RBF networks.International Journal of Systems Science,1998,29(2):179-189.
[40]王守觉,曲延锋,李卫军,覃鸿.基于仿生模式识别与传统模式识别的人脸识别效果比较研究.电子学报,2004,32(7):1057-1061.
[41]王建平,陈军,徐晓冰,王熹徽.基于SVM的脱机手写汉字机器学习识别方法研究.计算机技术与发展,2006,16(10):104-107.
[42]侯风雷.基于说话人聚类和支持向量的说话人确认研究.计算机应用,2002,22(10):33-35.
[43]付岩,王耀威,王伟强,高文.SVM用于基于内容的自然图像分类和检索.计算机学报,2003,26(10):1261-265.
[44]Drezet P M L,Harrison R F.Support vector machines for system identification.Proceedings of IACC International Conference on Control,1998(1):688-692.
[45]徐大平,杨金芳,翟永杰,韩璞.SVR的限定记忆在线辨识算法及其应用.动力工程,2005,25(5):680-684.
[46]Sayan Mukherjee,Edgar Osuna,and Federico Girosi.Nonlinear prediction of chaotic time series using support vector machines.Proceedings of IEEE NNSP'97,1997(9):24-26.
[47]孙德山,吴今培,肖健华.SVR在混沌时间序列预测中的应用.系统仿真学报,2004,16(3):519-521.
[48]Poyhonen S,Negrea M,Arkkio A,et al.Support vector classification for fault diagnostics of an electrical machine.Proceeding of International Conference on Signal Processing,2002:26-30.
[49]肖健华,樊可清,吴今培.应用于故障诊断的SVM理论研究.振动、测试与诊断,2001,21(4):258-262.
[50]Suykens J A K,Vandewalle J,De Moor B.Optimal control by least squares support vector machines.Neural Networks,2001,14(1):23-35.
[51]deKruifBJ,deVriesTJA.On using a support vector machine in learning feed-forward control.Proceedings of 2001 IEEE/ASME International Conference on Advanced Intelligent Mechatroncs,2001(1):272-277.
[52]曲文龙,樊广俭,杨炳儒.基于支持向量机的复杂时间序列预测研究.计算机工程,2005,31(23):1-3.
[53]赵昀,黄志尧.基于神经网络及机理分析的气力输送粉料质量流量软测量,仪器仪表学报,2000,21(4):360-363.
[54]Qi Haiyu,Zhou Xing-Gui,Liu Liang-Hong,Yuan Wei-Kang.A hybrid neural network-first principles model for ed-bed reactor,Chemical Engineering Science,1999,54(13-14):2521-2526.
[55]Georgieva P,Meireles M J.Knowledge-based hybrid modeling of a batch crystallization when ounting for nucleation,growth and agglomeration phenomena.Chemical Engineering Science.2003,58:3699 -3713.
[56]Psichogios D C,Ungar L H.A hybrid neural network-first principles approach to process modeling.AICHE 92,38(10):1499-1511.
[57]韩璞,王东风,周黎辉,等.火电厂计算机监控与监测.北京:中国水利电力出版社,2005.
[58]陈德新,于纪幸.传感器、仪表与发电厂监测技术.郑州:黄河水利出版社,2004.
[59]Xiong Zhi-hua,Zhu Feng,Shao Hui-he,et al.Application of thermal parameter soft sensor in power plant.Journal of Southeast University(English Edition),2005,21(1):44-47.
[60]熊志化,张卫庆,赵瑜,等.基于混合高斯过程的多模型热力参数测量软仪表.中国电机工程学报,2005,25(7):30-33,40.
[61]冯瑞,张浩然.基于SVM的软测量建模.信息与控制,2002,31(6):567-571.
[62]叶学民,彭波.燃煤电站锅炉飞灰含碳量偏高的原因分析与解决措施.锅炉技术,2004,35(3):49-51,58.
[63]冯长青.烟道型电站锅炉飞灰含碳量线测量技术研究.南京:南京理工大学,2003.
[64]刘鸿,周克毅.锅炉飞灰测碳仪的技术现状及发展趋势.锅炉技术,2004,35(2):65-68.
[65]吴戈,陆继东,余亮英,等.激光感生击穿光谱技术测量飞灰含碳量.热能动力工程,2005,20(4):365-368,411.
[66]李智,蔡九菊,郭宏.基于神经网络的电站锅炉飞灰含碳量软测量系统.节能技术,2004,22(126):6-7.
[67]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.中国电机工程学报,2002,22(6):96-100.
[68]王海群,张素贞,刘军.人工神经网络在燃煤锅炉含碳量测量中的应用.锅炉技术,2004,35(2):35-38.
[69]李智,蔡九菊,徐有宁,等.软测量技术在电站锅炉优化燃烧上的应用.过程工程学报,2004,4(6):549-553.
[70]陈敏生,刘定平.电站锅炉飞灰含碳量的优化控制.动力工程,2005,25(4):545-549.
[71]陈敏生,刘定成.基于核主元分析和支持向量机的电站锅炉飞灰含碳量软测量建模.华北电力大学学报,2006,33(1):72-75,92.
[72]陈强,王培红,李琳,等.电站锅炉飞灰含碳量在线软测量模型算法.电力系统自动化.2005,29(2):45-49.
[73]方湘涛,叶念渝.基于BP神经网络的电厂锅炉飞灰含碳量预测.华中科技大学学报(自然科学版),2003,31(12):75-77.
[74]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.中国电机工程学报,2005,25(20):72-76.
[75]王俊蕊.一种智能型球磨机载煤量测量装置的研究.保定:华北电力大学,2001.
[76]郝勇生,吕震中.基于软测量的球磨机制粉系统智能控制与优化决策.能源研究与利用,2003(4):21-24,48.
[77]张晓宏,谢京涛,唐贵基.球磨机载煤量测量装置的研究.河北农业大学学报,1997,20(4):97-100.
[78]王东风,韩璞.基于RBF神经网络的球磨机负荷软测量.仪器仪表学报,2002,23(3):311-312,317.
[79]梁秀满,孙文来.钢球磨煤机出口温度软测量方法.机械与电子,2000(6):14-16.
[80]王建国,彭雅轩,孙灵芳,等.电站锅炉烟气量在线软测量方法.仪器仪表学报,2002,23(3):756-757.
[81]陈丹,王劭伯.基于BP网络的火电厂煤仓煤位高度的软测量.工业控制计算机,2002,15(8):20-21,53.
[82]李勇,张瑞青,曹丽华.漏入汽轮机真空系统空气量的软测量.系统仿真学报,2003,15(3):444-446.
[83]刘福国,郝卫东,韩小岗,等.基于烟气成分分析的电站锅炉入炉煤质监测模型.燃烧科学与技术,2002,8(5):441-445.
[84]刘福国.电站锅炉入炉煤元素分析和发热量的软测量实时监测技术.中国电机工程学报,2005,25(6):139-145.
[85]刘吉臻,赵征,刘锦康,等.利用数据融合方法实现通风机流量软测量.华北电力大学学报,2005,32(3):61-65.
[86]董实现,徐向东.模糊神经网络在锅炉煤种辨识中的应用.清华大学学报(自然科学版),2004,44(8):1092-1095.
[87]许晨光.锅炉汽包水位软测量方法初探.华东电力,2005,33(8):47-50.
[88]樊绍胜,王耀南.基于模糊建模的冷凝器污脏软测量.控制理论与应用,2005,22(3):434-439.
[89]熊志化,杨辰,邵惠鹤,等.热力参数软仪表在电厂热工过程中的应用.武汉大学学报(工学版),2005,38(2):99-101.
[90]冯瑞,宋春林,张艳珠,等.基于支持向量机与RBF神经网络的软测量模型比较研究.上海交通大学学报,2003,37(增刊):122-125.
[91]冯瑞,张钥杰,张艳珠,等.基于加权支持向量机的移动建模方法及其在软测量中的应用.自动化学报,2004,30(3):436-441.
[92]桂卫华,李勇刚,阳春华,等.基于改进聚类算法的分布式SVM及其应用.控制与决策,2004,19(8):852-856.
[93]张英,苏宏业,褚健.一种基于支持向量机增量学习的软测量建模方法.化工自动化及仪表,2005,32(3):22-24.
[94]王华忠,俞金寿.基于混合SVR-PLS:疗法的丙烯腈收率软测量建模.控制与决策,2005,20(5):549-552.
[95]杨斌,田永清,朱仲英.智能建模方法中的数据预处理.信息与控制,2002,31(4):380-384.
[96]Ye H W,Ni W D.Nonlinear system identification using a Bayesian-Gaussian neural network for predictive control.Neurocomputing,1999,vol.28:21-36.
[97]叶海文.循环流化床锅炉建模与控制的人工神经网络方法研究[博士学位论文].北京:清华大学,1997.
[98]Iwan Solihin M,Wahyudi,Albagul A.Development of Soft Sensor for Sensorless Automatic Gantry Crane Using RBF Neural Networks.2006 IEEE Conference on Cybernetics and Intelligent Systems,2006 pp 1-6.
[99]王华忠,俞金寿.基于混合SVR-PLS方法的丙烯腈收率软测量建模.控制与决策,2005,5(3):32-36.
[100]张英,苏宏业,褚健.基于模糊最小二乘支持向量机的软测量建模.控制与决策,2005,6(23):12-16.
[101]李海生,朱学峰.支持向量机在纸浆蒸煮过程Kappa值软测量中的应用研究.计算机测量与控制,2004,11(7):45-51.
[102]Chang Y Q,Lv Z,Wang F L,MaoZ Z,Wang X G.Soft Sensing Modeling Based on Stacked Least Square-Support Vector Machine and Its Application.The Sixth World Congress on Intelligent Control and Automation,2006,vol.1:846-4850.
[103]Zhang H R,Wang X D,Zhang C J,Lv G.New Soft Sensor Method Based on SVM.2006 IEEE International Conference on Granular Computing:546-549.
[104]Bates J M,Granger C W J.The combination of forecasts.Operations Research Quarterly,1969,vol.20:319-323.
[105]Cho S B,Kim J H.Combining multiple neural networks by fuzzy integral for robust classification.IEEE Trans on Systems,Man and Cybernetics,1995,vol.25,no.2:380-384.
[106]吕伟杰,刘鲁源.多模型小波网络非线性动态系统辨识.信息与控制,2003,3(5):11-14.
[107]赵江,张贵炜,齐欢.发酵过程的多模型融合建模算法.信息与控制,2005,2(7):21-25.
[108]孙宗海,杨旭华,孙优贤.基于支持向量机的模糊回归估计.浙江大学学报,2005,6(8):63-67.
[109]Larose D T.Data Mining:Methods and Models.New Jersey:John Wiley & Sons,2006.
[110]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.北京:化学工业出版社,2000.
[111]王旭东,邵惠鹤.神经元网络建模与软测量技术.化工自动化及仪表,1996,(2):28-31.
[112]王俊峰.过程监测中的数据挖掘技术[硕士学位论文].广州:华南理工大学,2002.
[113]Nounou M N,Bakshi B R.On-line multiscale filtering of random and gross errors without process models.AIChEJ,1999,45(5):1041-1054.
[114]Serth R W,Heenan W A.Gross error detection and data rec-onciliation in steam-metering systems.AIChE J,1986,34(5):733-742.
[115]李华生,袁永根.过程系统测量数据校正技术.北京:中国石化出版社,1996.
[116]陈强.热工过程中的数据校正和多目标优化研究[博士学位论文].南京:东南大学,2004.
[117]付继华,孟浩,王中宇.基于灰色理论的动态测量系统非统计建模方法.仪器仪表学报,2008,7(6):1245-1249.
[118]孟庆超,莫志姣,谷正气,郭军朝.基于灰色理论的汽车室内空气品质评价研究.建筑热能通风空调,2007,26(2):74-77.
[119]邓聚龙.灰色系统理论教程.武汉:华中理工大学出版社,1990.37-60.
[120]邓聚龙.灰理论基础.武汉:华中科技大学出版社,2002:94-95.
[121]Vapnik VN,张学工[译].统计学习理论的本质.北京:清华大学出版社,2000.
[122]王兴玲,李占斌,等.基于网格搜索的支持向量机核函数参数的确定.中国海洋大学学报,2005,35(5):859-862.
[123]杨旭,纪玉波,等.基于遗传算法的SVM参数选取.辽宁石油化工大学学报,2004,24(1):54-58.
[124]Cherkasske V,Ma Y."Practical selection of SVM parameters and noise estimation for SVM regression",Neural Networks,2004,17(1),113-126.
[125]Drucker H,Burges C J,Kaufman L.Support Vector Regression Machines.In Mozer M.,Jordan M.,Jordan M.,and Petsche T.,editors,Advances in Neural Information Processing Systems 9.Cambridge,MA,1997,MIT Press,Page(s):155-161.
[126]Steve G.Support vector Machines Classification and Regression[R].ISIS Technical Report.Image Speech & Intelligent Systems Group,University of Southampton.May 10,1998.
[127]Keerthi S,Gilbert E.Convergence of a generalized SMO algorithm for classifier design.Machine Learning,2002,46(1/3):351-360.
[128]Gary W F,Steve L.Efficient SVM Regression Training with SMO.Machine Learning,2002,46:271-290.
[129]Hunt J,Sbarbaro D.Neural networks for nonlinear internal model control,lEE PROC.Control Theory and Applications,1991,138(5):431-438.
[130]Kennedy J,Eberhart R.Particle swarm optimization[A].Pro IEEE Int.Conf on Neural Networks.Perth,1995:1942-1948.
[131]Eberhart R,Kennedy J.A New Optimizer Using Particle Swarm Theory[A].Proceedings of Sixth International Symposium Micro Machine and Human Science,Nagoya,Japan,1995:39-43.
[132]谢晓锋,张文俊,杨之廉.微粒群算法综述.控制与决策,2003,18(2):129-134.
[133]蔡德聪等.工业控制计算机实时操作系统.北京:清华大学出版社,1999:25-73
[134]侯业勤,张箐.分布式嵌入式实时操作系统QNX.北京:宇航出版社,1999:5-35
[135]周强.基于QNX的分散控制系统现场控制站软件设计[硕士学位论文].保定:华北电力大学,2002.
[136]赵江,张贵炜,齐欢.发酵过程的多模型融合建模算法.信息与控制,2005,34(2):172-176,1R3.
[137]Murry S,Johansen T.Multiple model approaches to modeling and control London:Taylor and Francis,1997.
[138]Eikens B,Karimmn D.Process identification withmultipleneural network models.Int J Control,1999,72(7/8):576-590.
[139]Pottmann M,Unbehauenh S.Application of a general multi model approach for identification of highly nonlinear processed a case study.Int J Control,1993,57(1):97-120.
[140]罗健旭,邵惠鹤.应用多神经网络建立动态软测量模型.化工学报,2003,52(12):1770-1773.
[141]潘理黎,王佳莹,杨玉峰,等.火电厂飞灰含碳量在线监测设备现状.热力发电,2008,37(17):10-14.
[142]周建新,王雷,徐治皋,等.大型电站锅炉飞灰含碳量优化模型研究.锅炉技术,2008.39(03):21-24.
[2]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.北京:化学工业出版社,2000.
[3]汪东生,邵惠鹤.通用软测量软件包的开发与应用.化工自动化及仪表.2000,27(2):34-36.
[4]王剑东,王东风,韩璞.软测量技术及其在电厂热工过程中的应用.电站系统工程,2002,18(5):49-51.
[5]王跃宣,苏宏业,牟盛静,褚健.组件化软测量软件包的开发与应用.化工自动化及仪表.2003,30(3):43-46.
[6]Solihin M,Wahyudi D.Development of soft sensor for sensodess automatic gantry crane using RBF neural networks.Cybernetics and Intelligent Systems,2006,7(9):1-6.
[7]Arthur K.Robust soft sensors on integration of genetic programming analytical neural networks and support vector machines Evolutionary Computation.Proceedings of the 2002 Congress on Volume:1,12-17 May 2002:896-901.
[8]Meng E.Fuzzy neural networks based quality prediction system for sintering process.IEEE Trans.On Fuzzy Systems,2002,8(3):314-324.
[9]Nybom H,Kortelainen J,Jakobsson J.Freeness soft sensor in TMP-refining.Control Systems 2004 Conference,2004:227-311.
[10]Badhe Y,Tambe S,Kulkarni D.Soft-sensor development for fed-batch bioreactors using support vector regression.Biochemical Engineering Journal,2006,27(3):225-239.
[11]韩璞,王东风,翟永杰.基于神经网络的火电厂烟气含氧量软测量.信息与控制,2001,30(2):189-192.
[12]赵征.基于数据融合的氧量软测量技术的研究[硕士学位论文].保定:华北电力大学,2004.
[13]熊志化,邵惠鹤,张卫庆.基于支持向量机的火电厂烟气含氧量软测量.测控技术,2004,23(8):15-16.
[14]卢勇,徐向东.烟气含氧量软测量新方法研究.热能动力工程,2002,17(102):614-617,655.
[15]王东风,宋之平.基于神经元网络的制粉系统球磨机负荷软测量.中国电机工程学报,2001,21(12):97-99,104.
[16]王立志,翟永杰,于鹏娟,等.软测量技术在电厂锅炉监视及调整系统中的应用.电站系统工程,2005,21(3):55-26,59.
[17]Sarkar P,Gupta S K.Steady state simulation of continuous-flow stirred-tank slurry propylene polymerization reactors.Polymer Engineering and Science,1992,32(11):732-742.
[18]Sarkar P,Gupta S.Dynamic simulation of propylene polymerization in continuous flow stirred tank reactors.Polymer Engineering and Science,1993,33(6):368-374.
[19]McAuley B,Macgregor F.On-line inference of polymer properties in an industrial polyethylene reactor.AIChE Journal,1991,37(6):825-835.
[20]Sato C,Ohtani T,Nishitani H.Modeling simulation and nonlinear control of a gas -phase polymedzation process.Computers Chem.Engng,2000,24(2-7):945-951.
[21]王建国,彭雅轩,徐志明,等.电站锅炉省煤器积灰状态在线软测量方法.仪表技术与传感器.2005(3):24-25.
[22]金林,沈炯.乏气送粉锅炉煤粉浓度软测量技术及仿真研究.热能动力工程,2001,16(92):175-178,225.
[23]Wold S,Trygg J,Berglund A,Antti H.Some recent developments in PLS modeling,Chemometrics and Intelligent Laboratory Systems,2001,58:131-150.
[24]Geladi P,Kowalski B.Partial Least Squares Regression(PLS):A Tutorial,Analytical Chemical Acta,1986,185(1):1-17.
[25]Wold S,Kettaneh-Wold N.Nonlinear PLS Modeling,Chemometrics and Intelligent Laboratory Systems,1989,7:53-65.
[26]Hoskuldsson A.PLS Regression Methods,Journal of Chemomtrics,1988,(2):211-228.
[27]Mejdell T,Skogestad S.Estimation of distillation composition from multiple temperature measurements using partial least squares regression.Ind.Eng.Chem.Res.1991,30:2543-2555.
[28]MacGregor J,Jaeckle C,Kiparissides C.Process monitoring and diagnosis by multiblock PLS methods.AIChE Journal,1994,40(5):826-838.
[29]Piovoso J,Kosanovch A.Application of multivariate statistical methods to process monitoring and controller design.Int.J.Control,1994,59(3):743-756.
[30]Tham T,Montague G,Morris A.Soft-sensors for process estimation and inferential control.J.Process Control,1991,1(1):3-14.
[31]Guilandoust M T,Morris A J,Tham M T.Adaptive inferential control.IEE Proceedings-D,1987,134(3):171-179.
[32]Guilandoust M T,Mords A J,Tham M T.An adaptive estimation algorithm for nferential eontrol.Ind.Eng.Chem.Res.,1988,27:1658-1664.
[33]Quintero-Marmol E,Luyben W L,Georgakis C.Application of an extended Luenberger observer to the control of multicomponent batch distillation.Ind.Eng.Chem.Res.,1991,30(8):1870-1880.
[34]Bhat N V,McAvoy T J.Use of neural nets for dynamic modeling and control of chemical process system.Computers Chem.Engng,2000,14(4-5):573-583.
[35]Pollard J F,Broussard M R,Garrison D B.Analysis of contrasting neural network with small-world network.Computers Chem.Engng,2008,16(4):57-60.
[36]Ydstie B E.Foreeasting and control using adaptive connectionist networks.Computers Chem.Engng.,1990,14(4-5):583-599.
[37]Ressom H.Soft-Sensing Using Recurrent Neural Networks.Proceedings of the 1998IEEE ISIC/CIRA/ISAS Joint Conference,Gaithersburg,MD.September,1998:342-347.
[38]Yoo C K,Lee I B.Soft Sensor and Adaptive Model-based Dissolved Oxygen Control for Biological Wastewater Treatment Processes.Environmental Engineering Science,2004,21(3):331-340.
[39]McLoone S,Irwin C.Nonlinear optimization of RBF networks.International Journal of Systems Science,1998,29(2):179-189.
[40]王守觉,曲延锋,李卫军,覃鸿.基于仿生模式识别与传统模式识别的人脸识别效果比较研究.电子学报,2004,32(7):1057-1061.
[41]王建平,陈军,徐晓冰,王熹徽.基于SVM的脱机手写汉字机器学习识别方法研究.计算机技术与发展,2006,16(10):104-107.
[42]侯风雷.基于说话人聚类和支持向量的说话人确认研究.计算机应用,2002,22(10):33-35.
[43]付岩,王耀威,王伟强,高文.SVM用于基于内容的自然图像分类和检索.计算机学报,2003,26(10):1261-265.
[44]Drezet P M L,Harrison R F.Support vector machines for system identification.Proceedings of IACC International Conference on Control,1998(1):688-692.
[45]徐大平,杨金芳,翟永杰,韩璞.SVR的限定记忆在线辨识算法及其应用.动力工程,2005,25(5):680-684.
[46]Sayan Mukherjee,Edgar Osuna,and Federico Girosi.Nonlinear prediction of chaotic time series using support vector machines.Proceedings of IEEE NNSP'97,1997(9):24-26.
[47]孙德山,吴今培,肖健华.SVR在混沌时间序列预测中的应用.系统仿真学报,2004,16(3):519-521.
[48]Poyhonen S,Negrea M,Arkkio A,et al.Support vector classification for fault diagnostics of an electrical machine.Proceeding of International Conference on Signal Processing,2002:26-30.
[49]肖健华,樊可清,吴今培.应用于故障诊断的SVM理论研究.振动、测试与诊断,2001,21(4):258-262.
[50]Suykens J A K,Vandewalle J,De Moor B.Optimal control by least squares support vector machines.Neural Networks,2001,14(1):23-35.
[51]deKruifBJ,deVriesTJA.On using a support vector machine in learning feed-forward control.Proceedings of 2001 IEEE/ASME International Conference on Advanced Intelligent Mechatroncs,2001(1):272-277.
[52]曲文龙,樊广俭,杨炳儒.基于支持向量机的复杂时间序列预测研究.计算机工程,2005,31(23):1-3.
[53]赵昀,黄志尧.基于神经网络及机理分析的气力输送粉料质量流量软测量,仪器仪表学报,2000,21(4):360-363.
[54]Qi Haiyu,Zhou Xing-Gui,Liu Liang-Hong,Yuan Wei-Kang.A hybrid neural network-first principles model for ed-bed reactor,Chemical Engineering Science,1999,54(13-14):2521-2526.
[55]Georgieva P,Meireles M J.Knowledge-based hybrid modeling of a batch crystallization when ounting for nucleation,growth and agglomeration phenomena.Chemical Engineering Science.2003,58:3699 -3713.
[56]Psichogios D C,Ungar L H.A hybrid neural network-first principles approach to process modeling.AICHE 92,38(10):1499-1511.
[57]韩璞,王东风,周黎辉,等.火电厂计算机监控与监测.北京:中国水利电力出版社,2005.
[58]陈德新,于纪幸.传感器、仪表与发电厂监测技术.郑州:黄河水利出版社,2004.
[59]Xiong Zhi-hua,Zhu Feng,Shao Hui-he,et al.Application of thermal parameter soft sensor in power plant.Journal of Southeast University(English Edition),2005,21(1):44-47.
[60]熊志化,张卫庆,赵瑜,等.基于混合高斯过程的多模型热力参数测量软仪表.中国电机工程学报,2005,25(7):30-33,40.
[61]冯瑞,张浩然.基于SVM的软测量建模.信息与控制,2002,31(6):567-571.
[62]叶学民,彭波.燃煤电站锅炉飞灰含碳量偏高的原因分析与解决措施.锅炉技术,2004,35(3):49-51,58.
[63]冯长青.烟道型电站锅炉飞灰含碳量线测量技术研究.南京:南京理工大学,2003.
[64]刘鸿,周克毅.锅炉飞灰测碳仪的技术现状及发展趋势.锅炉技术,2004,35(2):65-68.
[65]吴戈,陆继东,余亮英,等.激光感生击穿光谱技术测量飞灰含碳量.热能动力工程,2005,20(4):365-368,411.
[66]李智,蔡九菊,郭宏.基于神经网络的电站锅炉飞灰含碳量软测量系统.节能技术,2004,22(126):6-7.
[67]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.中国电机工程学报,2002,22(6):96-100.
[68]王海群,张素贞,刘军.人工神经网络在燃煤锅炉含碳量测量中的应用.锅炉技术,2004,35(2):35-38.
[69]李智,蔡九菊,徐有宁,等.软测量技术在电站锅炉优化燃烧上的应用.过程工程学报,2004,4(6):549-553.
[70]陈敏生,刘定平.电站锅炉飞灰含碳量的优化控制.动力工程,2005,25(4):545-549.
[71]陈敏生,刘定成.基于核主元分析和支持向量机的电站锅炉飞灰含碳量软测量建模.华北电力大学学报,2006,33(1):72-75,92.
[72]陈强,王培红,李琳,等.电站锅炉飞灰含碳量在线软测量模型算法.电力系统自动化.2005,29(2):45-49.
[73]方湘涛,叶念渝.基于BP神经网络的电厂锅炉飞灰含碳量预测.华中科技大学学报(自然科学版),2003,31(12):75-77.
[74]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.中国电机工程学报,2005,25(20):72-76.
[75]王俊蕊.一种智能型球磨机载煤量测量装置的研究.保定:华北电力大学,2001.
[76]郝勇生,吕震中.基于软测量的球磨机制粉系统智能控制与优化决策.能源研究与利用,2003(4):21-24,48.
[77]张晓宏,谢京涛,唐贵基.球磨机载煤量测量装置的研究.河北农业大学学报,1997,20(4):97-100.
[78]王东风,韩璞.基于RBF神经网络的球磨机负荷软测量.仪器仪表学报,2002,23(3):311-312,317.
[79]梁秀满,孙文来.钢球磨煤机出口温度软测量方法.机械与电子,2000(6):14-16.
[80]王建国,彭雅轩,孙灵芳,等.电站锅炉烟气量在线软测量方法.仪器仪表学报,2002,23(3):756-757.
[81]陈丹,王劭伯.基于BP网络的火电厂煤仓煤位高度的软测量.工业控制计算机,2002,15(8):20-21,53.
[82]李勇,张瑞青,曹丽华.漏入汽轮机真空系统空气量的软测量.系统仿真学报,2003,15(3):444-446.
[83]刘福国,郝卫东,韩小岗,等.基于烟气成分分析的电站锅炉入炉煤质监测模型.燃烧科学与技术,2002,8(5):441-445.
[84]刘福国.电站锅炉入炉煤元素分析和发热量的软测量实时监测技术.中国电机工程学报,2005,25(6):139-145.
[85]刘吉臻,赵征,刘锦康,等.利用数据融合方法实现通风机流量软测量.华北电力大学学报,2005,32(3):61-65.
[86]董实现,徐向东.模糊神经网络在锅炉煤种辨识中的应用.清华大学学报(自然科学版),2004,44(8):1092-1095.
[87]许晨光.锅炉汽包水位软测量方法初探.华东电力,2005,33(8):47-50.
[88]樊绍胜,王耀南.基于模糊建模的冷凝器污脏软测量.控制理论与应用,2005,22(3):434-439.
[89]熊志化,杨辰,邵惠鹤,等.热力参数软仪表在电厂热工过程中的应用.武汉大学学报(工学版),2005,38(2):99-101.
[90]冯瑞,宋春林,张艳珠,等.基于支持向量机与RBF神经网络的软测量模型比较研究.上海交通大学学报,2003,37(增刊):122-125.
[91]冯瑞,张钥杰,张艳珠,等.基于加权支持向量机的移动建模方法及其在软测量中的应用.自动化学报,2004,30(3):436-441.
[92]桂卫华,李勇刚,阳春华,等.基于改进聚类算法的分布式SVM及其应用.控制与决策,2004,19(8):852-856.
[93]张英,苏宏业,褚健.一种基于支持向量机增量学习的软测量建模方法.化工自动化及仪表,2005,32(3):22-24.
[94]王华忠,俞金寿.基于混合SVR-PLS:疗法的丙烯腈收率软测量建模.控制与决策,2005,20(5):549-552.
[95]杨斌,田永清,朱仲英.智能建模方法中的数据预处理.信息与控制,2002,31(4):380-384.
[96]Ye H W,Ni W D.Nonlinear system identification using a Bayesian-Gaussian neural network for predictive control.Neurocomputing,1999,vol.28:21-36.
[97]叶海文.循环流化床锅炉建模与控制的人工神经网络方法研究[博士学位论文].北京:清华大学,1997.
[98]Iwan Solihin M,Wahyudi,Albagul A.Development of Soft Sensor for Sensorless Automatic Gantry Crane Using RBF Neural Networks.2006 IEEE Conference on Cybernetics and Intelligent Systems,2006 pp 1-6.
[99]王华忠,俞金寿.基于混合SVR-PLS方法的丙烯腈收率软测量建模.控制与决策,2005,5(3):32-36.
[100]张英,苏宏业,褚健.基于模糊最小二乘支持向量机的软测量建模.控制与决策,2005,6(23):12-16.
[101]李海生,朱学峰.支持向量机在纸浆蒸煮过程Kappa值软测量中的应用研究.计算机测量与控制,2004,11(7):45-51.
[102]Chang Y Q,Lv Z,Wang F L,MaoZ Z,Wang X G.Soft Sensing Modeling Based on Stacked Least Square-Support Vector Machine and Its Application.The Sixth World Congress on Intelligent Control and Automation,2006,vol.1:846-4850.
[103]Zhang H R,Wang X D,Zhang C J,Lv G.New Soft Sensor Method Based on SVM.2006 IEEE International Conference on Granular Computing:546-549.
[104]Bates J M,Granger C W J.The combination of forecasts.Operations Research Quarterly,1969,vol.20:319-323.
[105]Cho S B,Kim J H.Combining multiple neural networks by fuzzy integral for robust classification.IEEE Trans on Systems,Man and Cybernetics,1995,vol.25,no.2:380-384.
[106]吕伟杰,刘鲁源.多模型小波网络非线性动态系统辨识.信息与控制,2003,3(5):11-14.
[107]赵江,张贵炜,齐欢.发酵过程的多模型融合建模算法.信息与控制,2005,2(7):21-25.
[108]孙宗海,杨旭华,孙优贤.基于支持向量机的模糊回归估计.浙江大学学报,2005,6(8):63-67.
[109]Larose D T.Data Mining:Methods and Models.New Jersey:John Wiley & Sons,2006.
[110]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.北京:化学工业出版社,2000.
[111]王旭东,邵惠鹤.神经元网络建模与软测量技术.化工自动化及仪表,1996,(2):28-31.
[112]王俊峰.过程监测中的数据挖掘技术[硕士学位论文].广州:华南理工大学,2002.
[113]Nounou M N,Bakshi B R.On-line multiscale filtering of random and gross errors without process models.AIChEJ,1999,45(5):1041-1054.
[114]Serth R W,Heenan W A.Gross error detection and data rec-onciliation in steam-metering systems.AIChE J,1986,34(5):733-742.
[115]李华生,袁永根.过程系统测量数据校正技术.北京:中国石化出版社,1996.
[116]陈强.热工过程中的数据校正和多目标优化研究[博士学位论文].南京:东南大学,2004.
[117]付继华,孟浩,王中宇.基于灰色理论的动态测量系统非统计建模方法.仪器仪表学报,2008,7(6):1245-1249.
[118]孟庆超,莫志姣,谷正气,郭军朝.基于灰色理论的汽车室内空气品质评价研究.建筑热能通风空调,2007,26(2):74-77.
[119]邓聚龙.灰色系统理论教程.武汉:华中理工大学出版社,1990.37-60.
[120]邓聚龙.灰理论基础.武汉:华中科技大学出版社,2002:94-95.
[121]Vapnik VN,张学工[译].统计学习理论的本质.北京:清华大学出版社,2000.
[122]王兴玲,李占斌,等.基于网格搜索的支持向量机核函数参数的确定.中国海洋大学学报,2005,35(5):859-862.
[123]杨旭,纪玉波,等.基于遗传算法的SVM参数选取.辽宁石油化工大学学报,2004,24(1):54-58.
[124]Cherkasske V,Ma Y."Practical selection of SVM parameters and noise estimation for SVM regression",Neural Networks,2004,17(1),113-126.
[125]Drucker H,Burges C J,Kaufman L.Support Vector Regression Machines.In Mozer M.,Jordan M.,Jordan M.,and Petsche T.,editors,Advances in Neural Information Processing Systems 9.Cambridge,MA,1997,MIT Press,Page(s):155-161.
[126]Steve G.Support vector Machines Classification and Regression[R].ISIS Technical Report.Image Speech & Intelligent Systems Group,University of Southampton.May 10,1998.
[127]Keerthi S,Gilbert E.Convergence of a generalized SMO algorithm for classifier design.Machine Learning,2002,46(1/3):351-360.
[128]Gary W F,Steve L.Efficient SVM Regression Training with SMO.Machine Learning,2002,46:271-290.
[129]Hunt J,Sbarbaro D.Neural networks for nonlinear internal model control,lEE PROC.Control Theory and Applications,1991,138(5):431-438.
[130]Kennedy J,Eberhart R.Particle swarm optimization[A].Pro IEEE Int.Conf on Neural Networks.Perth,1995:1942-1948.
[131]Eberhart R,Kennedy J.A New Optimizer Using Particle Swarm Theory[A].Proceedings of Sixth International Symposium Micro Machine and Human Science,Nagoya,Japan,1995:39-43.
[132]谢晓锋,张文俊,杨之廉.微粒群算法综述.控制与决策,2003,18(2):129-134.
[133]蔡德聪等.工业控制计算机实时操作系统.北京:清华大学出版社,1999:25-73
[134]侯业勤,张箐.分布式嵌入式实时操作系统QNX.北京:宇航出版社,1999:5-35
[135]周强.基于QNX的分散控制系统现场控制站软件设计[硕士学位论文].保定:华北电力大学,2002.
[136]赵江,张贵炜,齐欢.发酵过程的多模型融合建模算法.信息与控制,2005,34(2):172-176,1R3.
[137]Murry S,Johansen T.Multiple model approaches to modeling and control London:Taylor and Francis,1997.
[138]Eikens B,Karimmn D.Process identification withmultipleneural network models.Int J Control,1999,72(7/8):576-590.
[139]Pottmann M,Unbehauenh S.Application of a general multi model approach for identification of highly nonlinear processed a case study.Int J Control,1993,57(1):97-120.
[140]罗健旭,邵惠鹤.应用多神经网络建立动态软测量模型.化工学报,2003,52(12):1770-1773.
[141]潘理黎,王佳莹,杨玉峰,等.火电厂飞灰含碳量在线监测设备现状.热力发电,2008,37(17):10-14.
[142]周建新,王雷,徐治皋,等.大型电站锅炉飞灰含碳量优化模型研究.锅炉技术,2008.39(03):21-24.