Abstract
In mining, the detection of overload conditions in SAG mills is of great relevance to guarantee their operational continuity due to their economic and environmental impact. Various authors have tried to use Machine Learning techniques to identify the relationship between the variables and the underlying overload phenomenon. Using a combination of techniques integrated into a framework, we seek to establish a model that learns and detects overloads, taking care of aspects such as selecting variables, the generation of an encode that maximizes the learning using a Gram’s matrices approach, and that consider the imbalance of the classes to training a Convolutional Neural Network. Our proposed framework allowed us to establish a mechanism that statistically exceeds the metrics presented by other authors and opens an interesting space of exploration for the continuous improvement of predictive models.
This work was supported in part by Basal Project AFB 1800082.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Apelt, T., Asprey, S., Thornhill, N.: Inferential measurement of sag mill parameters. Miner. Eng. 14(6), 575–591 (2001)
Bardinas, J., Aldrich, C., Napier, L.: Predicting the operating states of grinding circuits by use of recurrence texture analysis of time series data. Processes 6(2), 17 (2018)
Bouchard, J., Desbiens, A., Poulin, E.: Reducing the energy footprint of grinding circuits: the process control paradigm. IFAC-PapersOnLine 50(1), 1163–1168 (2017)
Gamboa, J.C.B.: Deep learning for time-series analysis. arXiv preprint arXiv:1701.01887 (2017)
Hatami, N., Gavet, Y., Debayle, J.: Classification of time-series images using deep convolutional neural networks. In: Tenth International Conference on Machine Vision (ICMV 2017) 10696, 106960Y (2018)
Liang, J., Hou, L., Luan, Z., Huang, W.: Feature selection with conditional mutual information considering feature interaction. Symmetry 11(7), 858 (2019)
McClure, K., Gopaluni, R.: Overload detection in semi-autogenous grinding: a nonlinear process monitoring approach. IFAC-PapersOnLine 48(8), 960–965 (2015)
Ortiz, J.M., Kracht, W., Pamparana, G., Haas, J.: Optimization of a sag mill energy system: integrating rock hardness, solar irradiation, climate change, and demand-side management. Mathematical Geosciences, pp. 1–25 (2019)
Pontt, J., Valderrama, W., Olivares, M., Rojas, F., Robles, H., L’Huissiers, S., Leiva, F.: Uso eficiente de la energia en procesos mineros. Centro de automatizacion para la industria minera, Chile (2012)
Salazar, J.L., Valdés-González, H., Vyhmesiter, E., Cubillos, F.: Model predictive control of semiautogenous mills (sag). Miner. Eng. 64, 92–96 (2014)
Wang, J., Jean, J.: Resolving multifont character confusion with neural networks. Pattern Recogn. 26(1), 175–187 (1993)
Wang, X., Yi, J., Zhou, Z., Yang, C.: Optimal speed control for a semi-autogenous mill based on discrete element method. Processes 8(2), 233 (2020)
Wang, Z., Oates, T.: Imaging time-series to improve classification and imputation. In: Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Hermosilla, R., Valle, C., Allende, H., Lucic, E., Espinoza, P. (2021). Semi-Autogeonous (SAG) Mill Overload Forecasting. In: Tavares, J.M.R.S., Papa, J.P., González Hidalgo, M. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2021. Lecture Notes in Computer Science(), vol 12702. Springer, Cham. https://doi.org/10.1007/978-3-030-93420-0_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-93420-0_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93419-4
Online ISBN: 978-3-030-93420-0
eBook Packages: Computer ScienceComputer Science (R0)