Multivariable predictive models for the estimation of power consumption (kW) of a Semi-autogenous mill applying Machine Learning algorithms [Modelos predictivos multivariables para la estimación de consumo de potencia (kW) de un molino Semi - autógeno aplicando algoritmos de Machine Learning]

Miguel Angel Vera Ruiz; Juan Antonio Vega Gonzales; Franklin Jhoan Bailon Villalba

doi:10.32829/eesj.v8i1.207

Authors

Miguel Angel Vera Ruiz Facultad de Ingeniería, Universidad Nacional de Trujillo, Peru https://orcid.org/0009-0004-7154-6139
Juan Antonio Vega Gonzales Facultad de Ingeniería, Universidad Nacional de Trujillo, Peru
Franklin Jhoan Bailon Villalba Facultad de Ingeniería, Universidad Nacional de Trujillo, Peru

DOI:

https://doi.org/10.32829/eesj.v8i1.207

Keywords:

Machine Learning, Semi-autogenous mill, power (kW).

Abstract

This research aimed to develop machine learning (ML) models to estimate power consumption (Kw) in a Semi-autogenous mill in the mining industry. Using Machine Learning algorithms considering various operating variables for the different models such as Multiple Linear Regression (RLM), Decision Tree Regression (RAD), Random Forest Regression (RBA) and Regression Artificial Neural Networks (ANN). The methodology adopted was applied, with an experimental design with a descriptive and transversal approach. The results of the application of these models revealed significant differences in terms of predictive efficiency. The RLM and RRNA stood out with coefficients of determination (R²) of 0.922 and 0.939, respectively, indicating a substantial capacity to explain the variability in power consumption. In contrast, the tree-based models (RAD and RBA) showed inferior performance, with R² of 0.762 and 0.471. When analyzing key metrics such as Mean Absolute Error (MAE), Mean Square Error (MSE) and Root Root Mean Square Error (RMSE), it was confirmed that both RLM and RRNA outperformed the tree-based models. These results support the choice of RLM and RRNA as preferred models for estimating power consumption in a Semi-autogenous mill.

Downloads

Download data is not yet available.

References

Castro P. P., & Valenzuela M. A. (2022). Robust estimation and protection of locked charge in grinding mills. In 2015 IEEE Industry Applications Society Annual Meeting (pp. 1-11). IEEE. DOI: 10.1109/TIA.2017.2654998 DOI: https://doi.org/10.1109/IAS.2015.7356908

Codelco Chile. (2019). MOLIENDA. Codelco Educa. https://www.codelcoeduca.cl/codelcoeduca/site/artic/20190109/asocfile/20190109005343/molienda_media_t__cnico_060119.pdf

Fu, Y., & Aldrich, C. (2020). Deep learning in mining and mineral processing operations: a review. IFAC-PapersOnLine, 53(2), 11920-11925. https://doi.org/10.1016/j.ifacol.2020.12.712 DOI: https://doi.org/10.1016/j.ifacol.2020.12.712

Ghasemi Z., Neumann F., Zanin M., Karageorgos J., & Chen L. (2024). A comparative study of prediction methods for semi-autogenous grinding mill throughput. Minerals Engineering, 205, 108458. https://doi.org/10.1016/j.mineng.2023.108458 DOI: https://doi.org/10.1016/j.mineng.2023.108458

Heredia Tejada H. J. (2016). Simulación y obtención de parámetros óptimos para la optimización de los revestimientos del Molino SAG 36 ft x 26.6 ft de la Minera Constancia–Hudbay. URI http://repositorio.unsa.edu.pe/handle/UNSA/1902

Hoseinzade Z., Mokhtari A. R., & Zekri H. (2023). Clay Minerals Characterization of the Miduk Ball Mill Output through Spectral Analysis. Ore Geology Reviews, 105629. https://doi.org/10.1016/j.oregeorev.2023.105629 DOI: https://doi.org/10.1016/j.oregeorev.2023.105629

Howard J., & Gugger S. (2020). Deep Learning for Coders with fastai and PyTorch. O'Reilly Media

Jayasundara C. T., & Zhu H. P. (2022a). Impact energy of particles in ball mills based on DEM simulations and data-driven approach. Powder Technology, 395, 226-234. https://doi.org/10.1016/j.powtec.2021.09.063 DOI: https://doi.org/10.1016/j.powtec.2021.09.063

Jayasundara C. T., & Zhu H. P. (2022b). Predicting liner wear of ball mills using discrete element method and artificial neural network. Chemical Engineering Research and Design, 182, 438-447. https://doi.org/10.1016/j.cherd.2022.04.013 DOI: https://doi.org/10.1016/j.cherd.2022.04.013

Jooshaki M., Nad A., & Michaux S. (2021). A systematic review on the application of machine learning in exploiting mineralogical data in mining and mineral industry. Minerals, 11(8), 816. https://doi.org/10.3390/min11080816 DOI: https://doi.org/10.3390/min11080816

Jung D., & Choi Y. (2021). Systematic review of machine learning applications in mining: Exploration, exploitation, and reclamation. Minerals, 11(2), 148. https://doi.org/10.3390/min11020148 DOI: https://doi.org/10.3390/min11020148

Khalifa R. M., Yacout S., & Bassetto S. (2021). Developing machine-learning regression model with Logical Analysis of Data (LAD). Computers & Industrial Engineering, 151, 106947. https://doi.org/10.1016/j.cie.2020.106947 DOI: https://doi.org/10.1016/j.cie.2020.106947

Loor Cárdenas V. E. (2020). Aplicación de inteligencia artificial para el agendamiento y optimización del diseño de fases en minería a cielo abierto.

López P., Reyes I., Risso N., Aguilera C., Campos P. G., Momayez M., & Contreras D. (2021). Assessing Machine Learning and Deep Learning-based approaches for SAG mill Energy consumption. In 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON) (pp. 1-6). IEEE. DOI: 10.1109/CHILECON54041.2021.9702951 DOI: https://doi.org/10.1109/CHILECON54041.2021.9702951

Loudari C., Cherkaoui M., Bennani R., Harraki I. E., Younsi Z. E., Adnani M. E., Baina K. (2023). Predicting energy consumption of grinding mills in mining industry: A review. In AIP Conference Proceedings (Vol. 2814, No. 1). AIP Publishing. https://doi.org/10.1063/5.0148768 DOI: https://doi.org/10.1063/5.0148768

Toro L. (2023). Como aplicar el Machine Learnig a la educación. OBS Business School

Murphy K. P. (2022). Machine learning: a probabilistic perspective. MIT press.

Peng J., Sun W., Xu J., Zhou G., Xie L., Han H., Li Q. (2023). Analyzing process parameters for industrial grinding circuit based on machine learning method. Advanced Powder Technology, 34(9), 104113. https://doi.org/10.1016/j.apt.2023.104113 DOI: https://doi.org/10.1016/j.apt.2023.104113

Rosas G. A. A. (2021). Modelamiento y Diseño de un Sistema de Control de las Variables Críticas de un Molino Semiautógeno Mediante un Sistema Experto Basado en Control MPC y Lógica Difusa (Doctoral dissertation, Pontificia Universidad Catolica del Peru (Peru)). URI http://hdl.handle.net/20.500.12404/21199

Salazar J. L., Valdés-González H., Vyhmesiter E., & Cubillos F. (2014). Model predictive control of semiautogenous mills (sag). Minerals Engineering, 64, 92-96. https://doi.org/10.1016/j.mineng.2014.03.029 DOI: https://doi.org/10.1016/j.mineng.2014.03.029

Venkata P., Pandya V., & Sant A. V. (2024). Data Mining and SVM Based Fault Diagnostic Analysis in Modern Power System Using Time and Frequency Series Parameters Calculated From Full-Cycle Moving Window. Journal of Operation and Automation in Power Engineering, 12(3), 206-214. DOI: 10.22098/JOAPE.2023.10819.1789

Wills B. A., & Finch J. (2015). Wills' mineral processing technology: an introduction to the practical aspects of ore treatment and mineral recovery. Butterworth-Heinemann. https://doi.org/10.1016/C2010-0-65478-2 DOI: https://doi.org/10.1016/C2010-0-65478-2

Zou G., Zhou J., Song T., Yang J., Li K. (2023). Hierarchical intelligent control method for mineral particle size based on machine learning. Minerals, 13(9), 1143. https://doi.org/10.3390/min13091143 DOI: https://doi.org/10.3390/min13091143