Analysis of Weak Links in the Mechanized Mining of Underground Metal Mines: Insights from Machine Learning and SHAP Explainability Models
Source abstract
Abstract
In the mechanized mining of metal mines, identifying and optimizing vulnerabilities within the production system is essential for enhancing operational efficiency and ensuring sustainable development. By leveraging data from 88 stopes at Guangxi Tongkeng Mine over a decade, we constructed a comprehensive dataset encompassing drilling, charging, blasting, ventilation, support, ore drawing, and maintenance. The XGBoost algorithm was employed to model factors influencing stope production capacity (PC), with its parameters optimized using the Marine Predator Algorithm (MPA). The MPA–XGBoost model demonstrates a high predictive accuracy for PC (R2 = 0.958, VAF = 95.981%, MAE = 4.844, RMSE = 7.033). A Shapley Additive Explanations (SHAP) analysis reveals that drilling efficiency (DE) contributes most positively (35.6%), while ventilation time (VT) and equipment maintenance time (EMT) negatively impact PC. SHAP dependence plots indicate that increasing DE significantly enhances PC, whereas excessive VT or EMT leads to a substantial decline in PC. These findings offer valuable insights and a robust foundation for optimizing design and improving production management in mechanized mining operations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Mineral Processing and Grinding · Mining Techniques and Economics · Drilling and Well Engineering
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Resources and Safety Engineering, Central South University, Changsha 410083, China
Funding
Changsha Science and Technology Project · Guangxi Key Research and Development Program · Fundamental Research Funds for the Central Universities of Central South University
References (45)
Show source-provided references
1. Boloz, L., and Bialy, W. (2020). Automation and Robotization of Underground Mining in Poland. Appl. Sci., 10.10.3390/app10207221 ↗
2. Screening ground risk in underground works as part of a predictive modelling approach
3. Augmented Reality Platform for the Unmanned Mining Process in Underground Mines
4. An Underground Mine Risk Identification Model and Safety Management Method Based on Explanation Graph-Probabilistic Multi-Plan Analysis (EG-PMPA)10.1109/ACCESS.2020.3045339 ↗
5. Ghorbani, Y., Nwaila, G.T., Zhang, S.E., Bourdeau, J.E., Cánovas, M., Arzua, J., and Nikadat, N. (2023). Moving towards deep underground mineral resources: Drivers, challenges and potential solutions. Resour. Policy, 80.10.1016/j.resourpol.2022.103222 ↗
6. Underground Lead-Zinc Mine Production Planning Using Fuzzy Stochastic Inventory Policy
7. Hou, J., Li, G.Q., Chen, L.Y., Wang, H., and Hu, N.L. (2023). Optimization of Truck-Loader Matching Based on a Simulation Method for Underground Mines. Sustainability, 15.10.3390/su15010216 ↗
8. A mobile application based on multi-criteria decision-making methods for underground mining method selection10.1080/17480930.2018.1467655 ↗
9. Automated Planning of Underground Mining Operations with Regard to Geological and Geotechnical Constraints10.1134/S106273912303016X ↗
10. Lu, G.Z., Wang, R., Li, Q.S., and Hu, F. (2022). Three-Dimensional Dynamic Visualization Simulation of Underground Mining Engineering considering Chaos Optimization of Symmetric Varieties. Mob. Inf. Syst., 2022.10.1155/2022/2916971 ↗
11. Safe mining operations through technological advancement10.1016/j.psep.2023.05.052 ↗
12. A value adding approach to hard-rock underground mining operations: Balancing orebody orientation and mining direction through meta-heuristic optimization10.1007/s11771-019-4241-1 ↗
13. A review of rock cutting for underground mining: Past, present, and future10.17159/2411-9717/2016/v116n11a3 ↗
14. The importance of people in the process of converting a narrow tabular hard-rock mine to mechanization10.17159/2411-9717/2016/v116n3a8 ↗
15. Yang, C.T., Zhang, R.P., Liu, D.W., Tang, Y., Huang, R.D., and Qiu, W.C. (2023). Evaluation of Excavation Ergonomics of Drill and Blast Method Based on Game Theory G2-EW-TOPSIS Model. Appl. Sci., 13.10.3390/app13127205 ↗
16. Non-explosive mechanized and intelligent mining/heading in underground mine10.1016/S1003-6326(23)66397-6 ↗
17. A new mathematical programming model for production schedule optimization in underground mining operations
18. Sotoudeh, F., Nehring, M., Kizil, M., Knights, P., and Mousavi, A. (2020). Production scheduling optimisation for sublevel stoping mines using mathematical programming: A review of literature and future directions. Resour. Policy, 68.10.1016/j.resourpol.2020.101809 ↗
19. Life-of-mine optimization for integrated open stope development and production scheduling using a mixed-integer linear programming framework
20. A Stochastic Mixed Integer Programming Framework for Underground Mining Production Scheduling Optimization Considering Grade Uncertainty10.1109/ACCESS.2020.2970480 ↗
21. Optimization of the cut-off grade for underground polymetallic mines
22. Artificial intelligence, machine learning and process automation: Existing knowledge frontier and way forward for mining sector10.1007/s10462-020-09841-6 ↗
23. Chimunhu, P., Topal, E., Ajak, A.D., and Asad, W. (2022). A review of machine learning applications for underground mine planning and scheduling. Resour. Policy, 77.10.1016/j.resourpol.2022.102693 ↗
24. Predictive asset availability optimization for underground trucks and loaders in the mining industry10.1007/s12597-020-00502-4 ↗
25. Assessing the viability of underground slate mining by combining an expert system with a GIS10.1016/j.enggeo.2006.06.001 ↗
26. Witulska, J., Stefaniak, P., Jachnik, B., Skoczylas, A., Sliwinski, P., and Dudzik, M. (2021). Recognition of LHD Position and Maneuvers in Underground Mining Excavations-Identification and Parametrization of Turns. Appl. Sci., 11.10.3390/app11136075 ↗
27. Gao, F., Li, X., Xiong, X., Lu, H.C., and Luo, Z.W. (2023). Refined Design and Optimization of Underground Medium and Long Hole Blasting Parameters-A Case Study of the Gaofeng Mine. Mathematics, 11.10.3390/math11071612 ↗
28. Tu, S.Y., Jia, M.T., Wang, L.G., Feng, S.Z., and Huang, S. (2023). A Dynamic Scheduling Model for Underground Metal Mines under Equipment Failure Conditions. Sustainability, 15.10.3390/su15097306 ↗
29. Yu, Z., Li, C.Q., and Zhou, J. (2023). Tunnel Boring Machine Performance Prediction Using Supervised Learning Method and Swarm Intelligence Algorithm. Mathematics, 11.10.3390/math11204237 ↗
30. Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization10.1016/j.undsp.2020.05.008 ↗
31. Hong, Z.X., Tao, M., Liu, L.L., Zhao, M.S., and Wu, C.Q. (2023). An intelligent approach for predicting overbreak in underground blasting operation based on an optimized XGBoost model. Eng. Appl. Artif. Intell., 126.10.1016/j.engappai.2023.107097 ↗
32. Marine Predators Algorithm: A Review10.1007/s11831-023-09912-1 ↗
33. Faramarzi, A., Heidarinejad, M., Mirjalili, S., and Gandomi, A.H. (2020). Marine Predators Algorithm: A Nature-inspired Metaheuristic. Expert Syst. Appl., 152.10.1016/j.eswa.2020.113377 ↗
34. Mugemanyi, S., Qu, Z.Y., Rugema, F.X., Dong, Y.C., Wang, L., Bananeza, C., Nshimiyimana, A., and Mutabazi, E. (2023). Marine predators algorithm: A comprehensive review. Mach. Learn. Appl., 12.10.1016/j.mlwa.2023.100471 ↗
35. Guo, H., Lin, L., Wu, J.L., Lv, Y.C., and Tong, C.S. (2024). Optimizing Driving Parameters of the Jumbo Drill Efficiently with XGBoost-DRWIACO Framework: Applied to Increase the Feed Speed. Sensors, 24.10.3390/s24082600 ↗
36. A New Method of Rockburst Prediction for Categories with Sparse Data Using Improved XGBoost Algorithm10.1007/s11053-024-10412-7 ↗
37. Prediction of mining induced subsidence by sparrow search algorithm with extreme gradient boosting and TOPSIS method10.1007/s11440-023-01830-7 ↗
38. A Combination of Expert-Based System and Advanced Decision-Tree Algorithms to Predict Air-Overpressure Resulting from Quarry Blasting10.1007/s11053-020-09773-6 ↗
39. Zhao, Y.F., Chen, J.H., Yang, S., and Chen, Y. (2022). Mining Plan Optimization of Multi-Metal Underground Mine Based on Adaptive Hybrid Mutation PSO Algorithm. Mathematics, 10.10.3390/math10142418 ↗
40. Wang, H., Zhang, X.X., Yuan, H., Wu, Z.G., and Zhou, M. (2023). A Lean Scheduling Framework for Underground Mines Based on Short Interval Control. Sustainability, 15.10.3390/su15129195 ↗
41. Clustering-based iterative approach to stope layout optimization for sublevel stoping10.17159/2411-9717/1237/2021 ↗
42. Rock Mass Preconditioning Methods in Underground Mines and Ways of Its Evaluation-State-of-the-Art
43. Genetic algorithm to simultaneously optimise stope sequencing and equipment dispatching in underground short-term mine planning under time uncertainty10.1080/17480930.2019.1584952 ↗
44. Pääkkönen, P., Horsmanheimo, S., Pakkala, D., Tuomimäki, L., and Backman, J. (2024). Reference architecture design and evaluation for digitalization of underground mining. Internet Things, 26.10.1016/j.iot.2024.101238 ↗
45. Salinas, J.P., Araujo, J.J.M., and Teatino, M.A.C. (2024). Uncertainty in underground mining operations: A bibliometric and systematic literature review analysis. World J. Eng.10.1108/WJE-07-2024-0388 ↗