MCM-22分子筛催化剂性能的BP神经网络预测模型研究
|
摘要
以MCM-22分子筛为对象,系统考察了挤条成型工艺条件对分子筛催化剂物理化学特性的影响,并以苯与丙烯液相烷基化合成异丙苯为模型反应,在实验研究基础上、结合人工神经网络建模方法,建立了MCM-22分子筛催化剂性能预测的BP(Back Propagation)神经网络模型,该模型关联了催化剂本征性能、工艺条件和反应产物分布之间的相互关系,以其达到较好地预测苯与丙烯烷基化反应性能的功能,为催化剂的开发和工业生产提供应用基础和参考。
利用颗粒强度测定、NH_3-TPD酸性表征和氮吸附脱附—压汞方法联合测试等手段对不同条件下成型的MCM-22分子筛物理化学特性进行了表征,系统考察了不同成型工艺条件对催化剂颗粒强度、孔结构和酸性等性质的影响。结果表明:成型过程中适宜助剂的加入,可以调节催化剂颗粒强度、比表面积和孔径分布以及酸性。其中,粘结剂SB粉主要调节催化剂颗粒强度和酸性,扩孔剂PEG20000主要调变孔径分布以及孔容。
对不同成型条件下得到的16种织构性能各异的MCM-22分子筛催化剂性能进行实验评价,将所获得的数据用于模型训练和预测结果检验。结果表明,所建立的BP神经网络模型具有进行实验数据拟合和在一定范围内预测未知结果的能力,预测平均相对误差为4.21%。因此,将该BP神经网络模型作为MCM-22分子筛催化剂的性能预测和苯与丙烯液相烷基化过程的定量描述模型,是适宜和可靠的。同时,应用该模型回归分析了温度、空速、苯烯比及分子筛的比表面积、平均孔径与产物选择性之间的相关关系。分析结果表明:丙烯空速、苯烯比、温度及分子筛的比表面积、平均孔径与异丙苯的选择性呈正相关关系,与二异丙苯和三异丙苯的选择性呈负相关关系。
The effect of extrusion molding condition on the physical and chemical properties of MCM-22 zeolite had been systematically investigated.And taking the liquid alkylation of benzene with propylene to produce cumene as model reaction,combined with the artificial neural networks(ANN) modeling method,Back-Propagation neural networks model was developed for the performance prediction of MCM-22 zeolite catalyst.The intrinsic performance of MCM-22 zeolite,the operation condition,and the product distribution were considered into this model,in order to predict the catalytic preformance of benzene alkylation with propylene and provide an applied reference for the catalyst development and industrial production.
The MCM-22 zeolites prepared under different molding condition were characterized using particle strength apparatus,NH_3-TPD acidity characterization,N_2 adsorption-desorption instrument and mercury penetration instrument to investigate the effects of molding conditions on mechanical strength,pore structure,acidity and other physical-chemical properties of MCM-22 zeolite catalyst using single factor experiment method.The results showed that in the molding process,suitable amount auxiliary materials could adjust the properties of catalyst.SB powder mainly adjusted the partical strength and acidity,PEG20000 regulated pore distribution and pore volume.
By means of the extrusion molding method,the catalytic performances of 16 kinds of MCM-22 zeolite catalysts with different textile properties were also experimentally investigated.According to these experimental data,the ANN model developed here was trained and tested.The results showed that the ANN model developed here had a very well simulation capability and the prediction results met with the experimental data,its average relative prediction error was only about 4.21%.Therefore,the ANN model established here was suitable and reliable when it was used to predict the catalytic performance of MCM-22 zeolite and simulate the alkylation result of benzene with propylene over MCM-22 zeolite.At the same time,the relation between some operating parameters and products selectivities had been regression analyzed,such as tempreture,space velocity,Benzene/Propene ratio,specific surface and average pore radius of MCM-22 zeolite etc.The result showed that space velocity,Benzene/Propene ratio,specific surface,average pore radius and tempreture were positive correlation with IPB and negative correlation with DIPB,TIPB.
利用颗粒强度测定、NH_3-TPD酸性表征和氮吸附脱附—压汞方法联合测试等手段对不同条件下成型的MCM-22分子筛物理化学特性进行了表征,系统考察了不同成型工艺条件对催化剂颗粒强度、孔结构和酸性等性质的影响。结果表明:成型过程中适宜助剂的加入,可以调节催化剂颗粒强度、比表面积和孔径分布以及酸性。其中,粘结剂SB粉主要调节催化剂颗粒强度和酸性,扩孔剂PEG20000主要调变孔径分布以及孔容。
对不同成型条件下得到的16种织构性能各异的MCM-22分子筛催化剂性能进行实验评价,将所获得的数据用于模型训练和预测结果检验。结果表明,所建立的BP神经网络模型具有进行实验数据拟合和在一定范围内预测未知结果的能力,预测平均相对误差为4.21%。因此,将该BP神经网络模型作为MCM-22分子筛催化剂的性能预测和苯与丙烯液相烷基化过程的定量描述模型,是适宜和可靠的。同时,应用该模型回归分析了温度、空速、苯烯比及分子筛的比表面积、平均孔径与产物选择性之间的相关关系。分析结果表明:丙烯空速、苯烯比、温度及分子筛的比表面积、平均孔径与异丙苯的选择性呈正相关关系,与二异丙苯和三异丙苯的选择性呈负相关关系。
The effect of extrusion molding condition on the physical and chemical properties of MCM-22 zeolite had been systematically investigated.And taking the liquid alkylation of benzene with propylene to produce cumene as model reaction,combined with the artificial neural networks(ANN) modeling method,Back-Propagation neural networks model was developed for the performance prediction of MCM-22 zeolite catalyst.The intrinsic performance of MCM-22 zeolite,the operation condition,and the product distribution were considered into this model,in order to predict the catalytic preformance of benzene alkylation with propylene and provide an applied reference for the catalyst development and industrial production.
The MCM-22 zeolites prepared under different molding condition were characterized using particle strength apparatus,NH_3-TPD acidity characterization,N_2 adsorption-desorption instrument and mercury penetration instrument to investigate the effects of molding conditions on mechanical strength,pore structure,acidity and other physical-chemical properties of MCM-22 zeolite catalyst using single factor experiment method.The results showed that in the molding process,suitable amount auxiliary materials could adjust the properties of catalyst.SB powder mainly adjusted the partical strength and acidity,PEG20000 regulated pore distribution and pore volume.
By means of the extrusion molding method,the catalytic performances of 16 kinds of MCM-22 zeolite catalysts with different textile properties were also experimentally investigated.According to these experimental data,the ANN model developed here was trained and tested.The results showed that the ANN model developed here had a very well simulation capability and the prediction results met with the experimental data,its average relative prediction error was only about 4.21%.Therefore,the ANN model established here was suitable and reliable when it was used to predict the catalytic performance of MCM-22 zeolite and simulate the alkylation result of benzene with propylene over MCM-22 zeolite.At the same time,the relation between some operating parameters and products selectivities had been regression analyzed,such as tempreture,space velocity,Benzene/Propene ratio,specific surface and average pore radius of MCM-22 zeolite etc.The result showed that space velocity,Benzene/Propene ratio,specific surface,average pore radius and tempreture were positive correlation with IPB and negative correlation with DIPB,TIPB.
引文
[1]张佩君.合成异丙苯生产现状及技术进展[J].石化技术,2005,12(2):62-65.
[2]Perego C,Lngallina P.Recent advances in the industrial alkylation of aromatics:new catalysts and new processes[J].Catal.Today,2002,73:3-22
[3]Sridevi U,Bokade V V,Satyanarayana C V V,Rao B S,Pradhan N C,Pao B K B.Kinetics of propylation of benzene over H-beta and SAPO-5 catalysts:a comparison[J].J.Mol.Catal.A:Chemical,2002,181:257-262
[4]Tanabe K,Misono M,Ono Y,et al.New solid acid and bases[M].Kodansha and Elsevier Co,1989.227
[5]Meima G R,Van Der Aals M J,et al.Recent development in the production of cumene with zeolite catalysts[J].Erdol Endgas Kohle,1996,112(7/8):315-319
[6]Degnan Jr T F,Smith C M,Venkat C R.Alkylation of aromatics with ethylene and propylene:recent developments in commercial processes[J].Appl Catal A:General,2001,221:283-294
[7]高辉,史建公,曹钢.异丙苯合成工艺进展[J].化学工业与工程技术.2003,24(6):36-38
[8]史建公,卢冠忠,曹钢.异丙苯生产技术进展[J].中国石油化工科技信息指南(上卷)[M].北京:中国石化出版社,2001.32-34
[9]魏文德.有机化工原料大全(下卷)[M].北京:化学工业出版社,1999.113-1381
[10]M.K.Rubin;P.Chu;Composition of synthetic porous crystalline material,its synthesis and use[P],United States Patent 4 954 325 September 4,1990
[11]Lawton S.L.,Leonowicz M.E.,Partridge R.D,et al.Twelve-ring pockets on the external surface of MCM-22 crystals[J],Microporous and Mesoporous Materials,1998,23,109-117
[12]Leonowicz M.E.,Lawton J.A.,Lawton S.L.,et al.MCM-22:A Molecular Sieve with Two Independent Multidimensional Channel Systems[J].Science,1994,264,1910-1913
[13]A.Corma,C.Corell,and P.J.Perez,Synthesis and Characterization of the MCM-22Zeolite[J].zeolites,1995,15,2-8
[14]袁忠勇,张怀彬,王敬中,李赫喧.沸石分子筛MCM-22的合成与表征[J].石油学报,1998,14(2):28-31
[15]Corma A.,Corell C.,Fornes V.,et al.Infrared spectroscopy,thermoprogrammed desorption,and nuclear magnetic resonance study of the acidity,structure,and stability of zeolite MCM-22[J].zeolites,1995,15,576-582
[16]Miguel A.Camblor,Avelino Corma,et al.Synthesis and Structural Characterization of MWW Type Zeolite ITQ-1,the Pure Silica Analog of MCM-22 and SSZ-25[J].Laboratory of Crystallography,ETH,CH-8092 Zurich,Switzerland J.Phys.Chem.B,1998,102(1),pp 44-51
[17]Corma A.From microporous to mesoporous molecular sieve materials and their use in catalysis[J].Chemical Reviews,1997,97(6):2373-2419
[18]徐文炀,窦涛,刘世欧.非水体系中丝光沸石的合成方法[P].CN,88100228.1988.
[19]Inagaki S,Hoshino M,Kikuchi E.Synthesis of MCM-22 zeolite by the vapor-phase transport method[J].Studies in Surface Science and Catalysis,2002,142(1):53-60
[20]Bellussi G,Pazzuconi G,Perego C,et al.Liquid-Phase Alkylation of Benzene with Light Olefms Catalyzed by β-Zeolites[J].J.Catal.,1995,157(1):227-234
[21]Geatti A,Lenarda M,Storaro L,et al.Perissinotto M.Solid acid catalysts from clays:Cumene synthesis by benzene alkylation with propene catalyzed by cation exchanged aluminum pillared clays[J].J.Mol.Catal.A,1997,121(1):111-118
[22]林衍华,方永成,顾星,谢在库.沸石液相烃化合成异丙苯中烷基转移技术进展[J].工业催化,1999,3:10-17
[23]Anand B H,Jagannath D.Novel catalytic aspects of beta zeolite for alkylaromatics transformation[J].Applied Catalysis A:General,1999,181(2):347-354
[24]杨平,潘履让,李赫喧.B分子筛的酸性和苯-丙烯烷基化反应的研究[J].燃料化学学报,1990,18(1):16-22
[25]何长青,刘中民,张盈珍.大孔沸石催化剂上苯与丙烯液相烷基化反应行为的研究[J].燃料化学学报,1999,27(3):203-208
[26]傅吉全,杨立英,张吉瑞.压力空速对FX-01催化剂上苯与丙烯烃化反应的影响[J].石油化工,1998,27(1):13-18
[27]Erich Harth.From brains to neural nets to brains[J].Neural networks,1997,7(10):1241-1255
[28]McCulloch W S,Pitts W A.A logical calculus of ideas immanent in nervous activity[J].Bulletin of Mathematical Biophysics,1943(5):115-133
[29]Hebb D O.The organization of behavior[M].New York:Wiley,1949
[30]Rosenblatt F.The Perceptron:A Probabilistic Model for Information Storage and Organization in the Brain.Psychological Review[J],1958(65):386-458
[31]Widrow B and Hoff M E.Adaptive switching circuits[M].New York:IRE,1960
[32]Minsky M,Papert S.Perceptrons[M],MIT Press,1969
[33]Hopfield J J.Neural networks and physical systems with emergent collective computational abilities[J].Proceedings of the National Academy of Science,1982,79:2554-2558
[34]Rumelhart D E,Hinton G E,Williams R J.Learning representations by back-propagation errors[J].Nature,1986(323):533-536
[35]Raj Sharma,Diwakar Singhal,Ranjana Ghosh.Potential applications of artificial neural networks to thermodynamics:vapor-liquid equilibrium predictions[J].Computers and Chemical Engineering,1999,23:385-390
[36]胡德栋,王威强,魏东,郭建章.固体在超临界流体中溶解度的BP人工神经网络模拟[J].山东大学学报(工学版),2006,36(2):8-11
[37]Macmurray J C,Himmelblau D M.Modeling and control of a packed distillation column using artificial neural networks[J].Computers Chem.Engng,1995,10(19):1077-1088
[38]Sebastian Engell,Gregor Fernholz.Control of a reactive separation process[J].Chemical Engineering and Processing,2003,42:201-210
[39]Tatlier M.,Cigizoglu H K,Ayse E S.Artificial neural network methods for the estimation of zeolite molar compositions that form from different reaction mixtures[J].Comput.Chem.Eng.2005,30,137-139
[40]Istadia I,Amin N A S.Modelling and optimization of catalytic-dielectric barrier discharge plasma reactor for methane and carbon dioxide conversion using hybrid artificial neural network-genetic algorithm technique[J].Chem.Eng.Sci.2007,62, 6568-6581
[41]Filho A C,Filho R M.Concurrent engineering reactor design[J].Comput.Aided Chem.Eng.,2005,20,559-582
[42]Tatlier M.,Cigizoglu H K,Ayse E S.Artificial neural network methods for the estimation of zeolite molar compositions that form from different reaction mixtures[J].Comput.Chem.Eng.2005,30,137-139
[43]Istadia I,Amin N A S.Modelling and optimization of catalytic-dielectric barrier discharge plasma reactor for methane and carbon dioxide conversion using hybrid artificial neural network-genetic algorithm technique[J].Chem.Eng.Sci.2007,62,6568-6581
[44]Filho A C,Filho R M.Concurrent engineering reactor design[J].Comput.Aided Chem.Eng.,2005,20,559-582
[45]魏海坤.神经网络结构设计的理论与方法[M].第一版.北京:国防工业出版社,2005
[46]Polycarpou M,Ioannou P.Learning and convergence analysis of neural-type structured networks[J],IEEE Trans.Neural Networks,1992(3):39-50
[47]卢焕章.石油化工基础数据手册[M].北京:化学工业出版社,1984:205
[48]朱洪法.催化剂成型[M].北京:中国石化出版社,1992:39-55
[49]魏秀萍,李军,崔凤霞,曾广俊,张立群.影响沸石分子筛催化剂强度因素的探讨[J].精细石油化工.2002.7(4):36-38
[50]马军.粉状沸石的成型及应用[J].甘肃科技.2002,1:16
[51]赵野,骆傲阳,于开荣,韩志波,陈广文.影响分子筛催化剂强度因素的探讨[J].石油炼制与化工.1995,3(3):28
[52]Jiratova K,Janacek L.Effect of peptizing on the physical and chemical properties of extruded alumina[J].International Chemical Engineering,1983,23(1):167-174
[53]Pradhan A R,Rao B S.Transalkylation of di-isopropylbenzenes over large pore zeolites[J].Appl Catal A:Gen,1993,106:143-157
[54]Suman K.Jana,Reiichi Nishida,Kazuya Shindo.Pore size control of mesoporous molecular sieves using different organic auxiliary chemicals[J].Microporous and Mesoporous Materials,2004,68:133-142
[55]史建文,李大东,薛用芳,挤出成型过程中的各种因素对氧化铝载体物性的影响[J].石油化工,1985,14(6):323-328
[56]余少兵,李永红,陈洪钫.改性对β分子筛酸性的影响[J].化工学报,2004,55(6):913-918
[57]Torrecilla J S,Otero L,Sanz P D.A Neural Network Approach for Thermal/pressure Food Processing[J].J.Food Eng,2004,62:89-95.
[58]Erich Harth.From brains to neural nets to brains[J].Neural networks,1997,7(10):1241-1255.
[59]管国锋,万辉,畅伟贤.基于神经网络的磷酸三丁醋络合萃取丁酸的研究[J].计算机与应用化学,2004,21(6):823-827.
[60]郭海军,胡星琪,段明.基于神经网络的双指标正交试验设计与分析[J].计算机与应用化学,2004,21(3):481-484.
[61]Raj Sharme,Dtwakar Singhal and Ranjana.Ghosh.Potential application of artificial neural networks to thermodynamics:vapor-liquid equilibrium predictions.Computers and Chemical Engineering.1999,23:385-390.
[62]Thomas E Q,Liu Y A.人工智能在化学工程中的应用[M].北京:中国石化出版社,1994.448-499
[63]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2000,10-26
[64]Torrecilla J S,Otero L,Sanz P D.A Neural Network Approach for Thermal/pressure Food Processing[J].J.Food Eng.2004,62,89-95
[65]Bas D,Boyacl I H.Modeling and optimization Ⅱ:Comparison of estimation capabilities of response surface methodology with artificial neural networks in a biochemical reaction[J].J.Food Eng.2007,78,846-854
[66]Bas D,Dudak F C,Boyacl I H.Modeling and optimization Ⅲ:Reaction rate estimation using artificial neural network(ANN) without a kinetic model[J].J.Food Eng.2007,79,622-628
[67]Filho A C,Filho R M.Concurrent engineering reator design[J].Comput.Aided Chem.Eng,2005,20:559-582.
[68]Thomas E Quantrille,Y A Liu.人工智能在化学工程中的应用[M].北京:中国石化出版社.1994:448-499.
[69]闻新,周露,王丹力.MATLAB神经网络应用设计[M].北京:科学出版社,2000.
[70]张军红,金永龙,沈峰满.应用优化BP神经网络建立铁水硅含量的预测模型[J].钢铁研究学报,2007,19(11):60-63.
[71]董长虹.Matlab神经网络与应用[M].北京:国防工业出版社,2007:64-68.
[72]唐志航,杨保安.一种改进的BP神经网络在故障诊断中的应用研究[J].机床与液压,2007,35(11):179.
[73]文震,李谦,党志.紫苏油在超临界CO2中溶解度的神经网络模型建立[J].化学工程,2003,31(6):67-70.
[2]Perego C,Lngallina P.Recent advances in the industrial alkylation of aromatics:new catalysts and new processes[J].Catal.Today,2002,73:3-22
[3]Sridevi U,Bokade V V,Satyanarayana C V V,Rao B S,Pradhan N C,Pao B K B.Kinetics of propylation of benzene over H-beta and SAPO-5 catalysts:a comparison[J].J.Mol.Catal.A:Chemical,2002,181:257-262
[4]Tanabe K,Misono M,Ono Y,et al.New solid acid and bases[M].Kodansha and Elsevier Co,1989.227
[5]Meima G R,Van Der Aals M J,et al.Recent development in the production of cumene with zeolite catalysts[J].Erdol Endgas Kohle,1996,112(7/8):315-319
[6]Degnan Jr T F,Smith C M,Venkat C R.Alkylation of aromatics with ethylene and propylene:recent developments in commercial processes[J].Appl Catal A:General,2001,221:283-294
[7]高辉,史建公,曹钢.异丙苯合成工艺进展[J].化学工业与工程技术.2003,24(6):36-38
[8]史建公,卢冠忠,曹钢.异丙苯生产技术进展[J].中国石油化工科技信息指南(上卷)[M].北京:中国石化出版社,2001.32-34
[9]魏文德.有机化工原料大全(下卷)[M].北京:化学工业出版社,1999.113-1381
[10]M.K.Rubin;P.Chu;Composition of synthetic porous crystalline material,its synthesis and use[P],United States Patent 4 954 325 September 4,1990
[11]Lawton S.L.,Leonowicz M.E.,Partridge R.D,et al.Twelve-ring pockets on the external surface of MCM-22 crystals[J],Microporous and Mesoporous Materials,1998,23,109-117
[12]Leonowicz M.E.,Lawton J.A.,Lawton S.L.,et al.MCM-22:A Molecular Sieve with Two Independent Multidimensional Channel Systems[J].Science,1994,264,1910-1913
[13]A.Corma,C.Corell,and P.J.Perez,Synthesis and Characterization of the MCM-22Zeolite[J].zeolites,1995,15,2-8
[14]袁忠勇,张怀彬,王敬中,李赫喧.沸石分子筛MCM-22的合成与表征[J].石油学报,1998,14(2):28-31
[15]Corma A.,Corell C.,Fornes V.,et al.Infrared spectroscopy,thermoprogrammed desorption,and nuclear magnetic resonance study of the acidity,structure,and stability of zeolite MCM-22[J].zeolites,1995,15,576-582
[16]Miguel A.Camblor,Avelino Corma,et al.Synthesis and Structural Characterization of MWW Type Zeolite ITQ-1,the Pure Silica Analog of MCM-22 and SSZ-25[J].Laboratory of Crystallography,ETH,CH-8092 Zurich,Switzerland J.Phys.Chem.B,1998,102(1),pp 44-51
[17]Corma A.From microporous to mesoporous molecular sieve materials and their use in catalysis[J].Chemical Reviews,1997,97(6):2373-2419
[18]徐文炀,窦涛,刘世欧.非水体系中丝光沸石的合成方法[P].CN,88100228.1988.
[19]Inagaki S,Hoshino M,Kikuchi E.Synthesis of MCM-22 zeolite by the vapor-phase transport method[J].Studies in Surface Science and Catalysis,2002,142(1):53-60
[20]Bellussi G,Pazzuconi G,Perego C,et al.Liquid-Phase Alkylation of Benzene with Light Olefms Catalyzed by β-Zeolites[J].J.Catal.,1995,157(1):227-234
[21]Geatti A,Lenarda M,Storaro L,et al.Perissinotto M.Solid acid catalysts from clays:Cumene synthesis by benzene alkylation with propene catalyzed by cation exchanged aluminum pillared clays[J].J.Mol.Catal.A,1997,121(1):111-118
[22]林衍华,方永成,顾星,谢在库.沸石液相烃化合成异丙苯中烷基转移技术进展[J].工业催化,1999,3:10-17
[23]Anand B H,Jagannath D.Novel catalytic aspects of beta zeolite for alkylaromatics transformation[J].Applied Catalysis A:General,1999,181(2):347-354
[24]杨平,潘履让,李赫喧.B分子筛的酸性和苯-丙烯烷基化反应的研究[J].燃料化学学报,1990,18(1):16-22
[25]何长青,刘中民,张盈珍.大孔沸石催化剂上苯与丙烯液相烷基化反应行为的研究[J].燃料化学学报,1999,27(3):203-208
[26]傅吉全,杨立英,张吉瑞.压力空速对FX-01催化剂上苯与丙烯烃化反应的影响[J].石油化工,1998,27(1):13-18
[27]Erich Harth.From brains to neural nets to brains[J].Neural networks,1997,7(10):1241-1255
[28]McCulloch W S,Pitts W A.A logical calculus of ideas immanent in nervous activity[J].Bulletin of Mathematical Biophysics,1943(5):115-133
[29]Hebb D O.The organization of behavior[M].New York:Wiley,1949
[30]Rosenblatt F.The Perceptron:A Probabilistic Model for Information Storage and Organization in the Brain.Psychological Review[J],1958(65):386-458
[31]Widrow B and Hoff M E.Adaptive switching circuits[M].New York:IRE,1960
[32]Minsky M,Papert S.Perceptrons[M],MIT Press,1969
[33]Hopfield J J.Neural networks and physical systems with emergent collective computational abilities[J].Proceedings of the National Academy of Science,1982,79:2554-2558
[34]Rumelhart D E,Hinton G E,Williams R J.Learning representations by back-propagation errors[J].Nature,1986(323):533-536
[35]Raj Sharma,Diwakar Singhal,Ranjana Ghosh.Potential applications of artificial neural networks to thermodynamics:vapor-liquid equilibrium predictions[J].Computers and Chemical Engineering,1999,23:385-390
[36]胡德栋,王威强,魏东,郭建章.固体在超临界流体中溶解度的BP人工神经网络模拟[J].山东大学学报(工学版),2006,36(2):8-11
[37]Macmurray J C,Himmelblau D M.Modeling and control of a packed distillation column using artificial neural networks[J].Computers Chem.Engng,1995,10(19):1077-1088
[38]Sebastian Engell,Gregor Fernholz.Control of a reactive separation process[J].Chemical Engineering and Processing,2003,42:201-210
[39]Tatlier M.,Cigizoglu H K,Ayse E S.Artificial neural network methods for the estimation of zeolite molar compositions that form from different reaction mixtures[J].Comput.Chem.Eng.2005,30,137-139
[40]Istadia I,Amin N A S.Modelling and optimization of catalytic-dielectric barrier discharge plasma reactor for methane and carbon dioxide conversion using hybrid artificial neural network-genetic algorithm technique[J].Chem.Eng.Sci.2007,62, 6568-6581
[41]Filho A C,Filho R M.Concurrent engineering reactor design[J].Comput.Aided Chem.Eng.,2005,20,559-582
[42]Tatlier M.,Cigizoglu H K,Ayse E S.Artificial neural network methods for the estimation of zeolite molar compositions that form from different reaction mixtures[J].Comput.Chem.Eng.2005,30,137-139
[43]Istadia I,Amin N A S.Modelling and optimization of catalytic-dielectric barrier discharge plasma reactor for methane and carbon dioxide conversion using hybrid artificial neural network-genetic algorithm technique[J].Chem.Eng.Sci.2007,62,6568-6581
[44]Filho A C,Filho R M.Concurrent engineering reactor design[J].Comput.Aided Chem.Eng.,2005,20,559-582
[45]魏海坤.神经网络结构设计的理论与方法[M].第一版.北京:国防工业出版社,2005
[46]Polycarpou M,Ioannou P.Learning and convergence analysis of neural-type structured networks[J],IEEE Trans.Neural Networks,1992(3):39-50
[47]卢焕章.石油化工基础数据手册[M].北京:化学工业出版社,1984:205
[48]朱洪法.催化剂成型[M].北京:中国石化出版社,1992:39-55
[49]魏秀萍,李军,崔凤霞,曾广俊,张立群.影响沸石分子筛催化剂强度因素的探讨[J].精细石油化工.2002.7(4):36-38
[50]马军.粉状沸石的成型及应用[J].甘肃科技.2002,1:16
[51]赵野,骆傲阳,于开荣,韩志波,陈广文.影响分子筛催化剂强度因素的探讨[J].石油炼制与化工.1995,3(3):28
[52]Jiratova K,Janacek L.Effect of peptizing on the physical and chemical properties of extruded alumina[J].International Chemical Engineering,1983,23(1):167-174
[53]Pradhan A R,Rao B S.Transalkylation of di-isopropylbenzenes over large pore zeolites[J].Appl Catal A:Gen,1993,106:143-157
[54]Suman K.Jana,Reiichi Nishida,Kazuya Shindo.Pore size control of mesoporous molecular sieves using different organic auxiliary chemicals[J].Microporous and Mesoporous Materials,2004,68:133-142
[55]史建文,李大东,薛用芳,挤出成型过程中的各种因素对氧化铝载体物性的影响[J].石油化工,1985,14(6):323-328
[56]余少兵,李永红,陈洪钫.改性对β分子筛酸性的影响[J].化工学报,2004,55(6):913-918
[57]Torrecilla J S,Otero L,Sanz P D.A Neural Network Approach for Thermal/pressure Food Processing[J].J.Food Eng,2004,62:89-95.
[58]Erich Harth.From brains to neural nets to brains[J].Neural networks,1997,7(10):1241-1255.
[59]管国锋,万辉,畅伟贤.基于神经网络的磷酸三丁醋络合萃取丁酸的研究[J].计算机与应用化学,2004,21(6):823-827.
[60]郭海军,胡星琪,段明.基于神经网络的双指标正交试验设计与分析[J].计算机与应用化学,2004,21(3):481-484.
[61]Raj Sharme,Dtwakar Singhal and Ranjana.Ghosh.Potential application of artificial neural networks to thermodynamics:vapor-liquid equilibrium predictions.Computers and Chemical Engineering.1999,23:385-390.
[62]Thomas E Q,Liu Y A.人工智能在化学工程中的应用[M].北京:中国石化出版社,1994.448-499
[63]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2000,10-26
[64]Torrecilla J S,Otero L,Sanz P D.A Neural Network Approach for Thermal/pressure Food Processing[J].J.Food Eng.2004,62,89-95
[65]Bas D,Boyacl I H.Modeling and optimization Ⅱ:Comparison of estimation capabilities of response surface methodology with artificial neural networks in a biochemical reaction[J].J.Food Eng.2007,78,846-854
[66]Bas D,Dudak F C,Boyacl I H.Modeling and optimization Ⅲ:Reaction rate estimation using artificial neural network(ANN) without a kinetic model[J].J.Food Eng.2007,79,622-628
[67]Filho A C,Filho R M.Concurrent engineering reator design[J].Comput.Aided Chem.Eng,2005,20:559-582.
[68]Thomas E Quantrille,Y A Liu.人工智能在化学工程中的应用[M].北京:中国石化出版社.1994:448-499.
[69]闻新,周露,王丹力.MATLAB神经网络应用设计[M].北京:科学出版社,2000.
[70]张军红,金永龙,沈峰满.应用优化BP神经网络建立铁水硅含量的预测模型[J].钢铁研究学报,2007,19(11):60-63.
[71]董长虹.Matlab神经网络与应用[M].北京:国防工业出版社,2007:64-68.
[72]唐志航,杨保安.一种改进的BP神经网络在故障诊断中的应用研究[J].机床与液压,2007,35(11):179.
[73]文震,李谦,党志.紫苏油在超临界CO2中溶解度的神经网络模型建立[J].化学工程,2003,31(6):67-70.