Computational Modeling and Machine Learning for Predicting the Volumetric Flows in Crude Distillation Units: A Detailed Simulation and Validation Approach
DOI:
https://doi.org/10.18321/ectj1659Keywords:
Artificial Neuronal Networks, Crude, DWSIM, MATLAB, NaphtaAbstract
This research presents a predictive model based on Artificial Neural Networks (ANNs) for the prediction of molar flows in Crude Distillation Units (CDUs). Through rigorous simulation in DWSIM, a database of 350 points was generated, correlating the True Boiling Point (TBP) distillation temperatures of crude oil with the volumetric flows of light and heavy naphtha, distillates, and residue. An ANN with 10 inputs, 20 hidden neurons, and 5 outputs was trained using Levenberg-Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG) algorithms. The BR algorithm demonstrated superior performance, achieving a mean squared error (MSE) of 2.6904E-04 and a regression coefficient (R) of 0.9971 during the testing phase. Validation with experimental data confirmed the accuracy of the model, with average percentage errors of less than 0.68% for all products except residue (6.4%). ANOVA analysis (95% confidence) corroborated the statistical robustness of the ANN. This predictive tool will allow for the optimization of CDU design and operation, with a focus on energy efficiency and minimizing environmental impact. The study discusses the implications for real-time integration with control systems.
References
(1) G. Pannocchia, L. Gallinelli, A. Brambilla, G. Marchetti, Rigorous simulation and model predictive control of a crude distillation unit, IFAC Proc. Vol. 39 (2006) 635–340. Crossref
(2) B. Chang, S. Lee, H. Kwon, I. Moon, Rigorous industrial dynamic simulation of a crude distillation unit considered valve tray rating parameters, Comput. Chem. Eng. 22 (1998) S863–S866. Crossref
(3) M.A. Gadalla, O.Y. Abdelaziz, D.A. Kamel, F.H. Ashour, A rigorous simulation-based procedure for retrofitting an existing Egyptian refinery distillation unit, Energy 83 (2015) 756–765. Crossref
(4) C. Yan, L. Lv, S. Wei, et al., Application of retrofitted design and optimization framework based on the exergy analysis to a crude oil distillation plant, Appl. Therm. Eng. 154 (2019) 637–649. Crossref
(5) V.M. Enríquez-Gutiérrez, M. Jobson, L.M. Ochoa-Estopier, R. Smith, Retrofit of heat-integrated crude oil distillation columns, Chem. Eng. Res. Des. 99 (2015) 185–198. Crossref
(6) M. Gadalla, D. Kamel, F. Ashour, H.N. El Din, A New Optimisation based Retrofit Approach for Revamping an Egyptian Crude Oil Distillation Unit, Energy Procedia 36 (2013) 454–464. Crossref
(7) R. Chen, H. Qian, M.K. Khashan, et al., Triple-objective optimization using ANN+NSGA-II for an innovative biomass gasification-heat recovery process, producing electricity, coolant, and liquefied hydrogen, Case Stud. Therm. Eng. 60 (2024) 104647. Crossref
(8) Y. Zhou, W. Li, Y. Song, ANN model of co-gasification process in bubbling fluidized bed: Contribution ratio analysis, Int. J. Hydrog. Energy 73 (2024) 10–19. Crossref
(9) D. Antanasijević, V. Pocajt, I. Popović, et al., The forecasting of municipal waste generation using artificial neural networks and sustainability indicators, Sustain. Sci. 8 (2013) 37–46. Crossref
(10) N. Elshaboury, E.M. Abdelkader, G. Alfalah, A. Al-Sakkaf, Predictive Analysis of Municipal Solid Waste Generation Using an Optimized Neural Network Model, Processes 9 (2021) 2045. Crossref
(11) B. Fang, J. Yu, Z. Chen, et al., Artificial intelligence for waste management in smart cities: A review, Environ. Chem. Lett. 21 (2023) 1959–1989. Crossref
(12) H.K. Balsora, K.S.J.B. Joshi, A. Sharma, et al., Artificial Neural Network-Based Models for the Prediction of Biomass Pyrolysis Products from Preliminary Analysis, Ind. Eng. Chem. Res. 62 (2023) 14311–14319. Crossref
(13) N. Sharma and K. Singh, Model predictive control and neural network predictive control of TAME reactive distillation column, Chem. Eng. Process.: Process Intensif. 59 (2012) 9–21. Crossref
(14) R. Porrazzo, A. Cipollina, M. Galluzzo, G. Micale, A neural network-based optimizing control system for a seawater-desalination solar-powered membrane distillation unit, Comput. Chem. Eng. 54 (2013) 79–96. Crossref
(15) L.M. Ochoa-Estopier, M. Jobson, R. Smith, Operational optimization of crude oil distillation systems using artificial neural networks, Comput. Chem. Eng. 59 (2013) 178–185. Crossref
(16) L.C.K. Liau, T.C.K. Yang, M. Te Tsai, Expert system of a crude oil distillation unit for process optimization using neural networks, Expert Syst. Appl. 26 (2004) 247–255. Crossref
(17) S. Motlaghi, F. Jalali, M.N. Ahmadabadi, An expert system design for a crude oil distillation column with the neural networks model and the process optimization using genetic algorithm framework, Expert Syst. Appl. 35 (2008) 1540–1545. Crossref
(18) D. Ibrahim, M. Jobson, J. Li, G. Guillén-Gosálbez, Optimal design of flexible heat-integrated crude oil distillation units using surrogate models, Chem. Eng. Res. Des. 165 (2021) 280–297. Crossref
(19) DWSIM, DWSIM – The Open Source Chemical Process Simulator, 2023. URL (accessed January 10, 2024).
(20) K. Ankita Singh, D. Kundu, Comprehensive thermodynamic modeling framework for the estimation of physico-chemical properties of deep eutectic solvent-heavy crude oil system, J. Mol. Liq. 392 (2023) 123489. Crossref
(21) M.A. Jamali, A. Bissenbay, N. Nuraje, Thermodynamic Modeling and Process Simulation of Kumkol Crude Oil Refining, Eurasian Chem.-Technol. J. 25 (2023) 183–192. Crossref
(22) Souck Jenny, Modelling of Crude Oil Distillation – Modellering av råoljedestillation, Stockholm, 2012., p. 57. URN: urn:nbn:se:kth:diva-146195
(23) H. Al-Muslim, I. Dincer, Thermodynamic analysis of crude oil distillation systems, Int. J. Energy Res. 29 (2005) 637–655. Crossref
(24) J.P. Gutierrez, L.A. Benítez, J. Martínez, et al., Thermodynamic properties for the simulation of crude oil primary refining, Int. Journal of Engineering Research and Applications 4 (2014) 190–194. URL
(25) P. Zafari, A. Ghaemi, Modeling and optimization of CO2 capture into mixed MEA-PZ amine solutions using machine learning based on ANN and RSM models, Results Eng. 19 (2023) 101279. Crossref
(26) J. Rasulzade, Y. Maksum, M. Nogaibayeva, et al., Reduction of Material Usage in 3D Printable Structures Using Topology Optimization Accelerated with U-Net Convolutional Neural Network, Eurasian Chem.-Technol. J. 24 (2022) 277–286. Crossref
(27) R. Al Dwood, Q. Meng, A.W. Ibrahim, et al., A novel hybrid ANN-GB-LR model for predicting oil and gas production rate, Flow Meas. Instrum. 100 (2024) 102690. Crossref
(28) F. Abbasian, G.I. Hadaller, R.A. Fortman, et al., An Artificial Neural Network (ANN) Model to Predict Critical Heat Flux (CHF) in a CANDU Fuel Element Simulation (FES) with Various Nonuniform Axial Heat Flux Shapes and Flow Liner Creep Profiles, Nucl. Eng. Des. 432 (2025) 113736. Crossref
(29) R.N.G. Santos, E.R.A. Lima, M.L.L. Paredes, ASTM D86 distillation curve: Experimental analysis and premises for literature modeling, Fuel 284 (2021) 118958. Crossref
(30) M. Troiano, E. Nobile, F. Mangini, et al., A Comparative Analysis of the Bayesian Regularization and Levenberg–Marquardt Training Algorithms in Neural Networks for Small Datasets: A Metrics Prediction of Neolithic Laminar Artefacts Information 15 (2024) 270. Crossref
(31) A. Taheri-Garavand, M. Beiranvandi, A. Ahmadi, N. Nikoloudakis, Predictive modeling of Satureja rechingeri essential oil yield and composition under water deficit and soil amendment conditions using artificial neural networks (ANNs), Comput. Electr. Agric. 222 (2024) 109072. Crossref
(32) S. Abubakar, D. Okoh, B.I. Tijjani, R.S. Said, Speed and accuracy investigations of neural network algorithms for ionospheric modelling at an equatorial region, J. Atmos. Sol.-Terr. Phys. 265 (2024) 106365. Crossref
(33) D. Chuquin-Vasco, G. Torres-Yanacallo, C. Calderón-Tapia, et al., ANN for the prediction of isobutylene dimerization through catalytic distillation for a preliminary energy and environmental evaluation, AIMS Environ. Sci. 11 (2024) 157–183. Crossref
(34) D. Chuquin-Vasco, D. Chicaiza-Sagal, C. Calderón-Tapia, et al., Forecasting mixture composition in the extractive distillation of n-hexane and ethyl acetate with n-methyl-2-pyrrolidone through ANN for a preliminary energy assessment, AIMS Energy 12 (2024) 439–463. Crossref
(35) F.L. Marcos, B. Plangklang, Design and simulation of hybrid renewable systems for rural electrification, Energy Rep. 11 (2024) 2220–2235. Crossref
(36) B. Choudhuri, R. Sen, Optimization of WEDM parameters for Machining Inconel 800 by ANN based Bayesian hybrid algorithm. Mater. Today Proc. 62 (2022) 1098–1101. Crossref
(37) A. Tgarguifa, T. Bounahmidi, S. Fellaou, Optimal Design of the Distillation Process Using the Artificial Neural Networks Method,” 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Meknes, Morocco, 2020, pp. 1-6. Crossref
(38) S.P. Pushkala, R.C. Panda, Design and analysis of reactive distillation for the production of isopropyl myristate, Cleaner Chem. Eng. 5 (2023) 100090. Crossref
(39) Statgraphics Technologies, STATGRAPHICS® Centurion 19 User Manual, 2020. URL
Downloads
Published
How to Cite
Issue
Section
