AI-based prediction and interpretation of column head temperature in a continuous distillation: a case study on methylcyclohexane separation
-
Mohammed El Jattioui
,
Imad Manssouri
Abstract
This study explores the application of artificial intelligence (AI) to predict the column head temperature in a continuous distillation process designed to separate methylcyclohexane from a binary mixture containing 23 % methylcyclohexane by mass. Several AI models were developed and evaluated, using key operational parameters such as heating power, reflux ratio, feed rate, pressure drop, and boiler temperature as input features. The column head temperature served as the target variable, representing the performance of the distillation system. Among the models tested, the Decision Tree Regressor achieved the best performance, with a mean absolute error (MAE) of 0.0090, a root mean square error (RMSE) of 0.0258, and a coefficient of determination R2 of 0.9572. To enhance model interpretability, SHapley Additive exPlanations (SHAP) analysis was applied, revealing that reflux ratio and boiler temperature are the most influential variables. These results demonstrate the model’s effectiveness in predicting the normal operation of an automated continuous distillation column. Furthermore, the model shows potential for real-time implementation, offering a promising approach for online monitoring and fault detection in industrial distillation processes.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: Not applicable.
References
1. Manssouri, I, Boudebbouz, B, Boudad, B. Using artificial neural networks of the type extreme learning machine for the modeling and prediction of the temperature in the head of the column: case of a C6H11–CH3 distillation column. Mater Today Proc 2021;45:7444–9. https://doi.org/10.1016/j.matpr.2021.01.920.Suche in Google Scholar
2. Singh, AK, Tyagi, B, Kumar, V. Classical and neural network-based approach of model predictive control for binary continuous distillation column. Chem Prod Process Model 2014;9:71–87. https://doi.org/10.1515/cppm-2013-0013.Suche in Google Scholar
3. Manssouri, I, Chetouani, Y, El Kihel, B. Using neural networks for fault detection in a distillation column. Int J Comput Appl Technol 2008;32:181–6. https://doi.org/10.1504/IJCAT.2008.020953.Suche in Google Scholar
4. Manssouri, I, Chetouani, Y, Kouddane, R, El Kihel, B. Fault detection and diagnosis in a distillation column by MLP neural networks. New Dev Comput Networks 2012:203–19.Suche in Google Scholar
5. Manssouri, I, Manssouri, M, El Kihel, B. Faults detection and diagnosis in a chemical process by RBF neural network. In: Knowledge management and communication in the information age; 2013:55–70 pp.Suche in Google Scholar
6. Manssouri, I, Manssouri, M, El Kihel, B. Fault detection by K-NN algorithm and MLP neural networks in a distillation column: comparative study. In: Knowledge management and communication in the information age; 2013. 201–15 pp.Suche in Google Scholar
7. Kwon, H, Oh, KC, Choi, Y, Kim, J. Development and application of machine learning-based prediction model for distillation column. Int J Intell Syst 2021. https://doi.org/10.1002/int.22368.Suche in Google Scholar
8. Aggoune, L, Chetouani, Y, Radjeai, H. Recursive identification of the dynamic behavior in a distillation column by means of autoregressive models. J Dyn Syst Measur Control Trans ASME 2014;136:044506. https://doi.org/10.1115/1.4026837.Suche in Google Scholar
9. Aggoune, L, Chetouani, Y. Modeling of a distillation column based on NARMAX and Hammerstein models. Int J Model Simul Sci Comput 2017. https://doi.org/10.1142/S1793962317500349.Suche in Google Scholar
10. Bahar, A, Güner, E, Ozgen, C, Halici, U. Design of state estimators for the inferential control of an industrial distillation column. In IEEE International Conference on Neural Networks – Conference Proceedings; 2006.10.1109/IJCNN.2006.246814Suche in Google Scholar
11. Azzaoui, H, Manssouri, I, Elkihel, B. Methylcyclohexane continuous distillation column fault detection using stationary wavelet transform and K-means. In Lecture Notes in Electrical Engineering 2019, vol 519. 399–411 pp.10.1007/978-981-13-1405-6_48Suche in Google Scholar
12. Kwon, H, Oh, KC, Chung, YG, Kim, J. Development of machine learning model for predicting distillation column temperature. Appl Chem Eng 2020;31:520–5. https://doi.org/10.14478/ace.2020.1057.Suche in Google Scholar
13. Alzakari, SA, Alhussan, AA, Qenawy, AT, Elshewey, AM. Early detection of potato disease using an enhanced convolutional neural network-long short-term memory deep learning model. Potato Res 2025;68:695–713. https://doi.org/10.1007/s11540-024-09760-x.Suche in Google Scholar
14. Samantaray, S, Sahoo, A, Yaseen, ZM, Al-Suwaiyan, MS. River discharge prediction based on multivariate climatological variables using hybridized long short-term memory with a nature-inspired algorithm. J Hydrol 2025;649:132453. https://doi.org/10.1016/j.jhydrol.2024.132453.Suche in Google Scholar
15. Atteia, G, El-Kenawy, EM, Abdel Samee, N, Jamjoom, MM, Ibrahim, A, Abdelhamid, AA, et al.. Adaptive dynamic dipper throated optimization for feature selection in medical data. Comput Mater Continua (CMC) 2023;75:6341–60. https://doi.org/10.32604/cmc.2023.031723.Suche in Google Scholar
16. Khodadadi, N, Abualigah, L, El-Kenawy, EM, Snasel, V, Mirjalili, S. An archive-based multi-objective arithmetic optimization algorithm for solving industrial engineering problems. IEEE Access 2022;10:116415–35. https://doi.org/10.1109/ACCESS.2022.3212081.Suche in Google Scholar
17. McKinney, W. Data structures for statistical computing in Python. In van der Walt, S & Millman, J, editors. Proceedings of the 9th Python in Science Conference; 2010. pp. 51–6.10.25080/Majora-92bf1922-00aSuche in Google Scholar
18. Harris, CR, Millman, KJ, van der Walt, SJ, Gommers, R, Virtanen, P, Cournapeau, D, et al.. Array programming with NumPy. Nature 2020;585:357–62. https://doi.org/10.1038/s41586-020-2649-2.Suche in Google Scholar PubMed PubMed Central
19. Hunter, JD. Matplotlib: a 2D graphics environment. Comput Sci Eng 2007;9:90–5. https://doi.org/10.1109/MCSE.2007.55.Suche in Google Scholar
20. Pedregosa, F, Varoquaux, G, Gramfort, A, Michel, V, Thirion, B, Grisel, O, et al.. Scikit-learn: machine learning in Python. J Mach Learn Res 2011;12:2825–30. https://doi.org/10.48550/arXiv.1201.0490.Suche in Google Scholar
21. Abadi, M, Barham, P, Chen, J, Chen, Z, Davis, A, Dean, J, et al.. TensorFlow: a system for large-scale machine learning. In 12th USENIX symposium on operating systems design and implementation (OSDI’16); 2016. 265–83 pp.Suche in Google Scholar
22. Quinlan, JR. Induction of decision trees. Mach Learn 1986;1:81–106. https://doi.org/10.1007/BF00116251.Suche in Google Scholar
23. Breiman, L. Random forests. Mach Learn 2001;45:5–32. https://doi.org/10.1023/A:1010933404324.10.1023/A:1010933404324Suche in Google Scholar
24. Cortes, C, Vapnik, V. Support-vector networks. Mach Learn 1995;20:273–97. https://doi.org/10.1007/BF00994018.Suche in Google Scholar
25. Lundberg, SM, Lee, S-I. A unified approach to interpreting model predictions. NeurIPS paper; 2017.Suche in Google Scholar
26. SHAP Documentation. SHAP (SHapley Additive exPlanations), SHAP documentation; n.d. Available from: https://shap.readthedocs.io/en/latest/.Suche in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
