Application of machine learning to process simulation of n-pentane cracking to produce ethylene and propene

doi:10.1016/j.cjche.2020.01.017

Abstract

Abstract: Modeling light olefin production was one of the main concerns in chemical engineering field. In this paper, machine learning model based on artificial neural networks (ANN) was established to describe the effects of temperature and catalyst on ethylene and propene formation in n-pentane cracking. The establishment procedure included data pretreatment, model design, training process and testing process, and the mean square error (MSE) and regression coefficient (R²) indexes were employed to evaluate model performance. It was found that the learning algorithm and ANN topology affected the calculation accuracy. GD24223, CGB2423, and LM24223 models were established by optimally matching the learning algorithm with ANN topology, and achieved excellent calculation accuracy. Furthermore, the stability of GD24223, CGB2423 and LM24223 models was investigated by gradually decreasing training data and simultaneously transforming data distribution. Compared with GD24223 and LM24223 models, CGB2423 model was more stable against the variations of training data, and the MSE values were always maintained at the magnitude of 10^-3-10^-4, confirming its applicability for simulating light olefin production in n-pentane cracking.

Key words: Machine learning, ANN, Calculation accuracy, Light olefins, n-Pentane cracking

摘要： Modeling light olefin production was one of the main concerns in chemical engineering field. In this paper, machine learning model based on artificial neural networks (ANN) was established to describe the effects of temperature and catalyst on ethylene and propene formation in n-pentane cracking. The establishment procedure included data pretreatment, model design, training process and testing process, and the mean square error (MSE) and regression coefficient (R²) indexes were employed to evaluate model performance. It was found that the learning algorithm and ANN topology affected the calculation accuracy. GD24223, CGB2423, and LM24223 models were established by optimally matching the learning algorithm with ANN topology, and achieved excellent calculation accuracy. Furthermore, the stability of GD24223, CGB2423 and LM24223 models was investigated by gradually decreasing training data and simultaneously transforming data distribution. Compared with GD24223 and LM24223 models, CGB2423 model was more stable against the variations of training data, and the MSE values were always maintained at the magnitude of 10^-3-10^-4, confirming its applicability for simulating light olefin production in n-pentane cracking.

关键词: Machine learning, ANN, Calculation accuracy, Light olefins, n-Pentane cracking

Weijun Zhu, Xingwang Liu, Xu Hou, Jiayao Hu, Zhenheng Diao. Application of machine learning to process simulation of n-pentane cracking to produce ethylene and propene[J]. Chinese Journal of Chemical Engineering, 2020, 28(7): 1832-1839.

Weijun Zhu, Xingwang Liu, Xu Hou, Jiayao Hu, Zhenheng Diao. Application of machine learning to process simulation of n-pentane cracking to produce ethylene and propene[J]. 中国化学工程学报, 2020, 28(7): 1832-1839.

References

[1] I. Amghizar, L.A. Vandewalle, K.M. Van Geem, G.B. Marin, New trends in olefin production, Engineering 3(2017) 171-178.
[2] A. Corma, E. Corresa, Y. Mathieu, L. Sauvanaud, S. Al-Bogami, M.S. Al-Ghrami, A. Bourane, Crude oil to chemicals:Light olefins from crude oil, Catal. Sci. Technol. 7(2017) 12-46.
[3] S.M. Sadrameli, Thermal/catalytic cracking of liquid hydrocarbons for the production of olefins:Astate-of-the-art review II:Catalytic cracking review, Fuel 173(2016) 285-297.
[4] N. Rahimi, R. Karimzadeh, Catalytic cracking of hydrocarbons over modified ZSM-5 zeolites to produce light olefins:A review, Appl. Catal. A 398(2011) 1-17.
[5] S.M. Sadrameli, Thermal/catalytic cracking of hydrocarbons for the production of olefins:Astate-of-the-art review I:Thermal cracking review, Fuel 140(2015) 102-115.
[6] A. Corma, L. Sauvanaud, Y. Mathieu, S. Al-Bogami, A. Bourane, M. Al-Ghrami, Direct crude oil cracking for producing chemicals:Thermal cracking modeling, Fuel 211(2018) 726-736.
[7] F.M. Alotaibi, S. González-Cortés, M.F. Alotibi, T. Xiao, H. Al-Megren, G. Yang, P.P. Edwards, Enhancing the production of light olefins from heavy crude oils:Turning challenges into opportunities, Catal. Today 317(2018) 86-98.
[8] Y. Che, M. Yuan, Y. Qiao, Q. Liu, J. Zhang, Y. Tian, Fundamental study of hierarchical millisecond gas-phase catalytic cracking process for enhancing the production of light olefins from vacuum residue, Fuel 237(2019) 1-9.
[9] M.A. Bari Siddiqui, A.M. Aitani, M.R. Saeed, S. Al-Khattaf, Enhancing the production of light olefins by catalytic cracking of FCC naphtha over mesoporous ZSM-5 catalyst, Top. Catal. 53(2010) 1387-1393.
[10] S. Al-Khattaf, M.R. Saeed, A. Aitani, M.T. Klein, Catalytic cracking of light crude oil to light olefins and naphtha over E-Cat and MFI:Microactivity test versus advanced cracking evaluation and the effect of high reaction temperature, Energy Fuel 32(2018) 6189-6199.
[11] A. Kossiakoff, F.O. Rice, Thermal decomposition of hydrocarbons, resonance stabilization and isomerization of free radicals, J. Am. Chem. Soc. 65(1943) 590-595.
[12] F.O. Rice, K.F. Herzfeld, Thermal decomposition of organic compounds from the standpoint of free radicals. VI. The mechanism of some chain reactions, J. Am. Chem. Soc. 56(1934) 284-289.
[13] W.O. Haag, R.M. Dessau, Duality of mechanism for acid-catalyzed paraffin cracking, Proceedings of the 8th International Congress on Catalysis, Dechema, Berlin, 2, 1984, pp. 305-316.
[14] X. Meng, C. Xu, J. Gao, L. Li, Studies on catalytic pyrolysis of heavy oils:Reaction behaviors and mechanistic pathways, Appl. Catal. A 294(2005) 168-176.
[15] X. Meng, C. Xu, L. Li, J. Gao, Cracking performance of gasoline and diesel fractions from catalytic pyrolysis of heavy gas oil derived from Canadian synthetic crude oil, Energy Fuel 25(2011) 3382-3388.
[16] R. Zhang, Z. Wang, H. Liu, Z. Liu, G. Liu, X. Meng, Thermodynamic equilibrium distribution of light olefins in catalytic pyrolysis, Appl. Catal. A 522(2016) 165-171.
[17] G.F. Froment, On fundamental kinetic equations for chemical reactions and processes, Curr. Opin. Chem. Eng. 5(2014) 1-6.
[18] G.F. Froment, Single event kinetic modeling of complex catalytic processes, Catal. Rev. 47(2005) 83-124.
[19] W. Feng, E. Vynckier, G.F. Froment, Single event kinetics of catalytic cracking, Ind. Eng. Chem. Res. 32(1993) 2997-3005.
[20] N.V. Dewachtere, F. Santaella, G.F. Froment, Application of a single-event kinetic model in the simulation of an industrial riser reactor for the catalytic cracking of vacuum gas oil, Chem. Eng. Sci. 54(1999) 3653-3660.
[21] G.G. Martens, G.B. Marin, J.A. Martens, P.A. Jacobs, G.V. Baron, A fundamental kinetic model for hydrocracking of C₈ to C₁₂ alkanes on Pt/US-Y zeolites, J. Catal. 195(2000) 253-267.
[22] J.W. Thybaut, G.B. Marin, G.V. Baron, P.A. Jacobs, J.A. Martens, Alkene protonation enthalpy determination from fundamental kinetic modeling of alkane hydroconversion on Pt/H-(US)Y-zeolite, J. Catal. 202(2001) 324-339.
[23] R. Quintana-Solórzano, J.W. Thybaut, G.B. Marin, R. Lødeng, A. Holmen, Single-event microkinetics for coke formation in catalytic cracking, Catal. Today 107-108(2005) 619-629.
[24] H.C. Beirnaert, J.R. Alleman, G.B. Marin, A fundamental kinetic model for the catalytic cracking of alkanes on a USY zeolite in the presence of coke formation, Ind. Eng. Chem. Res. 40(2001) 1337-1347.
[25] R. Quintana-Solórzano, J.W. Thybaut, G.B. Marin, A single-event microkinetic analysis of the catalytic cracking of (cyclo)alkanes on an equilibrium catalyst in the absence of coke formation, Chem. Eng. Sci. 62(2007) 5033-5038.
[26] R. Van Borm, M.-F. Reyniers, G.B. Marin, Catalytic cracking of alkanes on FAU:Singleevent microkinetic modeling including acidity descriptors, AIChE J 58(2012) 2202-2215.
[27] J.W. Thybaut, G.B. Marin, Single-event MicroKinetics:Catalyst design for complex reaction networks, J. Catal. 308(2013) 352-362.
[28] T. von Aretin, S. Schallmoser, S. Standl, M. Tonigold, J.A. Lercher, O. Hinrichsen, Single-event kinetic model for 1-pentene cracking on ZSM-5, Ind. Eng. Chem. Res. 54(2015) 11792-11803.
[29] S. Standl, M. Tonigold, O. Hinrichsen, Single-event kinetic modeling of olefins cracking on ZSM-5:Proof of feed independence, Ind. Eng. Chem. Res. 56(2017) 13096-13108.
[30] T. von Aretin, S. Standl, M. Tonigold, O. Hinrichsen, Optimization of the product spectrum for 1-pentene cracking on ZSM-5 using single-event methodology. Part 1:Two-zone reactor, Chem. Eng. J. 309(2017) 886-897.
[31] T. von Aretin, S. Standl, M. Tonigold, O. Hinrichsen, Optimization of the product spectrum for 1-pentene cracking on ZSM-5 using single-event methodology. Part 2:Recycle reactor, Chem. Eng. J. 309(2017) 873-885.
[32] J. Sundberg, S. Standl, T. von Aretin, M. Tonigold, S. Rehfeldt, O. Hinrichsen, H. Klein, Optimal process for catalytic cracking of higher olefins on ZSM-5, Chem. Eng. J. 348(2018) 84-94.
[33] G. Roohollahi, M. Kazemeini, A. Mohammadrezaee, R. Golhosseini, Chemical kinetic modeling of i-butane and n-butane catalytic cracking reactions over HZSM-5 zeolite, AIChE J 58(2012) 2456-2465.
[34] Y. Liu, X. Chen, H. Zhao, C. Yang, Establishment of kinetic model for catalytic pyrolysis of Daqing atmospheric residue, Chin. J. Chem. Eng. 17(2009) 78-82.
[35] M. Sedighi, K. Keyvanloo, J. Towfighi, Kinetic study of steam catalytic cracking of naphtha on a Fe/ZSM-5 catalyst, Fuel 109(2013) 432-438.
[36] A. Afshar Ebrahimi, H. Mousavi, H. Bayesteh, J. Towfighi, Nine-lumped kinetic model for VGO catalytic cracking:Using catalyst deactivation, Fuel 231(2018) 118-125.
[37] X. Meng, C. Xu, L. Li, J. Gao, Kinetics of catalytic pyrolysis of heavy gas oil derived from Canadian synthetic crude oil, Energy Fuel 25(2011) 3400-3407.
[38] X. Meng, C. Xu, L. Li, J. Gao, Kinetic study of catalytic pyrolysis of C₄ hydrocarbons on a modified ZSM-5 zeolite catalyst, Energy Fuel 24(2010) 6233-6238.
[39] X. Meng, C. Xu, L. Li, J. Gao, Studies on the kinetics of heavy oil catalytic pyrolysis, Ind. Eng. Chem. Res. 42(2003) 6012-6019.
[40] X. Meng, C. Xu, J. Gao, L. Li, Seven-lump kinetic model for catalytic pyrolysis of heavy oil, Catal. Commun. 8(2007) 1197-1201.
[41] J. Li, T. Li, H. Ma, Q. Sun, C. Li, W. Ying, D. Fang, Kinetics of coupling cracking of butene and pentene on modified HZSM-5 catalyst, Chem. Eng. J. 346(2018) 397-405.
[42] D.V. Naik, V. Karthik, V. Kumar, B. Prasad, M.O. Garg, Kinetic modeling for catalytic cracking of pyrolysis oils with VGO in a FCC unit, Chem. Eng. Sci. 170(2017) 790-798.
[43] D. Mier, A.T. Aguayo, M. Gamero, A.G. Gayubo, J. Bilbao, Kinetic modeling of nbutane cracking on HZSM-5 zeolite catalyst, Ind. Eng. Chem. Res. 49(2010) 8415-8423.
[44] E. Epelde, A.T. Aguayo, M. Olazar, J. Bilbao, A.G. Gayubo, Kinetic model for the transformation of 1-butene on a K-modifiedHZSM-5 catalyst, Ind. Eng. Chem. Res. 53(2014) 10599-10607.
[45] T. Cordero-Lanzac, A.T. Aguayo, A.G. Gayubo, P. Castaño, J. Bilbao, Simultaneous modeling of the kinetics for n-pentane cracking and the deactivation of a HZSM-5 based catalyst, Chem. Eng. J. 331(2018) 818-830.
[46] K. Xiong, C. Lu, Z. Wang, X. Gao, Quantitative correlations of cracking performance with physiochemical properties of FCC catalysts by a novel lump kinetic modelling method, Fuel 161(2015) 113-119.
[47] P. Nageswara Rao, D. Kunzru, Thermal cracking of JP-10:Kinetics and product distribution, J. Anal. Appl. Pyrol. 76(2006) 154-160.
[48] T. Ward, J.S. Ervin, R.C. Striebich, S. Zabarnick, Simulations of flowing mildly-cracked normal alkanes incorporating proportional product distributions, J. Propuls. Power 20(2004) 394-402.
[49] T.A. Ward, J.S. Ervin, S. Zabarnick, L. Shafer, Pressure effects on flowing mildlycracked n-decane, J. Propuls. Power 21(2005) 344-355.
[50] Y. Zhu, B. Liu, P. Jiang, Experimental and numerical investigations on n-decane thermal cracking at supercritical pressures in a vertical tube, Energy Fuel 28(2014) 466-474.
[51] D. Zhang, L. Hou, M. Gao, X. Zhang, Experiment and modeling on thermal cracking of n-dodecane at supercritical pressure, Energy Fuel 32(2018) 12426-12434.
[52] M. Mesbah, E. Soroush, M. Rezakazemi, Development of a least squares support vector machine model for prediction of natural gas hydrate formation temperature, Chin. J. Chem. Eng. 25(2017) 1238-1248.
[53] K. Bi, T. Qiu, An intelligent SVM modeling process for crude oil properties prediction based on a hybrid GA-PSO method, Chin. J. Chem. Eng. 27(2019) 1888-1894.
[54] M. Li, W. Wu, B. Chen, Y. Wu, X. Huang, Solubility prediction of gases in polymers based on an artificial neural network:a review, RSC Adv. 7(2017) 35274-35282.
[55] B. Vaferi, M. Karimi, M. Azizi, H. Esmaeili, Comparison between the artificial neural network, SAFT and PRSV approach in obtaining the solubility of solid aromatic compounds in supercritical carbon dioxide, J. Supercrit. Fluid. 77(2013) 44-51.
[56] A. KhazaiePoul, M. Soleimani, S. Salahi, Solubility prediction of disperse dyes in supercritical carbon dioxide and ethanol as co-solvent using neural network, Chin. J. Chem. Eng. 24(2016) 491-498.
[57] M. Karimi, B. Vaferi, S.H. Hosseini, M. Rasteh, Designing an efficient artificial intelligent approach for estimation of hydrodynamic characteristics of tapered fluidized bed from its design and operating parameters, Ind. Eng. Chem. Res. 57(2018) 259-267.
[58] F. Hua, Z. Fang, T. Qiu, Application of convolutional neural networks to largescale naphtha pyrolysis kinetic modeling, Chin. J. Chem. Eng. 26(2018) 2562-2572.
[59] Z. Chen, W. Ma, K. Wei, J. Wu, S. Li, K. Xie, G. Lv, Artificial neural network modeling for evaluating the power consumption of silicon production in submerged arc furnaces, Appl. Therm. Eng. 112(2017) 226-236.
[60] M. Hassanpour, B. Vaferi, M.E. Masoumi, Estimation of pool boiling heat transfer coefficient of alumina water-based nanofluids by various artificial intelligence (AI) approaches, Appl. Therm. Eng. 128(2018) 1208-1222.
[61] X. Hou, N. Ni, Y. Wang, W. Zhu, Y. Qiu, Z. Diao, G. Liu, X. Zhang, Roles of the free radical and carbenium ion mechanisms in pentane cracking to produce light olefins, J. Anal. Appl. Pyrol. 138(2019) 270-280.
[62] X. Xian, G. Liu, X. Zhang, L. Wang, Z. Mi, Cataltic cracking of n-dodecane over HZSM-5 zeolite under supercritical conditions:experiments and kinetics, Chem. Eng. Sci. 65(2010) 5588-5604.