Data-driven intelligent modeling framework for the steam cracking process

doi:10.1016/j.cjche.2023.03.020

Abstract

Abstract: Steam cracking is the dominant technology for producing light olefins, which are believed to be the foundation of the chemical industry. Predictive models of the cracking process can boost production efficiency and profit margin. Rapid advancements in machine learning research have recently enabled data-driven solutions to usher in a new era of process modeling. Meanwhile, its practical application to steam cracking is still hindered by the trade-off between prediction accuracy and computational speed. This research presents a framework for data-driven intelligent modeling of the steam cracking process. Industrial data preparation and feature engineering techniques provide computational-ready datasets for the framework, and feedstock similarities are exploited using k-means clustering. We propose LArge-Residuals-Deletion Multivariate Adaptive Regression Spline (LARD-MARS), a modeling approach that explicitly generates output formulas and eliminates potentially outlying instances. The framework is validated further by the presentation of clustering results, the explanation of variable importance, and the testing and comparison of model performance.

Key words: Mathematical modeling, Data-driven modeling, Process systems, Steam cracking, Clustering, Multivariate adaptive regression spline

摘要： Steam cracking is the dominant technology for producing light olefins, which are believed to be the foundation of the chemical industry. Predictive models of the cracking process can boost production efficiency and profit margin. Rapid advancements in machine learning research have recently enabled data-driven solutions to usher in a new era of process modeling. Meanwhile, its practical application to steam cracking is still hindered by the trade-off between prediction accuracy and computational speed. This research presents a framework for data-driven intelligent modeling of the steam cracking process. Industrial data preparation and feature engineering techniques provide computational-ready datasets for the framework, and feedstock similarities are exploited using k-means clustering. We propose LArge-Residuals-Deletion Multivariate Adaptive Regression Spline (LARD-MARS), a modeling approach that explicitly generates output formulas and eliminates potentially outlying instances. The framework is validated further by the presentation of clustering results, the explanation of variable importance, and the testing and comparison of model performance.

关键词: Mathematical modeling, Data-driven modeling, Process systems, Steam cracking, Clustering, Multivariate adaptive regression spline

Qiming Zhao, Kexin Bi, Tong Qiu. Data-driven intelligent modeling framework for the steam cracking process[J]. Chinese Journal of Chemical Engineering, 2023, 61(9): 237-247.

Qiming Zhao, Kexin Bi, Tong Qiu. Data-driven intelligent modeling framework for the steam cracking process[J]. 中国化学工程学报, 2023, 61(9): 237-247.

References

[1] K.X. Bi, S.Y. Zhang, C. Zhang, H.R. Li, X.Y. Huang, H.Y. Liu, T.Qiu, Knowledge expression, numerical modeling and optimization application of ethylene thermal cracking: from the perspective of intelligent manufacturing, Chin. J. Chem. Eng. 38 (2021) 1–17.
[2] M. Fakhroleslam, S.M.Sadrameli, Thermal cracking of hydrocarbons for the production of light olefins; A review on optimal process design, operation, and control, Ind. Eng. Chem. Res. 59 (27) (2020) 12288–12303.
[3] Y.M. Han, R.D. Zhou, Z.Q. Geng, J. Bai, B. Ma, J.Z.Fan, A novel data envelopment analysis cross-model integrating interpretative structural model and analytic hierarchy process for energy efficiency evaluation and optimization modeling: application to ethylene industries, J. Clean. Prod. 246 (2020) 118965.
[4] V.G. Yadav, G.D. Yadav, S.C. Patankar, The production of fuels and chemicals in the new world: critical analysis of the choice between crude oil and biomass vis-à-vis sustainability and the environment, Clean Technol. Environ. Policy22 (9) (2020) 1757–1774.
[5] Y.L. Xu, H. Dinh, Q. Xu, F.T. Eljack, M.M.El-Halwagi, Flare minimization for an olefin plant shutdown via plant-wide dynamic simulation, J. Clean. Prod. 254 (2020) 120129.
[6] M.C. Georgiadis, J.R. Banga, E.N. Pistikopoulos, eds., Process Systems Engineering: Volume 7: Dynamic Process Modeling, Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim, Germany, 2010.
[7] W.M. Marco, V. Goethem, Kleinendorst, V. Leeuwen, Equation-based SPYRO^® model and solver for the simulation of the steam cracking process, Comput. Chem. Eng. 25 (4–6) (2001) 905–911.
[8] M.K. Sabbe, K.M. Van Geem, M.F. Reyniers, G.B.Marin, First principle-based simulation of ethane steam cracking, AIChE J. 57 (2) (2011) 482–496.
[9] Z. Fang, T. Qiu, W. Zhou, Coupled simulation of recirculation zonal firebox model and detailed kinetic reactor model in an industrial ethylene cracking furnace, Chin. J. Chem. Eng. 25 (8) (2017) 1091–1100.
[10] L. Zhang, H.Z. Wang, T. Qiu, B.Z.Chen, Simulation and optimization of multi-period steam cracking process. In:Advances in Petrochemicals. InTech, 2015: .
[11] M. Fakhroleslam, S.M. Sadrameli, Thermal/catalytic cracking of hydrocarbons for the production of olefins; a state-of-the-art review III: process modeling and simulation, Fuel 252 (2019) 553–566.
[12] Kamyar, Keyvanloo, Genetic algorithm model development for prediction of main products in thermal cracking of naphtha: comparison with kinetic modeling, Chem. Eng. J. 209 (2012) 255–262.
[13] W. Wu, Z. Xiong, N. Lü, J. Wang, J. Shao, X. Zhong, Soft-sensor of product yields in ethylene pyrolysis based on support vector regression, CIESC J. 61 (2010) (8)2046–2050.(in Chinese).
[14] Qing, Li, An intelligent hybrid feature subset selection and production pattern recognition method for modeling ethylene plant, J. Anal. Appl. Pyrolysis 160 (2021) 105352.
[15] T. Bikmukhametov, J.Jäschke, Combining machine learning and process engineering physics towards enhanced accuracy and explainability of data-driven models, Comput. Chem. Eng. 138 (2020) 106834.
[16] P.P. Plehiers, S.H. Symoens, I. Amghizar, G.B. Marin, C.V. Stevens, K.M.Van Geem, Artificial intelligence in steam cracking modeling: a deep learning algorithm for detailed effluent prediction, Engineering 5 (6) (2019) 1027–1040.
[17] Yongming, Han, A novel DEACM integrating affinity propagation for performance evaluation and energy optimization modeling: application to complex petrochemical industries, Energy Convers. Manag. 183 (2019) 349–359.
[18] M. Moghadasi, H. Ali Ozgoli, F.Farhani, Steam consumption prediction of a gas sweetening process with methyldiethanolamine solvent using machine learning approaches, Int. J. Energy Res. 45 (1) (2021) 879–893.
[19] S. Gong, C. Shao, L. Zhu, Energy efficiency evaluation in ethylene production process with respect to operation classification, Energy 118 (2017) 1370–1379.
[20] T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition, Springer Science & Business Media, 2009.
[21] J.H.Friedman, Multivariate adaptive regression splines, Ann. Statist. 19 (1) (1991) 1–67.
[22] Y.C. Chen, L. Zhu, J. Gonder, S. Young, K.Walkowicz, Data-driven fuel consumption estimation: a multivariate adaptive regression spline approach, Transp. Res. C Emerg. Technol. 83 (2017) 134–145.
[23] S. Mehdizadeh, Using AR, MA, and ARMA time series models to improve the performance of MARS and KNN approaches in monthly precipitation modeling under limited climatic data, Water Resour. Manag.34 (1) (2020) 263–282.
[24] R.M. Adnan, Z.M. Liang, K.S. Parmar, K. Soni, O. Kisi, Modeling monthly streamflow in mountainous basin by MARS, GMDH-NN and DENFIS using hydroclimatic data, Neural Comput. Appl.33 (7) (2021) 2853–2871.
[25] S. García, J. Luengo, F. Herrera, Data Preprocessing in Data Mining, Springer International Publishing, Cham, New York, 2015.
[26] A. Mitsos, N. Asprion, C.A. Floudas, M. Bortz, M. Baldea, D. Bonvin, A. Caspari, P.Schäfer, Challenges in process optimization for new feedstocks and energy sources, Comput. Chem. Eng. 113 (2018) 209–221.
[27] K.X. Bi, B. Beykal, S. Avraamidou, I. Pappas, E.N. Pistikopoulos, T.Qiu, Integrated modeling of transfer learning and intelligent heuristic optimization for a steam cracking process, Ind. Eng. Chem. Res. 59 (37) (2020) 16357–16367.
[28] C.F. Tsai, M.L. Li, W.C.Lin, A class center based approach for missing value imputation, Knowl. Based Syst. 151 (2018) 124–135.
[29] C. Olsson, A. Eriksson, R. Hartley, Outlier removal using duality, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. June 13-18, 2010, San Francisco, CA, USA. IEEE, (2010) 1450–1457.
[30] Sunith, Bandaru, Data mining methods for knowledge discovery in multi-objective optimization: part A - Survey, Expert Syst. Appl. 70 (2017) 139–159.
[31] L. Al Shalabi, Z. Shaaban, Normalization as a preprocessing engine for data mining and the approach of preference matrix, 2006 International Conference on Dependability of Computer Systems. May 25-27, 2006, Szklarska Poreba, Poland. IEEE, (2006) 207–214.
[32] M. Mittal, L.M. Goyal, D.J. Hemanth, J.K.Sethi, Clustering approaches for high-dimensional databases: a review, Wires Data Min. Knowl. Discov. 9 (3) (2019) e1300.
[33] A. Likas, N. Vlassis, J.J.Verbeek, The global k-means clustering algorithm, Pattern Recognit. 36 (2) (2003) 451–461.
[34] P.J. Rousseeuw, Silhouettes: a graphical aid to the interpretation and validation of cluster analysis, J. Comput. Appl. Math. 20 (1987) 53–65.
[35] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, Scikit-learn: machine learning in Python, Mach. Learn. Python. 12 (2011) 2825–2830.
[36] S. Milborrow, Earth: Multivariate Adaptive Regression Splines models, (2011). http://www.milbo.users.sonic.net/earth/ (accessed June 21, 2021).
[37] K.M. Sundaram, M.M. Shreehan, E.F. Olszewski, Ethylene, in: John Wiley & Sons, Inc. (Ed.), Kirk-Othmer Encycl. Chem. Technol., John Wiley & Sons, Inc., Hoboken, NJ, USA, 2010.
[38] S.M. Sadrameli, Thermal/catalytic cracking of hydrocarbons for the production of olefins: a state-of-the-art review I: Thermal cracking review, Fuel 140 (2015) 102–115.
[39] Feng, Wang, Experimental investigation and modeling of steam cracking of Fischer-Tropsch naphtha for light olefins, Chem. Eng. Process. Process. Intensif. 49 (1) (2010) 51–58.
[40] K. Keyvanloo, J. Towfighi, S.M. Sadrameli, A.Mohamadalizadeh, Investigating the effect of key factors, their interactions and optimization of naphtha steam cracking by statistical design of experiments, J. Anal. Appl. Pyrolysis 87 (2) (2010) 224–230.
[41] B. Beykal, F. Boukouvala, C.A. Floudas, N. Sorek, H. Zalavadia, E.Gildin, Global optimization of grey-box computational systems using surrogate functions and application to highly constrained oil-field operations, Comput. Chem. Eng. 114 (2018) 99–110.
[42] B. Beykal, F. Boukouvala, C.A. Floudas, E.N.Pistikopoulos, Optimal design of energy systems using constrained grey-box multi-objective optimization, Comput. Chem. Eng. 116 (2018) 488–502.
[43] B. Burnak, E.N.Pistikopoulos, Integrated process design, scheduling, and model predictive control of batch processes with closed-loop implementation, AIChE J. 66 (10) (2020) 16981.
[44] I. Bilbao, J. Bilbao, Overfitting problem and the over-training in the era of data: particularly for Artificial Neural Networks, 2017 Eighth International Conference on Intelligent Computing and Information Systems (ICICIS). December 5-7, 2017, Cairo, Egypt. IEEE, (2018) 173–177.
[45] Yufei, Yuan, Induction of fuzzy decision trees, Fuzzy Sets Syst. 69 (2) (1995) 125–139.