Hydrogen concentration prediction in a polymerization reactor based on machine learning
DOI:
https://doi.org/10.5281/zenodo.15643200Keywords:
python, machine learning, predictive analysis, artificial intelligenceAbstract
The concentration of hydrogen in a polymerization reactor was modeled using Machine Learning in Python. Data preprocessing methods (lagged variables, cleaning, and outlier detection) were employed. Statistical techniques were applied for visualization of variable correlation using Heatmap. Linear Regression, ARIMAX and GBR models were adjusted, obtaining correlations of 0.7950, 0.6722 and 0.6395 respectively. Linear Regression predictive model was selected for its higher correlation, and a 14.96% improvement was obtained through observation grouping. For sensitivity analysis, concentration prediction was achieved with values of 0.65 and 0.44 for 3 and 2 kg/h raw hydrogen flow, respectively, showing a positive relationship with its variation. The results confirm the effectiveness of Machine Learning in the predictive analysis of industrial processes.
Downloads
References
Alharbi, F. y Csala, D. (2022). A Seasonal Autoregressive Integrated Moving Average with Exogenous Factors (SARIMAX) Forecasting Model-Based Time Series Approach. Inventions, 7(4), 94. https://doi.org/10.3390/inventions7040094
Calofir, V., Munteanu, R., Simoiu, M. y Lemnaru, K. (2024). Innovative approach to estimate structural damage using linear regression and K-nearest neighbors machine learning algorithms. Results in Engineering, 22. https://doi.org/10.1016/j.rineng.2024.102250
Chicco, D., Warrens, M. y Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 7, 623. https://doi.org/10.7717/peerj-cs.623
Dubravova, H., Cap, J., Holubova, K. y Hribnak, L. (2024). Artificial Intelligence as an Innovative Element of Support in Policing. Procedia Computer Science, 237, 237-244. https://doi.org/10.1016/j.procs.2024.05.101
Forero-Corba, W. y Negre, F. (2024). Técnicas y aplicaciones del Machine Learning e Inteligencia Artificial en educación: una revisión sistemática. Revista Iberoamericana de Educación a Distancia, 27(1), 209-253. https://doi.org/10.5944/ried.27.1.37491
Gou, J., Sajid, G., Sabri, M., El-Meligy, M., El Hindi, K. y Othman, N. (2024). Optimizing biochar yield and composition prediction with ensemble machine learning models for sustainable production. Ain Shams Engineering Journal, 16. https://doi.org/10.1016/j.asej.2024.103209
Hyndman, R. y Athanasopoulos, G. (2021). Forecasting: principles and practice. (3.ª ed.). OTexts. https://otexts.com/fpp3/
Khodabakhshi, M. y Bijani, M. (2024). Predicting scale deposition in oil reservoirs using machine learning optimization algorithms. Results in Engineering, 22. https://doi.org/10.1016/j.rineng.2024.102263
Kovac, N., Ratkovic, K., Farahani, H. y Watson P. (2024). A practical applications guide to machine learning regression models in psychology with Python. Methods in Psychology, 11. https://doi.org/10.1016/j.metip.2024.100156
Mansi, M., Almobarak, M., Ekundayo, J., Lagat C. y Xie, Q. (2023). Application of supervised machine learning to predict the enhanced gas recovery by CO2 injection in shale gas reservoirs. Petroleum, 10, 124-134. https://doi.org/10.1016/j.petlm.2023.02.003
Ngige, G., Ovuoraye, P., Igwegbec, C., Fetahi, E., Okekec, J., Yakubud, A. y Onyechi, P. (2022). RSM optimization and yield prediction for biodiesel produced from alkali-catalytic transesterification of pawpaw seed extract: Thermodynamics, kinetics, and Multiple Linear Regression analysis. Digital Chemical Engineering, 6. https://doi.org/10.1016/j.dche.2022.100066
Qu, K. (2024). Research on linear regression algorithm. MATEC Web of Conferences, 395. https://doi.org/10.1051/matecconf/202439501046
Shaveta, N. (2023). A review on machine learning. International Journal of Science and Research Archive, 9(1), 281–285. https://doi.org/10.30574/ijsra.2023.9.1.0410
Singh, U., Rizwan, M., Alaraj, M. y Alsaidan, I. (2021). A Machine Learning-Based Gradient Boosting Regression Approach for Wind Power Production Forecasting: A Step towards Smart Grid Environments. Energies, 14(16), 5196. https://doi.org/10.3390/en14165196
Downloads
Published
Issue
Section
License
Copyright (c) 2025 PetroRenova Indexed
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
