Downloads

Additional Files

Valverde, J. L., Ferro, V. R., Romero-Díaz, M. M., & Giroir-Fendler, A. Capability of Digital Twins for Representing a Complex Process—Prediction of Multicomponent Adsorption Breakthrough Curves and Times. Advanced Chemical Process Analysis. 2025. doi: Retrieved from https://w3.sciltp.com/journals/acpa/article/view/725
Volume 1, Issue 1, 2025
Copyright (c) 2025 by the authors.
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Article

Capability of Digital Twins for Representing a Complex Process—Prediction of Multicomponent Adsorption Breakthrough Curves and Times

Jose Luis Valverde 1,*, Victor Roberto Ferro 2,†, María Mercedes Romero-Díaz 1,† and Anne Giroir-Fendler 3,†

1 Department of Chemical Engineering, University of Castilla La Mancha, Avenida Camilo José Cela 10, 13071 Ciudad Real, Spain

2 Department of Chemical Engineering, Universidad Autónoma de Madrid, C. Francisco Tomás y Valiente 7, Fuencarral-El Pardo, 28049 Madrid, Spain

3 Department of Chemistry and Biochemistry, Université Claude Bernard Lyon 1, CNRS, IRCELYON, 2 Avenue Albert Einstein, F-69622 Villeurbanne, France

* Correspondence: joseluis.valverde@uclm.es; Tel.: +34-926-295-300

† These authors contributed equally to this work.

Received: 29 January 2025; Revised: 3 March 2025; Accepted: 4 March 2025; Published: 6 March 2025

Abstract: This work tries to elucidate the reliability of artificial neural networks (ANN) to predict complex processes. This way, breakthrough curves and breakthrough times corresponding to 243 different scenarios of the multicomponent adsorption of H2, CO and CO2 in a fixed bed from a large set of runs (rather than a single run, which is the majority situation reported in the literature) generated through Aspen AdsorptionTM, were fitted to 600 ANNs configurations through a homemade software running in Fortran and 8 additional algorithms contained in the Scikit-Learn, a Python module for machine learning. To generate a consistent ANN, data obtained through Aspen AdsorptionTM were randomly divided into two groups: training (80% of the breakthrough curves and breakthrough times) and validation (20% of them). This procedure was able to properly predict single breakthrough curves. However, the capacity of the ANN for predicting a set of breakthrough curves was not so good as expected although the trends followed by the prediction curves could be used to make a good estimation of the dynamic behaviour of adsorption process. Finally, it was observed a good agreement between the values of the breakthrough times corresponding to the reduction of the H2 concentration in the outlet stream of 2% computed by Aspen AdsorptionTM and used for validation and those predicted by the best ANN model. The general procedure here followed could be equally used for analyzing real set of adsorption experiments or other different complex processes as described here.

Keywords:

digital twin multicomponent adsorption Aspen AdsorptionTM

References

  1. Cavalcanti, F.M.; Kozonoe, C.E.; Pacheco, K.A.; et al. Application of Artificial Neural Networks to Chemical and Process Engineering. Deep. Learn. Appl. 2021, 2021, 167.
  2. Feise, H.J.; Schaer, E. Mastering Digitized Chemical Engineering. Educ. Chem. Eng. 2021, 34, 78–86. https://doi.org/10.1016/j.ece.2020.11.011.
  3. Venkatasubramanian, V. The Promise of Artificial Intelligence in Chemical Engineering: Is It Here, Finally? AIChE J. 2019, 65, 466.
  4. Barbero-Sánchez, J.; Megía-Ortega, A.; Ferro, V.R.; et al. Exploring Alternatives to Create Digital Twins from and for Process Simulation. J. Comput. Sci. Res. 2024, 6, 16–30.
  5. García, N.M.; Valverde, J.L.; Cano, B.D.; et al. Selective Recovery of Zinc from Alkaline Batteries via a Basic Leaching Process and the Use of a Machine Learning-Based Digital Twin for Predictive Purposes. Energies 2024, 17, 1–15.
  6. Li, C.; Yang, T.; Luo, H.; et al. Multi-Objective Optimization of Breakthrough Times for Hydrogen Purification through Layered Bed Pressure Swing Adsorption Based on Genetic Algorithm and Artificial Neural Network Model. Int. J. Hydrogen Energy 2024, 52, 390–405. https://doi.org/10.1016/j.ijhydene.2023.08.357.
  7. Babu, B.V.; Ramakrishna, V.; Chakravarthy, K.K. Artificial Neural Networks for Modeling of Adsorption. Learning 2008, 5, 1–6.
  8. Arora, A.; Iyer, S.S.; Hasan, M.M.F. Computational Material Screening Using Artificial Neural Networks for Adsorption Gas Separation. J. Phys. Chem. C 2020, 124, 21446–21460. https://doi.org/10.1021/acs.jpcc.0c05900.
  9. Ma, S.; Tong, L.; Ye, F.; et al. Hydrogen Purification Layered Bed Optimization Based on Artificial Neural Network Prediction of Breakthrough Curves. Int. J. Hydrogen Energy 2019, 44, 5324–5333. https://doi.org/10.1016/j.ijhydene.2018.12.142.
  10. Díaz-Rivera, A.; Zavala-Arce, R.E.; García-Rivas, J.L.; et al. Modeling of Artificial Neural Networks for the Adsorption of Synthetic Dyes in an Aqueous Solution Using Double Layer Hydroxides. MRS Adv. 2023, 8, 77–82. https://doi.org/10.1557/s43580-023-00535-z.
  11. Astray, G.; Soria-Lopez, A.; Barreiro, E.; et al. Machine Learning to Predict the Adsorption Capacity of Microplastics. Nanomaterials 2023, 13, 1061. https://doi.org/10.3390/nano13061061.
  12. Schio, R.R.; Salau, N.P.G.; Mallmann, E.S.; et al. Modeling of Fixed-Bed Dye Adsorption Using Response Surface Methodology and Artificial Neural Network. Chem. Eng. Commun. 2021, 208, 1081–1092.
  13. Chowdhury, S.; Das Saha, P. Artificial Neural Network (ANN) Modeling of Adsorption of Methylene Blue by NaOH-Modified Rice Husk in a Fixed-Bed Column System. Environ. Sci. Pollut. Res. 2013, 20, 1050–1058. https://doi.org/10.1007/s11356-012-0912-2.
  14. Yusuf, M.; Song, K.; Li, L. Fixed Bed Column and Artificial Neural Network Model to Predict Heavy Metals Adsorption Dynamic on Surfactant Decorated Graphene. Colloids Surf. A Physicochem. Eng. Asp. 2020, 585, 124076. https://doi.org/10.1016/j.colsurfa.2019.124076.
  15. Senthilkumar, V.; Ilavenil, K.K. Artificial Neural Network Prediction of Optimal Phenylic Acid Adsorption Using Lantana Camara Activated Carbon. Orient. J. Chem. 2023, 39, 172–178. https://doi.org/10.13005/ojc/390121.
  16. Hou, J.; Bao, W.; Zhang, J.; et al. Characteristics and Mechanisms of Sulfamethoxazole Adsorption onto Modified Biochars with Hierarchical Pore Structures: Batch, Predictions Using Artificial Neural Network and Fixed Bed Column Studies. J. Water Process Eng. 2023, 54, 103975. https://doi.org/10.1016/j.jwpe.2023.103975.
  17. Meena, G.; Rawal, N. Artificial Neural Network Modeling for Adsorption Efficiency of Cr(VI) Ion from Aqueous Solution Using Waste Tire Activated Carbon. Nat. Environ. Pollut. Technol. 2023, 22, 1481–1491. https://doi.org/10.46488/NEPT.2023.v22i03.033.
  18. Atta, H.A.M. Artificial Neural Network [ANN] Modeling for Tetracycline Adsorption on Rice Husk Using Continuous System. Desalination Water Treat. 2024, 317, 100026. https://doi.org/10.1016/j.dwt.2024.100026.
  19. Nighojkar, A.; Zimmermann, K.; Ateia, M.; et al. Application of Neural Network in Metal Adsorption Using Biomaterials (BMs): A Review. Environ. Sci. Adv. 2022, 2, 11–38. https://doi.org/10.1039/d2va00200k.
  20. Zafari, T.; Keyvani, B.; Mousavi, M.; et al. Adsorption of Cyclohexane onto Activated Nanoporous Graphene: Modeling Using Artificial Neural Network. Iran. J. Chem. Chem. Eng. 2023, 42, 772–785.
  21. Reynel-Ávila, H.E.; Aguayo-Villarreal, I.A.; Diaz-Muñoz, L.L.; et al. A Review of the Modeling of Adsorption of Organic and Inorganic Pollutants from Water Using Artificial Neural Networks. Adsorpt. Sci. Technol. 2022, 2022, 9384871. https://doi.org/10.1155/2022/9384871.
  22. Ghaedi, A.M.; Vafaei, A. Applications of Artificial Neural Networks for Adsorption Removal of Dyes from Aqueous Solution: A Review. Adv. Colloid Interface Sci. 2017, 245, 20–39. https://doi.org/10.1016/j.cis.2017.04.015.
  23. Subraveti, S.G.; Li, Z.; Prasad, V.; et al. Physics-Based Neural Networks for Simulation and Synthesis of Cyclic Adsorption Processes. Ind. Eng. Chem. Res. 2022, 61, 4095–4113. https://doi.org/10.1021/acs.iecr.1c04731.
  24. Tariq, R.; Abatal, M.; Vargas, J.; et al. Deep Learning Artificial Neural Network Framework to Optimize the Adsorption Capacity of 3-Nitrophenol Using Carbonaceous Material Obtained from Biomass Waste. Sci. Rep. 2024, 14, 20250. https://doi.org/10.1038/s41598-024-70989-0.
  25. Göde, F.; Yılmaz, A.; Aktaş, A.H.; et al. Artificial Neural Network Approach to Model Cr(III) and Cr(VI) Adsorption by NCS, ACS and BCS. Appl. Water Sci. 2024, 14, 28. https://doi.org/10.1007/s13201-023-02054-6.
  26. Mesutoğlu, Ö.Ç. The Use of Artificial Neural Network for Modeling Adsorption of Congo Red Onto Activated Hazelnut Shell. Environ. Monit. Assess. 2024, 196, 630. https://doi.org/10.21203/rs.3.rs-3804393/v1.
  27. Iftikhar, S.; Zahra, N.; Rubab, F.; et al. Artificial Neural Networks for Insights into Adsorption Capacity of Industrial Dyes Using Carbon-Based Materials. Sep. Purif. Technol. 2023, 326, 124891. https://doi.org/10.1016/j.seppur.2023.124891.
  28. Cong, G.; Gupta, A.; Neumann, R.; et al. Prediction of CO2 Adsorption in Nano-Pores with Graph Neural Networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Online, 22 February–1 March 2022.
  29. Chen, S.; Bai, S.; Ya, R.; et al. Continuous Silicic Acid Removal in a Fixed-Bed Column Using a Modified Resin: Experiment Investigation and Artificial Neural Network Modeling. J. Water Process Eng. 2022, 49, 102937. https://doi.org/10.1016/j.jwpe.2022.102937.
  30. Giri, A.K.; Mishra, P.C. Application of Artificial Neural Network for Prediction of Fluoride Removal Efficiency Using Neutralized Activated Red Mud from Aqueous Medium in a Continuous Fixed Bed Column. Environ. Sci. Pollut. Res. 2023, 30, 23997–24012. https://doi.org/10.21203/rs.3.rs-1702568/v1.
  31. Lee, W.S.; Park, M.Y.; Duong, X.Q.; et al. Time Allocation of a Three-Bed Adsorption Chiller Using an Artificial Neural Network. Case Stud. Therm. Eng. 2021, 28, 101553. https://doi.org/10.1016/j.csite.2021.101553.
  32. El Bey, A.; Laidi, M.; Yettou, A.; et al. Practical Artificial Neural Network Tool for Predicting the Competitive Adsorption of Dyes on Gemini Polymeric Nanoarchitecture. Kem. Ind. 2021, 70, 481–488. https://doi.org/10.15255/kui.2020.069.
  33. Dalhat, M.A.; Mu’Azu, N.D.; Essa, M.H. Generalized Decay and Artificial Neural Network Models for Fixed-Bed Phenolic Compounds Adsorption onto Activated Date Palm Biochar. J. Environ. Chem. Eng. 2021, 9, 104711. https://doi.org/10.1016/j.jece.2020.104711.
  34. Chen, C.; Chen, Z.; Shen, J.; et al. Dynamic Adsorption Models and Artificial Neural Network Prediction of Mercury Adsorption by a Dendrimer-Grafted Polyacrylonitrile Fiber in Fixed-Bed Column. J. Clean. Prod. 2021, 310, 127511. https://doi.org/10.1016/j.jclepro.2021.127511.
  35. Hentabli, M.; Hanini, S.; Laidi, M.; et al. Artificial Neural Network Modelling of Multi-System Dynamic Adsorption of Organic Pollutants on Activated Carbon. Kem. Ind. 2021, 70, 1–12. https://doi.org/10.15255/kui.2020.011.
  36. Ahmad, Z.U.; Yao, L.; Lian, Q.; et al. The Use of Artificial Neural Network (ANN) for Modeling Adsorption of Sunset Yellow onto Neodymium Modified Ordered Mesoporous Carbon. Chemosphere 2020, 256, 127081. https://doi.org/10.1016/j.chemosphere.2020.127081.
  37. Khan, T.; Manan, T.S.B.A.; Isa, M.H.; et al. Modeling of Cu(II) Adsorption from an Aqueous Solution Using an Artificial Neural Network (ANN). Molecules 2020, 25, 3263. https://doi.org/10.3390/molecules25143263.
  38. De Leon, V.B.; de Negreiros, B.A.F.; Brusamarello, C.Z.; et al. Artificial Neural Network for Prediction of Color Adsorption from an Industrial Textile Effluent Using Modified Sugarcane Bagasse: Characterization, Kinetics and Isotherm Studies. Environ. Nanotechnol. Monit. Manag. 2020, 14, 100387. https://doi.org/10.1016/j.enmm.2020.100387.
  39. Mazloom, M.S.; Rezaei, F.; Hemmati-Sarapardeh, A.; et al. Artificial Intelligence Based Methods for Asphaltenes Adsorption by Nanocomposites: Application of Group Method of Data Handling, Least Squares Support Vector Machine, and Artificial Neural Networks. Nanomaterials 2020, 10, 890. https://doi.org/10.3390/nano10050890.
  40. Anbazhagan, S.; Thiruvengadam, V.; Kulanthai, K. Adaptive Neuro-Fuzzy Inference System and Artificial Neural Network Modeling for the Adsorption of Methylene Blue by Novel Adsorbent in a Fixed-Bed Column Method. Iran. J. Chem. Chem. Eng. 2020, 39, 75–93.
  41. Kiraz, A.; Canpolat, O.; Erkan, E.F.; et al. Artificial Neural Networks Modeling for the Prediction of Pb(II) Adsorption. Int. J. Environ. Sci. Technol. 2019, 16, 5079–5086. https://doi.org/10.1007/s13762-018-1798-4.
  42. Yetilmezsoy, K.; Demirel, S. Artificial Neural Network (ANN) Approach for Modeling of Pb(II) Adsorption from Aqueous Solution by Antep Pistachio (Pistacia Vera L.) Shells. J. Hazard. Mater. 2008, 153, 1288–1300. https://doi.org/10.1016/j.jhazmat.2007.09.092.
  43. Zarei, M.; Fazli, S.; Najjari, N.; et al. Efficiency of Artificial Neural Networks for Modeling of Malachite Green Adsorption by Tea Waste and Adsorption Isotherm Study. J. Water Wastewater 2019, 30, 51–62. https://doi.org/10.22093/wwj.
  44. Dinçtürk Atalay, E.; Göde, F.; Aktaş, A.H. Artificial Neural Networks Approach for Modeling of Cr(VI) Adsorption from Aqueous Solution by MR, MAC, MS. J. Interfaces 2051, 2, 81–91. https://doi.org/10.22051/JITF.2018.18582.1014.
  45. Yildiz, S. Artificial Neural Network Approach for Modeling of Ni(II) Adsorption from Aqueous Solution by Peanut Shell. Ecol. Chem. Eng. 2018, 25, 581–604. https://doi.org/10.1515/eces-2018-0039.
  46. Bulut, A.; Yusan, S.; Aytas, S.; et al. Artificial Neural Network (ANN) Approach for Modeling of Sr(II) Adsorption from Aqueous Solution by Natural Calcium-Based Materials. Res. J. Environ. Sci. 2018, 12, 121–131. https://doi.org/10.3923/rjes.2018.121.131.
  47. de Araújo Padilha, C.E.; de Araújo Padilha, C.A.; de Santana Souza, D.F.; et al. Recurrent Neural Network Modeling Applied to Expanded Bed Adsorption Chromatography of Chitosanases Produced by Paenibacillus Ehimensis. Chem. Eng. Res. Des. 2017, 117, 24–33. https://doi.org/10.1016/j.cherd.2016.09.022.
  48. Sabri, N.H.; Rani, N.H.A.; Mohamad, N.F.; et al. Simulation of CO2 Capture for Amine Impregnated Activated Carbon–Palm Kernel Shell (AC-PKS) Adsorbent in Pressure Swing Adsorption (PSA) Using Aspen Adsorption. Mater. Today Proc. 2023. https://doi.org/10.1016/j.matpr.2022.12.206.
  49. Gabriela, A. The Potential of Aspen Adsorption TM Software Package to Simulate Pressure Swing Adsorption Units. Master’s Thesis, Universidade do Porto, Porto, Portugal, 2020.
  50. Kottititum, B.; Srinophakun, T.; Phongsai, N.; et al. Optimization of a Six-Step Pressure Swing Adsorption Process for Biogas Separation on a Commercial Scale. Appl. Sci. 2020, 10, 4692. https://doi.org/10.3390/app10144692.
  51. Tong, L.; Bénard, P.; Zong, Y.; et al. Artificial Neural Network Based Optimization of a Six-Step Two-Bed Pressure Swing Adsorption System for Hydrogen Purification. Energy AI 2021, 5, 100075. https://doi.org/10.1016/j.egyai.2021.100075.
  52. Lee, J.J.; Kim, M.K.; Lee, D.G.; et al. Heat-Exchange Pressure Swing Adsorption Process for Hydrogen Separation. AIChE J. 2008, 54, 2054–2064. https://doi.org/10.1002/aic.11544.
  53. Jagtap, A.D.; Karniadakis, G.E. How Important Are Activation Functions in Regression and Classification? A Survey, Performance Comparison, and Future Directions. J. Mach. Learn. Model. Comput. 2023, 4, 21–75.
  54. Alzubaidi, L.; Zhang, J.; Humaidi, A.J.; et al. Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions. J. Big Data 2021, 8, 1–74.
  55. Reyad, M.; Sarhan, A.M.; Arafa, M. A Modified Adam Algorithm for Deep Neural Network Optimization. Neural Comput. Appl. 2023, 35, 17095–17112.
  56. Hagan, M.T.; Demuth, H.B.; Beale, M. Neural Network Design; PWS Publishing Co.: Stillwater, OK, USA, 1997.
  57. Nanni, L.; Brahnam, S.; Paci, M.; et al. Comparison of Different Convolutional Neural Network Activation Functions and Methods for Building Ensembles for Small to Midsize Medical Data Sets. Sensors 2022, 22, 6129.
  58. Moré, J.J. The Levenberg-Marquardt Algorithm: Implementation and Theory. In Proceedings of the Numerical Analysis: Biennial Conference, Dundee, Scotland, 28 June–1 July 1977; Springer: Berlin/Heidelberg, Germany, 2006; pp. 105–116.
  59. Aas, K.; Jullum, M.; Løland, A. Explaining Individual Predictions When Features Are Dependent: More Accurate Approximations to Shapley Values. Artif. Intell. 2021, 298, 103502.
  60. De Oña, J.; Garrido, C. Extracting the Contribution of Independent Variables in Neural Network Models: A New Approach to Handle Instability. Neural Comput. Appl. 2014, 25, 859–869.
  61. Hagan, M.T.; Menhaj, M.B. Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Netw. 1994, 5, 989–993. https://doi.org/10.1109/72.329697.
  62. Valverde, J.L.; Ferro, V.R.; Giroir-Fendler, A. Prediction of the solid-liquid equilibrium of ternary and quaternary salt-water systems. Influence of the e-NRTL interaction parameters. Fluid Phase Equilib. 2023, 572, 113832. https://doi.org/10.1016/j.fluid.2023.113832.
  63. Valverde, J.L.; Ferro, V.R.; Giroir-Fendler, A. Application of the e-NRTL model to electrolytes in mixed solvents methanol-, ethanol-water, and PEG-water. Fluid Phase Equilib. 2022, 560, 113516. https://doi.org/10.1016/j.fluid.2022.113516.
  64. Valverde, J.L.; Ferro, V.R.; Giroir-Fendler, A. Estimation of e-NRTL binary interaction parameters and its impact on the prediction of thermodynamic properties of multicomponent electrolyte systems. Fluid Phase Equilib. 2022, 551, 113264. https://doi.org/10.1016/j.fluid.2021.113264.