基于多率采样的焦炉火道温度软测量集成模型
|
摘要
焦炭是钢铁等行业的重要生产原料,广泛的应用于各行各业。焦炉加热燃烧过程是炼焦过程中重要的流程,火道温度直接影响到焦炭质量和能源消耗。然而由于成本等原因,往往难以实现实时测取火道温度;而人工测温,也存在周期太长,迟滞的缺点。本文针对焦炉火道温度不易测量,过程参数具有非线性、时变等特点,探究基于多率采样的焦炉火道温度软测量集成模型,在焦炉燃烧过程中的应用,实现实时测取火道温度的目标。
在细致分析本课题的研究背景和意义的基础上,本文采用软测量集成建模的思想来分析焦炉燃烧过程。从炼焦工艺出发,通过深入研究焦炉加热燃烧的工作机理,甄选出蓄热室顶部温度(后简称蓄顶温度)作为焦炉火道温度软测量过程参数。然后,针对蓄顶温度和火道温度的复杂关系,建立线性回归模型来拟合两者问的线性关系;而对蓄顶温度和焦炉火道温度之间的非线性关系,本文将线性回归模型的预测误差,视为两者非线性关系的影响所致,采用基于时间差分法的Elman神经网络来拟合和多步预测,并采用规则集成的方法,将两模型组合成长周期组合预测模型。然而长周期组合预测模型的缺乏较好的实时性,本文继而在分析火道温度和蓄顶温度采样的基础上,采用多率采样的思想,对长周期组合预测模型有效和失效时,分别构建曲线拟合预测模型和多项式预测模型,使原焦炉燃烧系统由多率系统,成功转变成单率系统,从而全面改善集成模型的实时预测性能。最后,为了使软测量离线模型更能适应工况的变化,提出了一种模型自学习策略,进一步改进了集成模型的预测精度和应对焦炉燃烧工况突变的能力。
建立在焦炉燃烧过程现场数据上的模型仿真,其对火道温度良好的拟合和预测效果,有力的佐证了基于多率采样的焦炉火道温度软测量集成模型的有效性和可行性。
Coke is the main raw material in metallurgy industry, and is widely used in various industries. The combustion process is an important part in coking process and the flue temperature has direct impacts on the coke quality and resource consumption. However, it is difficult to measure the flue temperature through real-time method with low cost. And even the manual measurement is used, it also has the shortage of long circle and time-delay. The flue temperature has the characteristics of nonlinearity and time-varying, which is difficult to be measured. An integral model design of soft sensor based on multi-rate sampling is put forward to acquire the real-time flue temperature in this thesis.
Based on the careful analysis of the background and significance of this subject, the thesis firstly decides to use the integral model, basing on the soft sensor, to analyze the coking combustion process. In the view of technical mechanism from coking process, the regenerator top temperature is selected, which to be used as the process parameter of the coke oven flue temperature's soft sensor. Aiming at analyzing the complex relationship between regenerator top temperature and flue temperature, linear regress models (LR) are employed to reflect the linear relationship between them. Then in order to reflect the nonlinear relationship between them and predict multi-step ahead, the model combines the temporal difference method and Elman neural network (TD-ENN) is created. The TD-ENN is built on the basis of linear regress models' errors and then, the LR and TD-ENN are integrated as the combined predictable model (CPM) with some important rules. However, when the CPM is created on the long period data, it lack of good real-time ability. Then the multi-rate method is used to solve the CPM's deficiency. The curve fitting predictive model and the polynomial predictive model are built on the multi-rate method, consequently, when the CPM is valid or invalid, the shortage of the CPM is offset by one of the models respectively and the coking system is transforming from multi-rate to single rate successfully. At last, in order to fit the variable working condition well, the self-learning strategy is integrated in the combined model and the ability of the model is improved obviously. The effective drawings of the model simulation are built on the field data, the accurate precision of the prediction proves the high performance of the integrated coke oven flue temperature soft sensor model basing on the multi-rate.
在细致分析本课题的研究背景和意义的基础上,本文采用软测量集成建模的思想来分析焦炉燃烧过程。从炼焦工艺出发,通过深入研究焦炉加热燃烧的工作机理,甄选出蓄热室顶部温度(后简称蓄顶温度)作为焦炉火道温度软测量过程参数。然后,针对蓄顶温度和火道温度的复杂关系,建立线性回归模型来拟合两者问的线性关系;而对蓄顶温度和焦炉火道温度之间的非线性关系,本文将线性回归模型的预测误差,视为两者非线性关系的影响所致,采用基于时间差分法的Elman神经网络来拟合和多步预测,并采用规则集成的方法,将两模型组合成长周期组合预测模型。然而长周期组合预测模型的缺乏较好的实时性,本文继而在分析火道温度和蓄顶温度采样的基础上,采用多率采样的思想,对长周期组合预测模型有效和失效时,分别构建曲线拟合预测模型和多项式预测模型,使原焦炉燃烧系统由多率系统,成功转变成单率系统,从而全面改善集成模型的实时预测性能。最后,为了使软测量离线模型更能适应工况的变化,提出了一种模型自学习策略,进一步改进了集成模型的预测精度和应对焦炉燃烧工况突变的能力。
建立在焦炉燃烧过程现场数据上的模型仿真,其对火道温度良好的拟合和预测效果,有力的佐证了基于多率采样的焦炉火道温度软测量集成模型的有效性和可行性。
Coke is the main raw material in metallurgy industry, and is widely used in various industries. The combustion process is an important part in coking process and the flue temperature has direct impacts on the coke quality and resource consumption. However, it is difficult to measure the flue temperature through real-time method with low cost. And even the manual measurement is used, it also has the shortage of long circle and time-delay. The flue temperature has the characteristics of nonlinearity and time-varying, which is difficult to be measured. An integral model design of soft sensor based on multi-rate sampling is put forward to acquire the real-time flue temperature in this thesis.
Based on the careful analysis of the background and significance of this subject, the thesis firstly decides to use the integral model, basing on the soft sensor, to analyze the coking combustion process. In the view of technical mechanism from coking process, the regenerator top temperature is selected, which to be used as the process parameter of the coke oven flue temperature's soft sensor. Aiming at analyzing the complex relationship between regenerator top temperature and flue temperature, linear regress models (LR) are employed to reflect the linear relationship between them. Then in order to reflect the nonlinear relationship between them and predict multi-step ahead, the model combines the temporal difference method and Elman neural network (TD-ENN) is created. The TD-ENN is built on the basis of linear regress models' errors and then, the LR and TD-ENN are integrated as the combined predictable model (CPM) with some important rules. However, when the CPM is created on the long period data, it lack of good real-time ability. Then the multi-rate method is used to solve the CPM's deficiency. The curve fitting predictive model and the polynomial predictive model are built on the multi-rate method, consequently, when the CPM is valid or invalid, the shortage of the CPM is offset by one of the models respectively and the coking system is transforming from multi-rate to single rate successfully. At last, in order to fit the variable working condition well, the self-learning strategy is integrated in the combined model and the ability of the model is improved obviously. The effective drawings of the model simulation are built on the field data, the accurate precision of the prediction proves the high performance of the integrated coke oven flue temperature soft sensor model basing on the multi-rate.
引文
[1]郭焰.行业动态[J].山东化工,2004(1):55
[2]侯顺义.提高原燃料质量降低产品成本[J].冶金财会,2004,12:37
[3]于振东,蔡承祜.焦炉生产技术[M].沈阳:辽宁科学技术出版社,2003
[4]张永发,王鹏,谢克昌.中国焦化工业实现洁净可持续发展的思考[J].山西能源与节能,2005,37(2):13-2
[5]姚昭章.炼焦学[M].北京:冶金工业出版社,1995
[6]Obayashi S,Sasaki D.Multiobjective evolutionary computation for supersonic wingshape optimization[J].IEEE Transactions on Evolutionary Computation,2000,4(2):182-187
[7]Sargent R W H.Introduction:25 years of progress in process systems engineering[J].Computers and Chemical Engineering,2004,28(11):437-439
[8]蔡自兴,徐光祐.人工智能及其应用[M].北京:清华大学出版社,2003
[9]Lin B,Recke B,Knudsen J K H,Jorgensen S B.A systematic approach for soft sensor development[J].Computers and Chemical Engineering.2007,31(5):419-425
[10]曾黄麟.智能计算:关于粗集、模糊逻辑、神经网络的理论及其应用[M].重庆:重庆大学出版社,2004
[11]焦李成,刘静,钟伟才.协同进化计算与多智能体系统[M].北京:科学出版社,2006
[12]Niva Y,Watanabe Y,Inaba M.Upgrading of computerized combustion control in coke oven[C].Ironmaking Conference Proceedings,1989,72(5):421-425
[13]王国.节能降耗技术在焦化工艺中的应用[J].本钢技术,2007,4(1):28-30.
[14]Brosilow C B.Inferential control of process control[J].AIChE Journal,1978,24(3):475-484
[15]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(4):137-144
[16]阚晓旭,金晓明.RBF多模型神经网络软测量技术在湿法磷酸生产中的应用[J].化工自动化及仪表,2006,33(1):64-66
[17]陈凯,王秀丽,郑贵堂,等.低成本智能加热控制系统在焦炉上的应用[J].计控系统,2002,5:22-23
[18]张汉卿,梁鸿飞,刑建通.对焦炉边火道温度控制标准的学习与探讨[J]. 河南冶金,1995,16(4):13-15
[19]骆光强,温治,陈鸿复,等.焦炉燃烧室.炭化室传热过程数学模型[J].燃料与化工,1998,29(2):78-82
[20]李芳,骆光强,温治,等.焦炉火道温度数学模型[J].燃料与化工,2000,31(1):9-13
[21]姚昭章.焦炉加热自动控制系统数学模型的评述[J].燃料与化工,1997,28(4):191-196
[22]严文福,郑明东,宁方青,等.模拟火道温度采集方法的研究[J].燃料与化工,2000,31(2):67-69
[23]叶斌,郑明东,严文福.焦炉模拟火道温度采集方法的研究[J].上海金属,2000,22(6):21-24
[24]高军伟,叶阳东,史天运,等.焦炉加热智能控制系统的研究与应用[J].信息与控制,2003,32(1):86-90
[25]Shi T Y,Jia L M,Bai C M.Research and development of integrated intelligent control system of coking stove combustion[C].Proceedings of the 4th World Congress on Intelligent Control and Automation,Shanghai,2002:2347-2352
[26]邹肇村.宝钢三期焦炉加热控制系统[J].冶金自动化,1999,5:16-19
[27]Barbier C.Automatic control of heating by "CRAPO" system in the coke oven plant at Solmer[C].Ironmaking Conference Proceedings,1983,66:261-268
[28]Nakazaki A,Matsuo T,Nakagawa Y.Application and effects of automatic control of coke oven[C].Ironmaking Conference Proceedings,1987,70:299-306
[29]Battel E T,Chen K L.Automatic coke oven heating control system at Burn Harbor Works for normal and repair operation[C].Ironmaking Conference Proceedings,1997,80:499-504
[30]Hollo P V,Verfaille J,Munnix R.希德马焦化厂的加热和过程控制[C].第二届国际焦化会议论文集.北京:冶金工业出版社,1992:294-299
[31]Choi K I.A mathematical model for the estimation of flue temperature in a coke oven[C].Ironmaking Conference Proceedings,1997,80:107-113
[32]Watanabe Y,Inaba M.Upgrading of computerized combustion control in coke oven[C].Ironmaking Conference Proceedings,1989,72:421-425
[33]魏剑侠译.八幡厂5号炉炭化室控制加热系统投产[J].国外炼焦化学,1983,(1):23-28
[34]Thijssen N J W,Vander T.Influences of the measured coke end temperature on coke battery heating[C].Ironmaking Conference Proceedings,1984,67:209-214
[35]Ding F,Chen T W.Modeling and identification of multirate system[J].Acta automatica sinic,2005,31(11):105-122
[36]Kranc G.M.Input-Output analysis of multirate feedback systems[J],IEEE Transactions on Automatic Control,1957,3(6):21-28
[37]Meyer R A,Burrus C S.Design and implementation of multirate digital filters [J].IEEE Transactions on Circuits Systems.1975,22(2):162-168
[38]Miyawaki T,Barnes C W.Multirate recursive digital filters-A general approach and block structures[J].IEEE Transactions on Acoustics Speech,Signal Processing,1983,ASSP-31:1148-1154
[39]Khargonekar P P,Poola K,Tannenbaum A.Robust control of linear time-invariant plants using periodic compensation[J].IEEE Transactions on Automatic Control.1985,AC-30(11):1180-1197
[40]Zhu K Y,Ling K V.Multirate control for a gasification process[C].Proceedings of the American Control Conference,Maryland.1994,3:3268-3272
[41]Embirucu M,Fontes C.Multirate multivariable generalized predictive control and its application to a slurry reactor for ethylene polymerization[J].Chemical Engineering Science,2006,61(2):5754-5756
[42]严文福,郑明东,宁芳青,等.火道温度随结焦时间与换向时间变化规律的研究[J].煤炭学报,2004,29(1):93-96
[43]叶斌,郑明东,严文福.焦炉模拟火道温度采集方法的研究[J].上海金属,2000,11(6):21-24
[44]郑明东,宁方青.焦炉立火道温度控制研究[J].大连理工大学学报,2001,41(7):442-445
[45]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
[46]Fortuna L,Graziani S,Xibilia M G..Soft sensors for product quality monitoring in debutanizer distillation columns[J],Control Engineering Practice,2005,13(4):499-508
[47]刘瑞兰.软测量技术若干问题的研究及工业应用[D],浙江大学博士学位论文,2004
[48]Meyer D G..A parameterization of stabilizing controllers for multirate sampled-data systems[J].IEEE Transactions on Automatic Control,1990,35(2): 233-236
[49]彭安民.非单率系统及其广义预测控制研究[D],江南大学硕士学位论文,2006
[50]杨欣荣.智能仪器原理、设计和发展(第二版)[M].湖南:中南大学出版社,2006
[51]范金城,梅长林.数据分析[M].北京:科学出版社,2002
[52]王旭东,邵惠鹤.基于神经网络的通用软测量技[J].自动化学报,1998,24(5):702-706
[53]Adilson J A,Rubens M F.Soft sensors development for on-line bioreactor state estimation[J].Computers and Chemical Engineering,2000,24(5):1099-1103
[54]孙彦广,高克伟,陶百生.基于智能技术的钢水温度软测量[J].仪器仪表学报.2002,23(3):754-755
[55](美)塞伯著,方开泰等译.线性回归分析[M].北京:科学出版社,1987
[56]曹卫华,侯少云,吴敏.基于集成模型的焦炉火道温度软测量技术研究及应用[J].计算机测量与控制,2006,14(2):149-151
[57]雷琪,吴敏,曹卫华,等.焦炉立火道温度的智能集成软测量方法及其应用[J].华东理工大学学报,2006,7
[58]Yao X,Liu Y.A new evolutionary system for evolving artificial neural networks [J].IEEE Transactions on Neural Networks,1997,8(3):129-138
[59]Rumelhart D,James L,Mcclelland and the PDP Research Group.Parallel distributed processing.Exploration in the Microstructure of Cognition.Vol.1 &2[C].Cambridge,MA:MIT Press,1986
[60]金龙,陈宁.基于人工神经网络的集成预报方法研究和比较[J].气象学报,1999,7(2):198-206
[61]李翔.从复杂到有序—神经网络智能控制理论新进展[M].上海:上海交通大学出版社,2006
[62]Sutton R S.Learning to predict by the methods of temporal differences[J].Machine Learning,1988 3(1):9-44
[63]Anderson,C.W.Learning and problem solving with multilayer connectionist systems[D].Doctoral dissertation,Department of Computer and Information Science,University of Massachusetts,Amherst,1986
[64]Anderson,C.W.Strategy learning with multilayer connectionist representations [C].Proceedings of the Fourth International Workshop on Machine Learning,1987 1:103-114
[65]Gao X Z,Ovaska S J,Vasilakos A V.Temporal difference method-based multi-step prediction of long term deep fading in mobile networks[J].Computer communications.2002,2(5):1477-1486
[66]王雪松,程玉虎,易建强,等,基于Elman网络的非线性系统增强式学习控制[J],中国矿业大学学报,2006.35(5):653-657
[67]Elman J.Finding structure in time[J].Cognitive science,1990,14(1):179-211
[68]Gao X Z,Gao X M,Ovaska S J.A modified neural network model with application to dynamical systems identification[C].Proceedings of the IEEE International Conference on systems,Man,and Cybernetics,Beijing,China,1996,1376-1381
[69]Mistry S I,Nair S S.A CMAC-based reinforcement learning control scheme[J],IEEE Control Systems Magazine,1994,14(2):638-643
[70]Sastry P S,Santharam G,Unnikrishnan K P.Memory neuron networks for identification and control of dynamic systems[J],IEEE Transaction on Neural Networks,1994,5(2):306-319
[71]Wu L,Fisher D G.Output estimation with multirate sampling[J].International Journal of Control,1988,48(1):149-160
[72]Ramachandran P,Gary E Y.Intersample output estimation with multirate sampling[C].Proceedings of the 1996 IEEE International Conference on Control Applications Dearborn,MI,1996,4:118-129
[73]David J.Kruglinski,Scot W,Shepherd G.Inside Visual C++(希望图书创作室译)[M].北京:北京希望电子出版社,1998
[2]侯顺义.提高原燃料质量降低产品成本[J].冶金财会,2004,12:37
[3]于振东,蔡承祜.焦炉生产技术[M].沈阳:辽宁科学技术出版社,2003
[4]张永发,王鹏,谢克昌.中国焦化工业实现洁净可持续发展的思考[J].山西能源与节能,2005,37(2):13-2
[5]姚昭章.炼焦学[M].北京:冶金工业出版社,1995
[6]Obayashi S,Sasaki D.Multiobjective evolutionary computation for supersonic wingshape optimization[J].IEEE Transactions on Evolutionary Computation,2000,4(2):182-187
[7]Sargent R W H.Introduction:25 years of progress in process systems engineering[J].Computers and Chemical Engineering,2004,28(11):437-439
[8]蔡自兴,徐光祐.人工智能及其应用[M].北京:清华大学出版社,2003
[9]Lin B,Recke B,Knudsen J K H,Jorgensen S B.A systematic approach for soft sensor development[J].Computers and Chemical Engineering.2007,31(5):419-425
[10]曾黄麟.智能计算:关于粗集、模糊逻辑、神经网络的理论及其应用[M].重庆:重庆大学出版社,2004
[11]焦李成,刘静,钟伟才.协同进化计算与多智能体系统[M].北京:科学出版社,2006
[12]Niva Y,Watanabe Y,Inaba M.Upgrading of computerized combustion control in coke oven[C].Ironmaking Conference Proceedings,1989,72(5):421-425
[13]王国.节能降耗技术在焦化工艺中的应用[J].本钢技术,2007,4(1):28-30.
[14]Brosilow C B.Inferential control of process control[J].AIChE Journal,1978,24(3):475-484
[15]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(4):137-144
[16]阚晓旭,金晓明.RBF多模型神经网络软测量技术在湿法磷酸生产中的应用[J].化工自动化及仪表,2006,33(1):64-66
[17]陈凯,王秀丽,郑贵堂,等.低成本智能加热控制系统在焦炉上的应用[J].计控系统,2002,5:22-23
[18]张汉卿,梁鸿飞,刑建通.对焦炉边火道温度控制标准的学习与探讨[J]. 河南冶金,1995,16(4):13-15
[19]骆光强,温治,陈鸿复,等.焦炉燃烧室.炭化室传热过程数学模型[J].燃料与化工,1998,29(2):78-82
[20]李芳,骆光强,温治,等.焦炉火道温度数学模型[J].燃料与化工,2000,31(1):9-13
[21]姚昭章.焦炉加热自动控制系统数学模型的评述[J].燃料与化工,1997,28(4):191-196
[22]严文福,郑明东,宁方青,等.模拟火道温度采集方法的研究[J].燃料与化工,2000,31(2):67-69
[23]叶斌,郑明东,严文福.焦炉模拟火道温度采集方法的研究[J].上海金属,2000,22(6):21-24
[24]高军伟,叶阳东,史天运,等.焦炉加热智能控制系统的研究与应用[J].信息与控制,2003,32(1):86-90
[25]Shi T Y,Jia L M,Bai C M.Research and development of integrated intelligent control system of coking stove combustion[C].Proceedings of the 4th World Congress on Intelligent Control and Automation,Shanghai,2002:2347-2352
[26]邹肇村.宝钢三期焦炉加热控制系统[J].冶金自动化,1999,5:16-19
[27]Barbier C.Automatic control of heating by "CRAPO" system in the coke oven plant at Solmer[C].Ironmaking Conference Proceedings,1983,66:261-268
[28]Nakazaki A,Matsuo T,Nakagawa Y.Application and effects of automatic control of coke oven[C].Ironmaking Conference Proceedings,1987,70:299-306
[29]Battel E T,Chen K L.Automatic coke oven heating control system at Burn Harbor Works for normal and repair operation[C].Ironmaking Conference Proceedings,1997,80:499-504
[30]Hollo P V,Verfaille J,Munnix R.希德马焦化厂的加热和过程控制[C].第二届国际焦化会议论文集.北京:冶金工业出版社,1992:294-299
[31]Choi K I.A mathematical model for the estimation of flue temperature in a coke oven[C].Ironmaking Conference Proceedings,1997,80:107-113
[32]Watanabe Y,Inaba M.Upgrading of computerized combustion control in coke oven[C].Ironmaking Conference Proceedings,1989,72:421-425
[33]魏剑侠译.八幡厂5号炉炭化室控制加热系统投产[J].国外炼焦化学,1983,(1):23-28
[34]Thijssen N J W,Vander T.Influences of the measured coke end temperature on coke battery heating[C].Ironmaking Conference Proceedings,1984,67:209-214
[35]Ding F,Chen T W.Modeling and identification of multirate system[J].Acta automatica sinic,2005,31(11):105-122
[36]Kranc G.M.Input-Output analysis of multirate feedback systems[J],IEEE Transactions on Automatic Control,1957,3(6):21-28
[37]Meyer R A,Burrus C S.Design and implementation of multirate digital filters [J].IEEE Transactions on Circuits Systems.1975,22(2):162-168
[38]Miyawaki T,Barnes C W.Multirate recursive digital filters-A general approach and block structures[J].IEEE Transactions on Acoustics Speech,Signal Processing,1983,ASSP-31:1148-1154
[39]Khargonekar P P,Poola K,Tannenbaum A.Robust control of linear time-invariant plants using periodic compensation[J].IEEE Transactions on Automatic Control.1985,AC-30(11):1180-1197
[40]Zhu K Y,Ling K V.Multirate control for a gasification process[C].Proceedings of the American Control Conference,Maryland.1994,3:3268-3272
[41]Embirucu M,Fontes C.Multirate multivariable generalized predictive control and its application to a slurry reactor for ethylene polymerization[J].Chemical Engineering Science,2006,61(2):5754-5756
[42]严文福,郑明东,宁芳青,等.火道温度随结焦时间与换向时间变化规律的研究[J].煤炭学报,2004,29(1):93-96
[43]叶斌,郑明东,严文福.焦炉模拟火道温度采集方法的研究[J].上海金属,2000,11(6):21-24
[44]郑明东,宁方青.焦炉立火道温度控制研究[J].大连理工大学学报,2001,41(7):442-445
[45]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
[46]Fortuna L,Graziani S,Xibilia M G..Soft sensors for product quality monitoring in debutanizer distillation columns[J],Control Engineering Practice,2005,13(4):499-508
[47]刘瑞兰.软测量技术若干问题的研究及工业应用[D],浙江大学博士学位论文,2004
[48]Meyer D G..A parameterization of stabilizing controllers for multirate sampled-data systems[J].IEEE Transactions on Automatic Control,1990,35(2): 233-236
[49]彭安民.非单率系统及其广义预测控制研究[D],江南大学硕士学位论文,2006
[50]杨欣荣.智能仪器原理、设计和发展(第二版)[M].湖南:中南大学出版社,2006
[51]范金城,梅长林.数据分析[M].北京:科学出版社,2002
[52]王旭东,邵惠鹤.基于神经网络的通用软测量技[J].自动化学报,1998,24(5):702-706
[53]Adilson J A,Rubens M F.Soft sensors development for on-line bioreactor state estimation[J].Computers and Chemical Engineering,2000,24(5):1099-1103
[54]孙彦广,高克伟,陶百生.基于智能技术的钢水温度软测量[J].仪器仪表学报.2002,23(3):754-755
[55](美)塞伯著,方开泰等译.线性回归分析[M].北京:科学出版社,1987
[56]曹卫华,侯少云,吴敏.基于集成模型的焦炉火道温度软测量技术研究及应用[J].计算机测量与控制,2006,14(2):149-151
[57]雷琪,吴敏,曹卫华,等.焦炉立火道温度的智能集成软测量方法及其应用[J].华东理工大学学报,2006,7
[58]Yao X,Liu Y.A new evolutionary system for evolving artificial neural networks [J].IEEE Transactions on Neural Networks,1997,8(3):129-138
[59]Rumelhart D,James L,Mcclelland and the PDP Research Group.Parallel distributed processing.Exploration in the Microstructure of Cognition.Vol.1 &2[C].Cambridge,MA:MIT Press,1986
[60]金龙,陈宁.基于人工神经网络的集成预报方法研究和比较[J].气象学报,1999,7(2):198-206
[61]李翔.从复杂到有序—神经网络智能控制理论新进展[M].上海:上海交通大学出版社,2006
[62]Sutton R S.Learning to predict by the methods of temporal differences[J].Machine Learning,1988 3(1):9-44
[63]Anderson,C.W.Learning and problem solving with multilayer connectionist systems[D].Doctoral dissertation,Department of Computer and Information Science,University of Massachusetts,Amherst,1986
[64]Anderson,C.W.Strategy learning with multilayer connectionist representations [C].Proceedings of the Fourth International Workshop on Machine Learning,1987 1:103-114
[65]Gao X Z,Ovaska S J,Vasilakos A V.Temporal difference method-based multi-step prediction of long term deep fading in mobile networks[J].Computer communications.2002,2(5):1477-1486
[66]王雪松,程玉虎,易建强,等,基于Elman网络的非线性系统增强式学习控制[J],中国矿业大学学报,2006.35(5):653-657
[67]Elman J.Finding structure in time[J].Cognitive science,1990,14(1):179-211
[68]Gao X Z,Gao X M,Ovaska S J.A modified neural network model with application to dynamical systems identification[C].Proceedings of the IEEE International Conference on systems,Man,and Cybernetics,Beijing,China,1996,1376-1381
[69]Mistry S I,Nair S S.A CMAC-based reinforcement learning control scheme[J],IEEE Control Systems Magazine,1994,14(2):638-643
[70]Sastry P S,Santharam G,Unnikrishnan K P.Memory neuron networks for identification and control of dynamic systems[J],IEEE Transaction on Neural Networks,1994,5(2):306-319
[71]Wu L,Fisher D G.Output estimation with multirate sampling[J].International Journal of Control,1988,48(1):149-160
[72]Ramachandran P,Gary E Y.Intersample output estimation with multirate sampling[C].Proceedings of the 1996 IEEE International Conference on Control Applications Dearborn,MI,1996,4:118-129
[73]David J.Kruglinski,Scot W,Shepherd G.Inside Visual C++(希望图书创作室译)[M].北京:北京希望电子出版社,1998