Predicting open-pit mine production using machine learning techniques

• Autorzy: Kumah Faustin Nartey , Alex Kwasi Saim , Oppong Millicent Nkrumah , Arthur Clement Kweku

Identyfikatory

DOI

10.46873/2300-3960.1411

• Języki publikacji: EN

Abstrakty

EN

In mining, where production is affected by several factors, including equipment availability, it is necessary to develop reliable models to accurately predict mine production to improve operational efficiency. Hence, in this study, four (4) machine learning algorithms - namely: artificial neural network (ANN), random forest (RF), gradient boosting regression (GBR) and decision tree (DT)) - were implemented to predict mine production. Multiple Linear Regression (MLR) analysis was used as a baseline study for comparison purposes. In that regard, one hundred and twenty-six (126) datasets from an open-pit gold mine were used. The developed models were evaluated and compared using the correlation coefficient (R2), mean absolute percentage error (MAPE) and variance accounted for (VAF). It has been shown in this study that the ANN model can best estimate open-pit mine production by comparing its performance to that of the other machine learning models. The R2, MAPE, RMSE and VAF of the models were 0.8003, 0.7486, 0.7519, 0.6538, 0.6044, 4.23%, 5.07%, 5.44%, 6.31%, 6.15% and 79.66%, 74.69%, 74.10%, 65.16% and 60.11% for ANN, RF, GBR, DT and MLR, respectively. Overall, this study has shown that machine learning algorithms predict mine production with higher accuracy.

Słowa kluczowe

EN

mine production; artificial neural network; open-pit mining; mining excavator; machine learning

PL

produkcja górnicza; sztuczna sieć neuronowa; górnictwo odkrywkowe; koparka górnicza; uczenie maszynowe

• Wydawca: Elsevier ; Główny Instytut Górnictwa
• Czasopismo: Journal of Sustainable Mining
• Rocznik: 2024
• Tom: Vol. 23, iss. 2
• Strony: 118--131
• Opis fizyczny: Bibliogr. 61 poz.

Twórcy

autor

Kumah Faustin Nartey

• Department of Mineral Engineering, New Mexico Institute of Mining and Technology, Socorro, NM, USA

• https://orcid.org/0000-0002-3944-5336

autor

Alex Kwasi Saim

• Department of Minerals Engineering, Faculty of Mining and Minerals Technology, University of Mines and Technology, Tarkwa, Western Region, Ghana

• https://orcid.org/0000-0003-0171-7815

autor

Oppong Millicent Nkrumah

• Department of Mining Engineering, School of Mines and Engineering, Montana Technological University, Butte, MT, USA

• https://orcid.org/0000-0002-3243-2284

autor

Arthur Clement Kweku

• Department of Mining Engineering, Faculty of Mining and Minerals Technology, University of Mines and Technology, Tarkwa, Western Region, Ghana

• https://orcid.org/0000-0002-4954-1532

Bibliografia

• [1] Alarie S, Gamache M. Overview of solution strategies used in truck dispatching systems for open pit mines. Int J Surf Min Reclamat Environ 2002. https://doi.org/10.1076/ijsm.16.1.59.3408.
• [2] Arteaga F, Nehring M, Knights P. The equipment utilisation versus mining rate trade-off in open pit mining. Int J Min Reclamat Environ 2018;32:495-518. https://doi.org/10.1080/17480930.2017.1306674.
• [3] Santelices G, Pascual R, Lüer-Villagra A, Mac Cawley A, Galar D. Integrating mining loading and hauling equipment selection and replacement decisions using stochastic linear programming. Int J Min Reclamat Environ 2017;31:52-65. https://doi.org/10.1080/17480930.2015.1115589.
• [4] Edwards DJ, Holt GD, Harris FC. Predicting downtime costs of tracked hydraulic excavators operating in the UK opencast mining industry. Construct Manag Econ 2002;20:581-91. https://doi.org/10.1080/01446190210163552.
• [5] Fisonga M, Mutambo V. Optimization of the fleet per shovel productivity in surface mining: case study of Chilanga Cement, Lusaka Zambia. Cogent Eng 2017;4:1386852. https://doi.org/10.1080/23311916.2017.1386852.
• [6] Ozdemir B, Kumral M. Appraising production targets through agent-based Petri net simulation of material handling systems in open pit mines. Simulat Model Pract Theor 2018. https://doi.org/10.1016/j.simpat.2018.06.008.
• [7] Lanke AA, Hoseinie SH, Ghodrati B. Mine production index (MPI)-extension of OEE for bottleneck detection in mining. Int J Min Sci Technol 2016;26:753-60. https://doi.org/10.1016/j.ijmst.2016.05.050.
• [8] Soofastaei A, Karimpour E, Knights P, Kizil M. Energy-efficient loading and hauling operations. Green Energy Technol 2018:121-46. https://doi.org/10.1007/978-3-319-54199-0_7.
• [9] Kaba FA, Temeng VA, Eshun PA. Application of Discrete event simulation in mine production forecast. Ghana Min J 2016;16:40. https://doi.org/10.4314/gmj.v16i1.5.
• [10] Sehulsoe TC, Musingnini C. Characterizing a mining production system for decision-making purposes in a platinum mine. J South African Inst Min Metall 2017. https://doi.org/10.17159/2411-9717/2017A/117rt2a11.
• [11] Hall RA, Knights PF, Daneshmend LK. Pareto analysis and condition-based maintenance of underground mining equipment. Min Technol 2000;109:14-22. https://doi.org/10.1179/mnt.2000.109.1.14.
• [12] Markeset T, Kumar U. Application of LCC techniques in selection of mining equipment and technology. Mine Plan Equip Sel 2000;2018:635-40. https://doi.org/10.1201/9780203747124-120. Routledge.
• [13] Moradi Afrapoli A, Tabesh M, Askari-Nasab H. A stochastic hybrid simulation-optimization approach towards haul fleet sizing in surface mines. Min Technol 2019;128:9-20. https://doi.org/10.1080/25726668.2018.1473314.
• [14] Manyele SV. Investigation of excavator performance factors in an open-pit mine using loading cycle time. Engineering 2017;9:599-624. https://doi.org/10.4236/eng.2017.97038.
• [15] Mohammadi M, Rai P, Gupta S. Performance evaluation of bucket based excavating, loading and transport (BELT) equipment - an OEE approach. Arch Min Sci 2017;62: 105-20. https://doi.org/10.1515/amsc-2017-0008.
• [16] Arthur CK, Temeng VA, Ziggah YY. Novel approach to predicting blast-induced ground vibration using Gaussian process regression. Eng Comput 2020;36:29-42. https://doi.org/10.1007/s00366-018-0686-3.
• [17] Paneiro G, Rafael M. Artificial neural network with a crossvalidation approach to blast-induced ground vibration propagation modeling. Undergr Sp 2020. https://doi.org/10.1016/j.undsp.2020.03.002.
• [18] Yang H, Hasanipanah M, Tahir MM, Bui DT. Intelligent prediction of blasting-induced ground vibration using ANFIS optimized by GA and PSO. Nat Resour Res 2020;29: 739-50. https://doi.org/10.1007/s11053-019-09515-3.
• [19] Nwaila GT, Zhang SE, Frimmel HE, Manzi MSD, Dohm C, Durrheim RJ, et al. Local and target exploration of conglomerate-hosted gold deposits using machine learning algorithms: a case study of the witwatersrand gold ores, South Africa. Nat Resour Res 2020;29:135-59. https://doi.org/10.1007/s11053-019-09498-1.
• [20] Qi X, Wang H, Pan X, Chu J, Chiam K. Prediction of interfaces of geological formations using the multivariate adaptive regression spline method. Undergr Sp 2020. https://doi.org/10.1016/j.undsp.2020.02.006.
• [21] Avalos S, Kracht W, Ortiz JM. Machine learning and deep learning methods in mining operations: a data-driven SAG mill energy consumption prediction application. Mining, Metall Explor 2020. https://doi.org/10.1007/s42461-020-00238-1.
• [22] Li S, Sari YA, Kumral M. Optimization of miningemineral processing integration using unsupervised machine learning algorithms. Nat Resour Res 2020;29:3035-46. https://doi.org/10.1007/s11053-020-09628-0.
• [23] Wang X, Huang L, Yang P, Yang C, Xie Q. Online estimation of the pH value for froth flotation of bauxite based on adaptive multiple neural Networks**Sponsor and financial support: the national natural science foundation of China (61304126, 61304019) and foundation for innovative research groups. IFAC-PapersOnLine 2016;49:149-54. https://doi.org/10.1016/j.ifacol.2016.10.112.
• [24] Dindarloo SR, Siami-Irdemoosa E. Data mining in mining engineering: results of classification and clustering of shovels failures data. Int J Min Reclamat Environ 2017;31:105-18. https://doi.org/10.1080/17480930.2015.1123599.
• [25] Baek J, Choi Y. Deep neural network for ore production and crusher utilization prediction of truck haulage system in underground mine. Appl Sci 2019. https://doi.org/10.3390/app9194180.
• [26] Baek J, Choi Y. Deep neural network for predicting ore production by truck-haulage systems in open-pit mines. Appl Sci 2020;10:1657. https://doi.org/10.3390/app10051657.
• [27] Choi Y, Nguyen H, Bui X-N, Nguyen-Thoi T, Park S. Estimating ore production in open-pit mines using various machine learning algorithms based on a truck-haulage system and support of internet of things. Nat Resour Res 2021; 30:1141-73. https://doi.org/10.1007/s11053-020-09766-5.
• [28] Edwards DJ, Griffiths IJ. Artificial intelligence approach to calculation of hydraulic excavator cycle time and output. Inst Min Metall Trans Sect A Min Technol 2000. https://doi.org/10.1179/mnt.2000.109.1.23.
• [29] Kassem M, Mahamedi E, Rogage K, Duffy K, Huntingdon J. Measuring and benchmarking the productivity of excavators in infrastructure projects: a deep neural network approach. Autom ConStruct 2021;124:103532. https://doi.org/10.1016/j.autcon.2020.103532.
• [30] Ok SC, Sinha SK. Construction equipment productivity estimation using artificial neural network model. Construct Manag Econ 2006;24:1029-44. https://doi.org/10.1080/01446190600851033.
• [31] Kim Y, Lee SS. Application of artificial neural networks in assessing mining subsidence risk. Appl Sci 2020;10:1302. https://doi.org/10.3390/app10041302.
• [32] da Silva IN, Hernane Spatti D, Andrade Flauzino R, Liboni LHB, dos Reis Alves SF. Artificial neural network architectures and training processes. Artif Neural Networks 2017:21-8. https://doi.org/10.1007/978-3-319-43162-8_2. Cham: Springer International Publishing.
• [33] An Overview and Applications of Artificial Neural Networks n.d. https://www.analyticsvidhya.com/blog/2022/03/an-overview-and-applications-of-artificial-neural-networks-ann/(accessed March 12, 2023).
• [34] Breiman L. Random forests. Mach Learn 2001. https://doi.org/10.1023/A:1010933404324.
• [35] Johnson RW. An introduction to the bootstrap. Teach Stat 2001;23:49-54. https://doi.org/10.1111/1467-9639.00050.
• [36] Guo L, Chehata N, Mallet C, Boukir S. Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests. ISPRS J Photogrammetry Remote Sens 2011. https://doi.org/10.1016/j.isprsjprs.2010.08.007.
• [37] Rodriguez-Galiano V, Sanchez-Castillo M, Chica-Olmo M, Chica-Rivas M. Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geol Rev 2015. https://doi.org/10.1016/j.oregeorev.2015.01.001.
• [38] Mbaabu O. Introduction to random forest in machine learning [internet]. 2020. Retrieved from: https://www.section.io/engineering-education/introduction-to-random-forest-in-machine-learning/.
• [39] Zhang Y, Haghani A. A gradient boosting method to improve travel time prediction. Transport Res C Emerg Technol 2015. https://doi.org/10.1016/j.trc.2015.02.019.
• [40] Pekel E. Estimation of soil moisture using decision tree regression. Theor Appl Climatol 2020;139:1111-9. https://doi.org/10.1007/s00704-019-03048-8.
• [41] Jena M, Dehuri S. Decision tree for classification and regression: a state-of-the art review. Inform 2020. https://doi.org/10.31449/INF.V44I4.3023.
• [42] Bowden GJ, Maier HR, Dandy GC. Optimal division of data for neural network models in water resources applications. Water Resour Res 2002. https://doi.org/10.1029/2001wr000266.
• [43] Mas JF, Flores JJ. The application of artificial neural networks to the analysis of remotely sensed data. Int J Rem Sens 2008; 29:617-63. https://doi.org/10.1080/01431160701352154.
• [44] Hunter JD. Matplotlib: a 2D graphics environment. Comput Sci Eng 2007. https://doi.org/10.1109/MCSE.2007.55.
• [45] McKinney W. Data structures for statistical computing in Python. Proc. 9th Python Sci. Conf. 2010:56-61. https://doi.org/10.25080/Majora-92bf1922-00a.
• [46] 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.
• [47] Moolayil J. Learn Keras for deep neural networks: a fasttrack approach to modern deep learning with Python. 2019.
• [48] Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. TensorFlow: a system for large-scale machine learning. In: Proc. 12th USENIX Symp. Oper. Syst. Des. Implementation, OSDI. 2016; 2016.
• [49] Yu Y, Adu K, Tashi N, Anokye P, Wang X, Ayidzoe MA. RMAF: Relu-Memristor-like activation function for deep learning. IEEE Access 2020;8:72727-41. https://doi.org/10.1109/ACCESS.2020.2987829.
• [50] Kingma DP, Ba J. Adam: a method for stochastic optimization. In: 3rd int conf learn represent ICLR 2015 - conf track proc; 2014.
• [51] Ying X. An overview of overfitting and its solutions. J Phys Conf Ser 2019;1168:022022. https://doi.org/10.1088/1742- 6596/1168/2/022022.
• [52] Ogutu JO, Piepho H-P, Schulz-Streeck T. A comparison of random forests, boosting and support vector machines for genomic selection. BMC Proc 2011;5:S11. https://doi.org/10.1186/1753-6561-5-S3-S11.
• [53] Li Y, Zou C, Berecibar M, Nanini-Maury E, Chan JCW, van den Bossche P, et al. Random forest regression for online capacity estimation of lithium-ion batteries. Appl Energy 2018. https://doi.org/10.1016/j.apenergy.2018.09.182.
• [54] Liu D, Fan Z, Fu Q, Li M, Faiz MA, Ali S, et al. Random forest regression evaluation model of regional flood disaster resilience based on the whale optimization algorithm. J Clean Prod 2020. https://doi.org/10.1016/j.jclepro.2019.119468.
• [55] Gupta D, Hazarika BB, Berlin M. Robust regularized extreme learning machine with asymmetric Huber loss function. Neural Comput Appl 2020;32:12971-98. https://doi.org/10.1007/s00521-020-04741-w.
• [56] Yang S-H, Hu B-G. A stagewise least square loss function for classification. In: Proc. 2008 SIAM int. Conf. Data min. Philadelphia, PA: Society for Industrial and Applied Mathematics; 2008. p. 120-31. https://doi.org/10.1137/1.9781611972788.11.
• [57] San Millan-Castillo R, Morgado E, Goya-Esteban R. On the use of decision tree regression for predicting vibration frequency response of handheld probes. IEEE Sensor J 2020;20: 4120-30. https://doi.org/10.1109/JSEN.2019.2962497.
• [58] Pal M, Mather PM. An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sens Environ 2003. https://doi.org/10.1016/S0034-4257(03)00132-9.
• [59] Park S, Choi Y, Park H-S. Simulation of shovel-truck haulage systems in open-pit mines by considering breakdown of trucks and crusher capacity. J Korean Soc Rock Mech 2014; 24:1-10. https://doi.org/10.7474/TUS.2014.24.1.001.
• [60] Park S, Choi Y, Park H. Optimization of truck-loader haulage systems in an underground mine using simulation methods. Geosystem Eng 2016;19:222-31. https://doi.org/10.1080/12269328.2016.1176538.
• [61] Siami-irdemoosa E, Dindarloo SR. Prediction of fuel consumption of mining dump trucks : a neural networks approach. Appl Energy 2015;151:77-84. https://doi.org/10.1016/j.apenergy.2015.04.064.