Machine Learning and Deep Learning Methods in Mining Operations: a Data-Driven SAG Mill Energy Consumption Prediction Application

Abstract

Semi-autogenous grinding mills play a critical role in the processing stage of many mining operations. They are also one of the most intensive energy consumers of the entire process. Current forecasting techniques of energy consumption base their inferences on feeding ore mineralogical features, SAG dimensions, and operational variables. Experts recognize their capabilities to provide adequate guidelines but also their lack of accuracy when real-time forecasting is desired. As an alternative, we propose the use of real-time operational variables (feed tonnage, bearing pressure, and spindle speed) to forecast the upcoming energy consumption via machine learning and deep learning techniques. Several predictive methods were studied: polynomial regression, k-nearest neighbor, support vector machine, multilayer perceptron, long short-term memory, and gated recurrent units. A step-by-step workflow on how to deal with real datasets, and how to find optimum models and final model selection is presented. In particular, recurrent neural networks achieved the best forecasting metrics in the energy consumption prediction task. The workflow has the potential of being extended to any other temporal and multivariate mineral processing datasets.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

References

  1. 1.

    van den Boogaart K, Tolosana-Delgado R (2018) Predictive Geometallurgy: An Interdisciplinary Key Challenge for Mathematical Geosciences. In: Handbook of Mathematical Geosciences pages 673–686 Springer

  2. 2.

    Cherkassky V, Ma Y (2004) Practical selection of SVM parameters and noise estimation for SVM regression. Neural networks 17(1):113–126

    MATH  Article  Google Scholar 

  3. 3.

    Cho K, Van Merriënboer B, Bahdanau D, Bengio Y (2014) On the properties of neural machine translation: Encoder-decoder approaches. arXiv:1409.1259

  4. 4.

    Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555

  5. 5.

    Cochilco (2013) Actualización de Información sobre el Consumo de Energía asociado a la Minería del Cobre al año 2012.Tech. rep.. COCHILCO

  6. 6.

    Cortes C, Vapnik V (1995) Support-vector networks. Machine learning 20(3):273–297

    MATH  Google Scholar 

  7. 7.

    Curilem M, Acuña G, Cubillos F, Vyhmeister E (2011) Neural networks and support vector machine models applied to energy consumption optimization in semiautogeneous grinding. Chemical Engineering Transactions 25:761–766

    Google Scholar 

  8. 8.

    Dey R, Salemt FM (2017) Gate-variants of Gated Recurrent Unit GRU neural networks. In: 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS). IEEE, pp 1597–1600

  9. 9.

    Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, volume 1. MIT press, Cambridge

  10. 10.

    Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B (1998) Support vector machines. IEEE Intelligent Systems and their applications 13(4):18–28

    Article  Google Scholar 

  11. 11.

    Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural computation 9(8):1735–1780

    Article  Google Scholar 

  12. 12.

    Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural networks 2(5):359–366

    MATH  Article  Google Scholar 

  13. 13.

    Hoseinian FS, Abdollahzadeh A, Rezai B (2018) Semi-autogenous mill power prediction by a hybrid neural genetic algorithm. Journal of Central South University 25(1):151–158

    Article  Google Scholar 

  14. 14.

    Hoseinian F , Faradonbeh RS, Abdollahzadeh A, Rezai B, Soltani-Mohammadi S (2017) Semi-autogenous mill power model development using gene expression programming. Powder Technology 308:61–69

    Article  Google Scholar 

  15. 15.

    Inapakurthi RK, Miriyala SS, Mitra K (2020) Recurrent Neural Networks based Modelling of Industrial Grinding Operation. Chemical Engineering Science, 115585

  16. 16.

    Izenman AJ (2008) Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning Springer, 1st edition

  17. 17.

    Jnr WV, Morrell S (1995) The development of a dynamic model for autogenous and semi-autogenous grinding. Minerals Engineering 8(11):1285–1297

    Article  Google Scholar 

  18. 18.

    Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980

  19. 19.

    Morrell S (2004a) A new autogenous and semi-autogenous mill model for scale-up, design and optimisation. Minerals Engineering 17(3):437–445

    Article  Google Scholar 

  20. 20.

    Morrell S (2004b) Predicting the specific energy of autogenous and semi-autogenous mills from small diameter drill core samples. Minerals Engineering 17(3):447–451

    Article  Google Scholar 

  21. 21.

    Navot A, Shpigelman L, Tishby N, Vaadia E (2006) Nearest neighbor based feature selection for regression and its application to neural activity. In: Advances in neural information processing systems, pages 996–1002

  22. 22.

    Ortiz J, Kracht W, Townley B, Lois P, Cardenas E, Miranda R, Alvarez M (2015) Workflows in geometallurgical prediction: challenges and outlook. In: 17th Annual Conference of the International Association for Mathematical Geosciences IAMG

  23. 23.

    Pamparana G, Kracht W, Haas J, Díaz-Ferrán G, Palma-Behnke R, Román R (2017) Integrating photovoltaic solar energy and a battery energy storage system to operate a semi-autogenous grinding mill. Journal of Cleaner Production 165:273–280

    Article  Google Scholar 

  24. 24.

    Ramchoun H, Idrissi MAJ, Ghanou Y, Ettaouil M (2016) Multilayer Perceptron: Architecture Optimization and Training. IJIMAI 4(1):26–30

    Article  Google Scholar 

  25. 25.

    Román-Collado R, Ordoñez M, Mundaca L (2018) Has electricity turned green or black in Chile? A structural decomposition analysis of energy consumption. Energy 162:282–298

    Article  Google Scholar 

  26. 26.

    Rosenblatt F (1961) Principles of neurodynamics, perceptrons and the theory of brain mechanisms (No. VG-1196-G-8). Cornell Aeronautical Lab Inc, Buffalo, NY

    Google Scholar 

  27. 27.

    Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536

    MATH  Article  Google Scholar 

  28. 28.

    Salazar J-L, Valdés-González H, Vyhmesiter E, Cubillos F (2014) Model predictive control of semiautogenous mills sag. Minerals Engineering 64:92–96

    Article  Google Scholar 

  29. 29.

    Silva M, Casali A (2015) Modelling SAG milling power and specific energy consumption including the feed percentage of intermediate size particles. Minerals Engineering 70:156–161

    Article  Google Scholar 

  30. 30.

    Smola AJ, Schö̈lkopf B (2004) A tutorial on support vector regression. Statistics and computing 14 (3):199–222

    MathSciNet  Article  Google Scholar 

  31. 31.

    Van Ooyen A, Nienhuis B (1992) Improving the convergence of the back-propagation algorithm. Neural networks 5(3):465–471

    Article  Google Scholar 

  32. 32.

    Vapnik V (1995) The nature of statistical learning theory. Springer-Verlag, New York

    Google Scholar 

  33. 33.

    Warner B, Misra M (1996) Understanding neural networks as statistical tools. The american statistician 50(4):284–293

    Google Scholar 

  34. 34.

    Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proceedings of the IEEE 78(10):1550–1560

    Article  Google Scholar 

  35. 35.

    Wu Z, King S (2016) Investigating gated recurrent neural networks for speech synthesis. arXiv:1601.02539

Download references

Funding

The authors received funding provided by the Natural Sciences and Engineering Council of Canada (NSERC), funding reference number RGPIN-2017-04200 and RGPAS-2017-507956, and the Chilean National Commission for Scientific and Technological Research (CONICYT), through CONICYT/PIA Project AFB180004, and the CONICYT/FONDAP Project 15110019.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Sebastian Avalos.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Avalos, S., Kracht, W. & Ortiz, J.M. Machine Learning and Deep Learning Methods in Mining Operations: a Data-Driven SAG Mill Energy Consumption Prediction Application. Mining, Metallurgy & Exploration 37, 1197–1212 (2020). https://doi.org/10.1007/s42461-020-00238-1

Download citation

Keywords

  • Energy consumption
  • Semi-autogenous grinding mill
  • Machine learning
  • Deep learning
  • Mining