The application of hybrid DOE/ANN methodology in lumped kinetic modeling of Fischer–Tropsch reaction

Abstract In this article the application of design of experiment coupled with artificial neural networks in kinetic study of CO hydrogenation reaction and a method of data collection/fitting for the experiment are presented. The kinetic experimental data has been collected from two factors of central composite designs, pressure and feed ratio in different temperatures. Response surface and artificial neural network models have been constructed based on the DOE points and used for generating simulated data. Then different data sets were used to fit LHHW kinetic rates of CO disappearance. The application of the neural networks to solve the problem of correlation of the rate equation parameters has been addressed. The results of kinetic modeling with simulated data sets from ANN and RSM models were compared with randomly collected experimental and the DOE data sets. It was observed that three rate equations were able to fit the data sets and kinetic modeling with the proposed DOE-based and simulated data, are very efficient for assessing the quality of the models. However, conducting kinetic modeling with ANN simulated data presented the best results.

[1]  Yong-wang Li,et al.  Intrinsic kinetics of Fischer–Tropsch synthesis over an Fe–Cu–K catalyst , 1995 .

[2]  Estefania Argente,et al.  Can artificial neural networks help the experimentation in catalysis , 2003 .

[3]  T. Ishihara,et al.  Hydrogenation of carbon monoxide over SiO2-supported Fe-Co, Co-Ni and Ni-Fe bimetallic catalysts , 1987 .

[4]  Ali Aminian,et al.  Predicting the vapor-liquid equilibrium of carbon dioxide+alkanol systems by using an artificial neural network , 2011 .

[5]  R. A. Santen,et al.  Surface Composition and Selectivity of Alloy Catalysts , 1977 .

[6]  Ali Lohi,et al.  Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor , 2011 .

[7]  Myung-June Park,et al.  Kinetic parameter estimation of the Fischer-Tropsch synthesis reaction on K/Fe-Cu-Al catalysts , 2009 .

[8]  Deniz Baş,et al.  Modeling and optimization III: Reaction rate estimation using artificial neural network (ANN) without a kinetic model , 2007 .

[9]  M. Vannice.  Kinetics of Catalytic Reactions , 2005 .

[10]  Tadashi Hattori,et al.  Analysis of factors controlling catalytic activity by neural network , 2006 .

[11]  Wen-Ping Ma,et al.  Kinetics modelling of Fischer–Tropsch synthesis over an industrial Fe–Cu–K catalyst☆ , 2003 .

[12]  Y. Zamani,et al.  Intrinsic kinetics of Fischer–Tropsch reactions over an industrial Co–Ru/γ-Al2O3 catalyst in slurry phase reactor , 2009 .

[13]  W. Ying,et al.  Effects of the ratio of Fe to Co over Fe-Co/SiO2 bimetallic catalysts on their catalytic performance for Fischer-Tropsch synthesis , 2009 .

[14]  E. Shustorovich,et al.  The UBI-QEP method: A practical theoretical approach to understanding chemistry on transition metal surfaces , 1998 .

[15]  M. Dry,et al.  Practical and theoretical aspects of the catalytic Fischer-Tropsch process , 1996 .

[16]  G. Buzzi-ferraris,et al.  Planning of experiments and kinetic analysis , 1999 .

[17]  F. G. Botes,et al.  The Effects of Water and CO2 on the Reaction Kinetics in the Iron‐Based Low‐Temperature Fischer‐Tropsch Synthesis: A Literature Review , 2008 .

[18]  R. Zennaro,et al.  Detailed Kinetics of the Fischer–Tropsch Synthesis on Cobalt Catalysts Based on H-Assisted CO Activation , 2011 .

[19]  C. Satterfield,et al.  Intrinsic kinetics of the Fischer-Tropsch synthesis on a cobalt catalyst , 1991 .

[20]  N. Coville,et al.  Fe:Co/TiO2 bimetallic catalysts for the Fischer–Tropsch reaction: Part 3: The effect of Fe:Co ratio, mixing and loading on FT product selectivity , 2005 .

[21]  Adesoji A. Adesina,et al.  Hydrocarbon synthesis via Fischer-Tropsch reaction: travails and triumphs , 1996 .

[22]  Marcio Schwaab,et al.  Optimum reference temperature for reparameterization of the Arrhenius equation. Part 1 : Problems involving one kinetic constant , 2007 .

[23]  Fischer–Tropsch synthesis with Co/SiO2–Al2O3 catalyst and steady-state modeling using artificial neural networks , 1998 .

[24]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[25]  Deniz Baş,et al.  Modeling and optimization IV: Investigation of reaction kinetics and kinetic constants using a program in which artificial neural network (ANN) was integrated , 2007 .

[26]  F. Fernandes,et al.  Selective cracking of natural gasoline over HZSM-5 zeolite , 2008 .

[27]  Z. Önsan,et al.  Kinetics of CO hydrogenation over coprecipitated cobalt-alumina , 1997 .

[28]  A. Mirzaei,et al.  Kinetic modeling of Fischer–Tropsch synthesis on bimetallic Fe–Co catalyst with phenomenological based approaches , 2012 .

[29]  A. Steynberg,et al.  Fischer-Tropsch technology , 2004 .

[30]  Francesca Pagnanelli,et al.  Shrinking core model with variable activation energy: A kinetic model of manganiferous ore leaching with sulphuric acid and lactose , 2001 .

[31]  Michel Cabassud,et al.  Sequential Experimental Design Strategy for Rapid Kinetic Modeling of Chemical Synthesis , 2005 .

[32]  D. W. Bacon,et al.  Sequential statistical design strategy in an experimental kinetic study , 1972 .

[33]  Manos Mavrikakis,et al.  CO activation pathways and the mechanism of Fischer–Tropsch synthesis , 2010 .

[34]  Sandhya Samarasinghe,et al.  Neural Networks for Applied Sciences and Engineering , 2006 .