Modeling of thermal cracking of LPG: Application of artificial neural network in prediction of the main product yields

Abstract A three layer perceptron neural network, with back propagation (BP) training algorithm, was developed for modeling of thermal cracking of LPG. The optimum structure of neural network was determined by a trial and error method and different structures were tried. The model investigates the influence of the coil outlet temperature, steam ratio (H 2 O/LPG), total mass feed rate and composition of feed such as C 3 H 8 , C 2 H 6 , iC 4 , and nC 4 on the thermal cracking product yields. Good agreement was found between model results and industrial data. A comparison between the results of mathematical model and designed neural networks was also conducted and ANOVA calculation was carried out. Performance of the neural network model was better than mathematical model.

[1]  R. Zou,et al.  Study on a kinetic model of atmospheric gas oil pyrolysis and coke deposition , 1993 .

[2]  V. Cozzani,et al.  Modeling and Experimental Verification of Physical and Chemical Processes during Pyrolysis of a Refuse-Derived Fuel , 1996 .

[3]  Petr Zamostny,et al.  The kinetic model of thermal cracking for olefins production , 2003 .

[4]  D. Kunzru,et al.  Modeling of naphtha pyrolysis , 1985 .

[5]  Roda Bounaceur,et al.  Modeling of hydrocarbons pyrolysis at low temperature. Automatic generation of free radicals mechanisms , 2002 .

[6]  Tiziano Faravelli,et al.  A wide range kinetic modeling study of the pyrolysis and combustion of naphthenes , 2003 .

[7]  Nikola Pavesic,et al.  A Fast Simplified Fuzzy ARTMAP Network , 2003, Neural Processing Letters.

[8]  Dingli Yu,et al.  Enhanced Neural Network Modelling for a Real Multi-variable Chemical Process , 2002, Neural Computing & Applications.

[9]  P. Savage,et al.  Pyrolysis Kinetics for Long-Chain n-Alkylcyclohexanes , 2001 .

[10]  Stavros Papadokonstantakis,et al.  Variable selection and data pre-processing in NN modelling of complex chemical processes , 2005, Comput. Chem. Eng..

[11]  Jafar Towfighi,et al.  Systematics and modelling representations of LPG thermal cracking for olefin production , 2006 .

[12]  Eugeniusz Molga,et al.  Neural network approach to support modelling of chemical reactors: problems, resolutions, criteria of application , 2003 .

[13]  Ali Elkamel,et al.  Hybrid artificial neural network—First principle model formulation for the unsteady state simulation and analysis of a packed bed reactor for CO2 hydrogenation to methanol , 2005 .

[14]  Tadashi Hattori,et al.  Application of neural network to estimation of catalyst deactivation in methanol conversion , 2004 .

[15]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[16]  Jafar Towfighi,et al.  The combined simulation of heat transfer and pyrolysis reactions in industrial cracking furnaces , 2004 .

[17]  H. Budzinski,et al.  Thermal stability of alkylaromatics in natural systems: Kinetics of thermal decomposition of dodecylbenzene , 2002 .

[18]  Sunwon Park,et al.  Pyrolysis Reaction Mechanism for Industrial Naphtha Cracking Furnaces , 2001 .

[19]  Roberto Guardani,et al.  Neural network based approach for optimization of industrial chemical processes , 2000 .

[20]  Kevin Dahm,et al.  Experimental and modelling investigation of the thermal decomposition of n-dodecane , 2004 .

[21]  Kohji Omata,et al.  Artificial Neural Network Aided Design of a Stable Co-MgO Catalyst of High-Pressure Dry Reforming of Methane , 2005 .

[22]  F Despagne,et al.  Neural networks in multivariate calibration. , 1998, The Analyst.