氧化铝生产四效逆流降膜式蒸发过程出口浓度预测模型研究
|
摘要
生产实践表明,在氧化铝生产蒸发过程中,料液出口浓度是重要的蒸发质量指标,也是对蒸发操作参数(料液入口流量、生蒸汽流量和压力)进行调整的主要依据。由于料液出口浓度的人工检测滞后数小时以上,难以及时起到反馈修正操作参数的作用;并且由于蒸汽流量等操作参数是人工调节的,为控制出口浓度而进行的操作参数的调整,也是建立在操作人员经验的基础上,系统调整时间长。
为了解决蒸发过程出口浓度预测的问题,需要建立出口浓度变化与各操作参数之间的关系,论文以某氧化铝厂四效逆流降膜式蒸发过程为研究对象,建立蒸发过程出口浓度预测模型。在分析蒸发过程的工艺机理分析的基础上,建立了基于物料平衡、热量平衡和相平衡的机理模型;同时,基于大量实际生产运行数据,建立了以直接影响出口浓度的当前状态参数为输入,出口浓度为输出的BP神经网络预测模型。
两种模型仿真研究表明:BP神经网络模型总体的拟合性好,但在工况不稳定时由于数据的不完备使预测精度降低;机理模型误差相对较大,而在工况不稳定时,比BP神经网络的预测精度高。根据二者的特点,建立了由这两个模型结合的智能集成预测模型。实际生产应用验证了所建立的智能集成模型在工况稳定和不稳定时都能以较高的精度实现氧化铝生产蒸发过程出口浓度的预测,预测精度满足工业生产要求,对蒸发过程的优化操作具有参考价值。
The practices of production indicated that, in the evaporation process of alumina production, the feed outlet concentration is an important indicator; it is also the primary base for regulating the operational parameters (flow of imported feed, the fresh steam flow and pressure). Because the manual measurement of the feed outlet concentration lag behind production process several hours later, it's difficult for us to modify the model by feedback timely. Further, owing to the artificial regulation to steam flow and other operating parameters, the adjustment of operating parameters for the control of outlet concentration is also built on the experience of the operators and the adjustment time of system is too long.
In order to solve the problem of the outlet concentration forecast in the evaporation process and establish the relationship between outlet concentration and the operating parameters, the forecast model of the outlet concentration of the evaporation process is established by studying the four-effect back-feed falling film evaporation system of a certain alumina plant. This paper establishes a mechanism model based on materiel balance, heat balance and phase balance by analyzing the mechanism. Further, based on industrial running data, a BP neural network model for the forecast of the outlet concentration is established, whose inputs are the direct influencing factors of the outlet concentration and the output is the outlet concentration, too.
The characters of the two models are analyzed respectively, and some conclusions can be drawn as follows: the BP neural network model's fitting performance is fine by and large, but it can not predict exactly when the work conditions are unstable because of the shortage of data; the mechanism model's precision is lower than the former generally, but its effect is better than it when the work conditions change abruptly. So an intelligent integrated forecast model is established by combination the two models above. Actual production application indicate that the intelligent integrated model could do estimation well in any condition and could provide reference to the optimization of the industrial operation in the evaporation process of alumina production.
为了解决蒸发过程出口浓度预测的问题,需要建立出口浓度变化与各操作参数之间的关系,论文以某氧化铝厂四效逆流降膜式蒸发过程为研究对象,建立蒸发过程出口浓度预测模型。在分析蒸发过程的工艺机理分析的基础上,建立了基于物料平衡、热量平衡和相平衡的机理模型;同时,基于大量实际生产运行数据,建立了以直接影响出口浓度的当前状态参数为输入,出口浓度为输出的BP神经网络预测模型。
两种模型仿真研究表明:BP神经网络模型总体的拟合性好,但在工况不稳定时由于数据的不完备使预测精度降低;机理模型误差相对较大,而在工况不稳定时,比BP神经网络的预测精度高。根据二者的特点,建立了由这两个模型结合的智能集成预测模型。实际生产应用验证了所建立的智能集成模型在工况稳定和不稳定时都能以较高的精度实现氧化铝生产蒸发过程出口浓度的预测,预测精度满足工业生产要求,对蒸发过程的优化操作具有参考价值。
The practices of production indicated that, in the evaporation process of alumina production, the feed outlet concentration is an important indicator; it is also the primary base for regulating the operational parameters (flow of imported feed, the fresh steam flow and pressure). Because the manual measurement of the feed outlet concentration lag behind production process several hours later, it's difficult for us to modify the model by feedback timely. Further, owing to the artificial regulation to steam flow and other operating parameters, the adjustment of operating parameters for the control of outlet concentration is also built on the experience of the operators and the adjustment time of system is too long.
In order to solve the problem of the outlet concentration forecast in the evaporation process and establish the relationship between outlet concentration and the operating parameters, the forecast model of the outlet concentration of the evaporation process is established by studying the four-effect back-feed falling film evaporation system of a certain alumina plant. This paper establishes a mechanism model based on materiel balance, heat balance and phase balance by analyzing the mechanism. Further, based on industrial running data, a BP neural network model for the forecast of the outlet concentration is established, whose inputs are the direct influencing factors of the outlet concentration and the output is the outlet concentration, too.
The characters of the two models are analyzed respectively, and some conclusions can be drawn as follows: the BP neural network model's fitting performance is fine by and large, but it can not predict exactly when the work conditions are unstable because of the shortage of data; the mechanism model's precision is lower than the former generally, but its effect is better than it when the work conditions change abruptly. So an intelligent integrated forecast model is established by combination the two models above. Actual production application indicate that the intelligent integrated model could do estimation well in any condition and could provide reference to the optimization of the industrial operation in the evaporation process of alumina production.
引文
[1]王亚平.我国铝工业发展新格局及对策建议.经济研究参考,2007,35:34-39
[2]周国宝.略论发展我国氧化铝工业战略取向.世界有色金属,2004,1:25
[3]Chen Qi,Guan Huiqin,xiong Hui.World aluminum industry resourcesexpioration and utilization state of bauxite and alumina.WORLD NONFERROUS METALS,2007,1:27-31
[4]赵清杰,陈建华.中国氧化铝工业发展战略措施探讨.镁铝通讯,2001,3:1-4
[5]杨巧芳,赵清杰.我国氧化铝工业现状及世邻初发展战略探讨.世界有色金属,2001,3:24-26
[6]史金东,刘义伦.我国氧化铝工业可持续发展问题的思考.轻金属,2006,11:3-6
[7]曹异生,唐健.氧化铝工业现状和前景分析.世界有色金属,2003,12:11-14
[8]邢东生,管永诗.我国铝土矿资源及氧化铝工业的现状与分析.采矿技术,2001,6:53-55
[9]陶英君,杨玉华.我国氧化铝发展现状与发展建议.轻金属,1998,7:3-9
[10]陈咸章.当前我国氧化铝生产中的几个问题.有色金属,1999,3:26-27
[11]毕诗文.氧化铝生产工艺.北京:化学工业出版社,2006
[12]杨重愚.氧化铝生产工艺学.北京:冶金工业出版社,1992
[13]王勇.复杂多效蒸发过程模拟与操作优化研究:[博士学位论文].福州:福州大学,2006
[14]李珊.多效蒸发系统热力学优化研究.西安交通大学报,1994,28(8):30-36
[15]梁虎,王黎,朱平.多效蒸发系统优化设计研究.化学工程,1997,26(6):48-51
[16]周大军.多效蒸发系统热泵流程的设计与优化.氯碱工业,1998,(7):24-28
[17]阮奇,黄诗煌,叶长燊,陈文波.多效蒸发系统优化设计目标函数的建立与求解.计算机与应用化学,2001,18(1):69-75
[18]王培进,周作伸.多效蒸发系统的数学描述及优化目标函数分析.化学工程,1997,25(2):33-39.
[19]王培进,周作伸.提高多效蒸发系统投资价值的优化设计.价值工程,1997,(1):19-21.
[20]蔡恩照,林匡行,杨东华.混流多效蒸发系统的过程模拟.华东理工大学学 报,1995,21(2):177-180.
[21]T.Hisham,El-Dessouky.a al.Performance of parallel feed multiple evaporation system for seawater desalination.Applied Thermal Engineering,2000(20):1679-1706
[22]A.H.Osman,A.K.Mohammad,Al-Sofi,Monazir Imam,M.Ghulam,Mustafa,Khalid Bamardouf,Hamad Al-Washmi,Simulation of multistage flash desalination process.Desalinlation,2001,(134):195-203
[23]A.Jernqvista,M.Jernqvista,G.Alyb.Simulation of thermal desalination processes.Desalination,2001,134:187-193
[24]A.zdravkovic,N.Marsenic.Multiple Effect Evaporation Station Simulation and Control.1992,IASETD Conf.ROC&RA:98-102
[25]A.Zdravkovic,S.Turajlic,N.Marsenic.Fuzzy PI Control Algorithm for the Multiple Effect Evaporation Station.IEEE,1994:677-682
[26]S.Lissane Elhaq,F.Giri,H.Unbehauen.Modelling identification and control of sugar evaporation theoretical design and experimental evaluation.Control Engineering Practice,1999,7:931-942
[27]Krzysztof Patan,Thomas Parisini.Identification of neural dynamic models for fault detection and isolation:the case of a real sugar evaporation process.Journal of Process Control,2005,15(1):67-79
[28]田海蓉,陈国礼,吴俊生,张素贞.五效蒸发装置模型与仿真.华东理工大学学报,2000,26(5):568-572
[29]田海蓉,张素贞.软测量技术在5效蒸发装置中的应用.北华大学学报,2000,1(4):365-368
[30]李泽国,张素贞.五效蒸发装置软测量模型的建立.吉林化工学院学报,2000,17(2):58-61
[31]翟光群,张玉凤.烧碱浓度Fuzzy检测中隶属函数的确定.郑州工业大学学报,2001,22(4):56-59
[32]潘丰,林金星.基于神经网络的柠檬酸蒸发过程软测量研究.测控技术,2004,23(8):17-25
[33]A.Jernqvista,M.Jernqvista,G.Alyb.Simulation of thermal desalination processes.Desalination,2001,134:187-193
[34]Bacha,H.Ben,M.Bouzguenda,M.S.Abid,A.y.Maalej.Modelling and simulation of a water desalination station with solar multiple condensation evaporation cycle technique.Renewable Energy Volume,1999,18(3):349-365
[35]Yousef,A.Al-Wazzan,Faisal A1-Modafb.Seawater desalination in Kuwait using multistage flash evaporation technology historical overview.Desalination,2001134:257-267
[36]Yuan Zhou,S.J.Richard.Evaluating the costs of desalination and water transport.Desalination,2004,164:225-240
[37]Hisham M Ettouney,Hisham T El-Dessouky,Kuwait Univ.Evaluating the Economics of Desalination.Heat Transfer,2002,12:32-39
[38]G.N.Tiwari,Sanjeev&mar,Om Prakash.Study of heat and masstransfer from sugarcanejuice for evaporation.Desalination,2003,159:81-96
[39]H.Heluane,M.Colombo,A.Ingaramo,M.R.Hernandez and M.Cesca.Multipleeffect evaporation in a sugar factory a measured variables study.Latin American Applied Research,2001,31:519-524
[40]S.Lissane Elhaq,F.Giri,H.Unbehauen.Modelling identification and control of sugar evaporation-theoretical design and experimental evaluation.Control Engineering Practice,1999,7:931-942
[41]Z.I.Stefanov,K.A.Hoo.Distributed Parameter Model of Black Liquor Falling-Film Evaporators.American Chemical Society,2004,43:8117-8132
[42]Jessica Algehed,Thore Berntsson.Evaporation of black liquor and wastewater using medium-pressure steam:Simulation and economic evaluation of novel designs.Applied Thermal Engineering,2003,23:481-495
[43]柴诚敬.化工原理(上册).北京:高等教育出版社,2002,344-374
[44]H.N叶列明著,王延明译.氧化铝生产过程与设备.北京:冶金工业出版社,1987,3:340-369
[45]孙佩权.冶金化工过程及设备.北京:冶金工业出版社,1987:321-327
[46]徐文熙,穆文俊.化工原理(上).北京:中国石化出版社,1992
[47]于静江,周春晖.过程控制中的软测量技术.控制理论与应用,1996,13(2):137-144
[48]俞金寿,刘爱伦等编著.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
[49]李海清,黄志尧等.软测量技术原理及应用.北京:化学工业出版社,2000
[50]胡守仁.神经网络导论.长沙:国防科技大学出版社,1993:27-32
[51]胡守仁.神经网络实现技术.长沙:国防科技大学出版社,1993:15-18
[52]王旭东,邵惠鹤.神经元网络建模与软测量技术.化工自动化与仪表,1996,2:28-31
[53]E.S.chng.Gradient Radial Basis Function Networks for Nonlinear and Nonstationary Time Series Prediction.IEEE Transaction on.Neural Networks,1996,7(1):190-194
[54]吴佑寿,赵明生,丁晓青.一种激励函数可调的新神经网络及应用.中国科学(E辑),1997,27(1):55-60
[55]A.W.Bruce.Cooperative-Competitive Genetic Evolution of Radial Basis Function Centers and Widths for Time Series Prediction.IEEE Transactions on Neural Networks,1996,7(4):869-880
[56]张昊,吴捷,郁滨.应用模糊神经网络进行负荷预测的研究.自动化学报,1995,25(1):60-67
[57]李人厚,张平安.关于模糊辨识理论与应用实际问题.控制理论与应用,1995,12(2):129-137
[58]T.Takagi,M.Sugeno.A robust stabilization problem of fuzzy control systems and its application to baking up control of track-trailer.IEEE Trans.On Fuzzy Sets,1994,2(2):119-133
[59]李少远等.Sugeno模糊模型的辨识与控制.自动化学报,1999,24(4):488-492
[60]程惠涛,黄文虎,姜兴渭.基于灰色模型的故障预报技术及其在空间推进系统上的应用.推进技术,1998,3:74-77
[61]王雅琳.智能集成建模理论及其在有色过程优化控制中的应用研究:[博士学位论文].长沙:中南大学,2001
[62]颜青君.铜闪速熔炼操作参数优化的研究与应用:[硕士学位论文].长沙:中南大学,2007
[63]曾丹芩等.工程热力学.北京:人民教育出版社,1980
[64]史贤林,潘鹤林.NaCl饱和的烧碱溶液的物性和汽、液平衡关系式.氯碱工业,1996,(3):21-25
[65]董元彦.无机及分析化学.北京:高等教育出版社,2002
[66]徐文熙,穆文俊.化工原理(上).中国石化出版社,1992
[67]李正东.管式降膜蒸发技术在氧化铝生产中的应用:[硕士学位论文].长沙:中南大学,2005
[68]梁春来.溶出自蒸发和种分母液的Na_2CO_3、Na_2SO_4平衡溶解度试验研究,世界有色金属,1999(6):25-28
[69]李华昌,符斌.实用化学手册.北京:化学工业出版社,2006
[70]林成森.数值计算方法.北京:科学技术出版社,1992
[71]胡亮,杨大锦.Excel与化学化工试验数据处理.北京:化学工业出版社, 2005:159-162
[72]司捷,周贵安.基于梯度监督学习的理论与应用(Ⅰ)-基本算法.清华大学学报(自然科学版),1997,37(7):71-73
[73]赵弘,周瑞祥,林廷圻.基于Levenberg-Marquardt算法的神经网络监督控制,西安交通大学学报,2002,36(5):523-527
[74]李勇刚.基于智能集成模型的苛性比值与熔出率软测量及其应用研究:[博士学位论文].长沙:中南大学,2004
[75]陈晓方,桂卫华,王雅琳等.基于智能集成策略的烧结块残硫软测量模型.控制理论与应用,2004,21(1):75-80
[2]周国宝.略论发展我国氧化铝工业战略取向.世界有色金属,2004,1:25
[3]Chen Qi,Guan Huiqin,xiong Hui.World aluminum industry resourcesexpioration and utilization state of bauxite and alumina.WORLD NONFERROUS METALS,2007,1:27-31
[4]赵清杰,陈建华.中国氧化铝工业发展战略措施探讨.镁铝通讯,2001,3:1-4
[5]杨巧芳,赵清杰.我国氧化铝工业现状及世邻初发展战略探讨.世界有色金属,2001,3:24-26
[6]史金东,刘义伦.我国氧化铝工业可持续发展问题的思考.轻金属,2006,11:3-6
[7]曹异生,唐健.氧化铝工业现状和前景分析.世界有色金属,2003,12:11-14
[8]邢东生,管永诗.我国铝土矿资源及氧化铝工业的现状与分析.采矿技术,2001,6:53-55
[9]陶英君,杨玉华.我国氧化铝发展现状与发展建议.轻金属,1998,7:3-9
[10]陈咸章.当前我国氧化铝生产中的几个问题.有色金属,1999,3:26-27
[11]毕诗文.氧化铝生产工艺.北京:化学工业出版社,2006
[12]杨重愚.氧化铝生产工艺学.北京:冶金工业出版社,1992
[13]王勇.复杂多效蒸发过程模拟与操作优化研究:[博士学位论文].福州:福州大学,2006
[14]李珊.多效蒸发系统热力学优化研究.西安交通大学报,1994,28(8):30-36
[15]梁虎,王黎,朱平.多效蒸发系统优化设计研究.化学工程,1997,26(6):48-51
[16]周大军.多效蒸发系统热泵流程的设计与优化.氯碱工业,1998,(7):24-28
[17]阮奇,黄诗煌,叶长燊,陈文波.多效蒸发系统优化设计目标函数的建立与求解.计算机与应用化学,2001,18(1):69-75
[18]王培进,周作伸.多效蒸发系统的数学描述及优化目标函数分析.化学工程,1997,25(2):33-39.
[19]王培进,周作伸.提高多效蒸发系统投资价值的优化设计.价值工程,1997,(1):19-21.
[20]蔡恩照,林匡行,杨东华.混流多效蒸发系统的过程模拟.华东理工大学学 报,1995,21(2):177-180.
[21]T.Hisham,El-Dessouky.a al.Performance of parallel feed multiple evaporation system for seawater desalination.Applied Thermal Engineering,2000(20):1679-1706
[22]A.H.Osman,A.K.Mohammad,Al-Sofi,Monazir Imam,M.Ghulam,Mustafa,Khalid Bamardouf,Hamad Al-Washmi,Simulation of multistage flash desalination process.Desalinlation,2001,(134):195-203
[23]A.Jernqvista,M.Jernqvista,G.Alyb.Simulation of thermal desalination processes.Desalination,2001,134:187-193
[24]A.zdravkovic,N.Marsenic.Multiple Effect Evaporation Station Simulation and Control.1992,IASETD Conf.ROC&RA:98-102
[25]A.Zdravkovic,S.Turajlic,N.Marsenic.Fuzzy PI Control Algorithm for the Multiple Effect Evaporation Station.IEEE,1994:677-682
[26]S.Lissane Elhaq,F.Giri,H.Unbehauen.Modelling identification and control of sugar evaporation theoretical design and experimental evaluation.Control Engineering Practice,1999,7:931-942
[27]Krzysztof Patan,Thomas Parisini.Identification of neural dynamic models for fault detection and isolation:the case of a real sugar evaporation process.Journal of Process Control,2005,15(1):67-79
[28]田海蓉,陈国礼,吴俊生,张素贞.五效蒸发装置模型与仿真.华东理工大学学报,2000,26(5):568-572
[29]田海蓉,张素贞.软测量技术在5效蒸发装置中的应用.北华大学学报,2000,1(4):365-368
[30]李泽国,张素贞.五效蒸发装置软测量模型的建立.吉林化工学院学报,2000,17(2):58-61
[31]翟光群,张玉凤.烧碱浓度Fuzzy检测中隶属函数的确定.郑州工业大学学报,2001,22(4):56-59
[32]潘丰,林金星.基于神经网络的柠檬酸蒸发过程软测量研究.测控技术,2004,23(8):17-25
[33]A.Jernqvista,M.Jernqvista,G.Alyb.Simulation of thermal desalination processes.Desalination,2001,134:187-193
[34]Bacha,H.Ben,M.Bouzguenda,M.S.Abid,A.y.Maalej.Modelling and simulation of a water desalination station with solar multiple condensation evaporation cycle technique.Renewable Energy Volume,1999,18(3):349-365
[35]Yousef,A.Al-Wazzan,Faisal A1-Modafb.Seawater desalination in Kuwait using multistage flash evaporation technology historical overview.Desalination,2001134:257-267
[36]Yuan Zhou,S.J.Richard.Evaluating the costs of desalination and water transport.Desalination,2004,164:225-240
[37]Hisham M Ettouney,Hisham T El-Dessouky,Kuwait Univ.Evaluating the Economics of Desalination.Heat Transfer,2002,12:32-39
[38]G.N.Tiwari,Sanjeev&mar,Om Prakash.Study of heat and masstransfer from sugarcanejuice for evaporation.Desalination,2003,159:81-96
[39]H.Heluane,M.Colombo,A.Ingaramo,M.R.Hernandez and M.Cesca.Multipleeffect evaporation in a sugar factory a measured variables study.Latin American Applied Research,2001,31:519-524
[40]S.Lissane Elhaq,F.Giri,H.Unbehauen.Modelling identification and control of sugar evaporation-theoretical design and experimental evaluation.Control Engineering Practice,1999,7:931-942
[41]Z.I.Stefanov,K.A.Hoo.Distributed Parameter Model of Black Liquor Falling-Film Evaporators.American Chemical Society,2004,43:8117-8132
[42]Jessica Algehed,Thore Berntsson.Evaporation of black liquor and wastewater using medium-pressure steam:Simulation and economic evaluation of novel designs.Applied Thermal Engineering,2003,23:481-495
[43]柴诚敬.化工原理(上册).北京:高等教育出版社,2002,344-374
[44]H.N叶列明著,王延明译.氧化铝生产过程与设备.北京:冶金工业出版社,1987,3:340-369
[45]孙佩权.冶金化工过程及设备.北京:冶金工业出版社,1987:321-327
[46]徐文熙,穆文俊.化工原理(上).北京:中国石化出版社,1992
[47]于静江,周春晖.过程控制中的软测量技术.控制理论与应用,1996,13(2):137-144
[48]俞金寿,刘爱伦等编著.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
[49]李海清,黄志尧等.软测量技术原理及应用.北京:化学工业出版社,2000
[50]胡守仁.神经网络导论.长沙:国防科技大学出版社,1993:27-32
[51]胡守仁.神经网络实现技术.长沙:国防科技大学出版社,1993:15-18
[52]王旭东,邵惠鹤.神经元网络建模与软测量技术.化工自动化与仪表,1996,2:28-31
[53]E.S.chng.Gradient Radial Basis Function Networks for Nonlinear and Nonstationary Time Series Prediction.IEEE Transaction on.Neural Networks,1996,7(1):190-194
[54]吴佑寿,赵明生,丁晓青.一种激励函数可调的新神经网络及应用.中国科学(E辑),1997,27(1):55-60
[55]A.W.Bruce.Cooperative-Competitive Genetic Evolution of Radial Basis Function Centers and Widths for Time Series Prediction.IEEE Transactions on Neural Networks,1996,7(4):869-880
[56]张昊,吴捷,郁滨.应用模糊神经网络进行负荷预测的研究.自动化学报,1995,25(1):60-67
[57]李人厚,张平安.关于模糊辨识理论与应用实际问题.控制理论与应用,1995,12(2):129-137
[58]T.Takagi,M.Sugeno.A robust stabilization problem of fuzzy control systems and its application to baking up control of track-trailer.IEEE Trans.On Fuzzy Sets,1994,2(2):119-133
[59]李少远等.Sugeno模糊模型的辨识与控制.自动化学报,1999,24(4):488-492
[60]程惠涛,黄文虎,姜兴渭.基于灰色模型的故障预报技术及其在空间推进系统上的应用.推进技术,1998,3:74-77
[61]王雅琳.智能集成建模理论及其在有色过程优化控制中的应用研究:[博士学位论文].长沙:中南大学,2001
[62]颜青君.铜闪速熔炼操作参数优化的研究与应用:[硕士学位论文].长沙:中南大学,2007
[63]曾丹芩等.工程热力学.北京:人民教育出版社,1980
[64]史贤林,潘鹤林.NaCl饱和的烧碱溶液的物性和汽、液平衡关系式.氯碱工业,1996,(3):21-25
[65]董元彦.无机及分析化学.北京:高等教育出版社,2002
[66]徐文熙,穆文俊.化工原理(上).中国石化出版社,1992
[67]李正东.管式降膜蒸发技术在氧化铝生产中的应用:[硕士学位论文].长沙:中南大学,2005
[68]梁春来.溶出自蒸发和种分母液的Na_2CO_3、Na_2SO_4平衡溶解度试验研究,世界有色金属,1999(6):25-28
[69]李华昌,符斌.实用化学手册.北京:化学工业出版社,2006
[70]林成森.数值计算方法.北京:科学技术出版社,1992
[71]胡亮,杨大锦.Excel与化学化工试验数据处理.北京:化学工业出版社, 2005:159-162
[72]司捷,周贵安.基于梯度监督学习的理论与应用(Ⅰ)-基本算法.清华大学学报(自然科学版),1997,37(7):71-73
[73]赵弘,周瑞祥,林廷圻.基于Levenberg-Marquardt算法的神经网络监督控制,西安交通大学学报,2002,36(5):523-527
[74]李勇刚.基于智能集成模型的苛性比值与熔出率软测量及其应用研究:[博士学位论文].长沙:中南大学,2004
[75]陈晓方,桂卫华,王雅琳等.基于智能集成策略的烧结块残硫软测量模型.控制理论与应用,2004,21(1):75-80