Investigating the Applicability of Stacked Generalization Technique for the Prediction of Hard Rock Pillar Stability Status | ||
| Journal of Mining and Environment | ||
| مقاله 7، دوره 16، شماره 3، مرداد و شهریور 2025، صفحه 907-923 اصل مقاله (1.6 M) | ||
| نوع مقاله: Original Research Paper | ||
| شناسه دیجیتال (DOI): 10.22044/jme.2025.15335.2940 | ||
| نویسندگان | ||
| Festus Kunkyin-Saadaari* ؛ Jude Baah Offei؛ Sadique Ibn Sadique؛ Victor Kwaku Agadzie؛ Ishamel Abeiku Forson | ||
| Faculty of Mining & Minerals Technology, Mining Eng, University of Mines and Technology, Tarkwa, Ghana | ||
| چکیده | ||
| The underground mining operations at the Obuasi Gold Mine rely heavily on the stability of hard rock pillars for safety and productivity. The traditional empirical and numerical methods for predicting pillar stability have limitations, prompting the exploration of advanced machine learning techniques. Hence, this work investigates the applicability of stacked generalisation techniques for predicting the stability status of hard rock pillars in underground mines. Four stacked models were developed, using Gradient Boosting Decision Trees (GBDTs), Random Forest (RF), Extra Trees (ET), and Light Gradient Boosting Machines (LightGBMs), with each model taking turns as the meta-learner, while the remaining three models acted as the base learners in each case. The models were trained and tested on a dataset of 201 pillar cases from the AngloGold Ashanti Obuasi Mine in Ghana. Model performance was evaluated using classification metrics, including accuracy, precision, recall, F1-score and Matthews Correlation Coefficient (MCC). The RF-stacked model demonstrated the best overall performance, achieving an accuracy of 93.44%, precision of 94.27%, recall of 93.44%, F1-score of 93.59%, and MCC of 88.90%. Feature importance analysis revealed pillar depth and pillar stress as the most influential factors affecting pillar stability prediction. The results indicate that stacked generalisation techniques, particularly the RF-stacked model, offer promising capabilities for predicting hard rock pillar stability in underground mining operations. | ||
| کلیدواژهها | ||
| Matthews Correlation Coefficient؛ Hard Rock Pillar؛ Stacked Generalisation؛ Underground Mining؛ Extra Tree | ||
| مراجع | ||
|
[1]. Yu, Y., Deng, K. Z., & Chen, S. E. (2018). Mine size effects on coal pillar stress and their application for partial extraction. Sustainability, 10(3), 792.
[2]. Kadkhodaei, M. H., Ghasemi, E., Zhou, J., & Zahraei, M. (2024). Evaluation of underground hard rock mine pillar stability using gene expression programming and decision tree‐support vector machine models. Deep Underground Science and Engineering, 1, 53-73.
[3]. Wessels, D. G., & Malan, D. F. (2023). A limit equilibrium model to simulate time-dependent pillar scaling in hard rock bord and pillar mines. Rock Mechanics and Rock Engineering, 56(5), pp.3773-3786.
[4]. Martin, C. D., & Maybee, W. G. (2000). The strength of hard-rock pillars. International Journal of Rock Mechanics and Mining Sciences, 37, 1239–1246.
[5]. Bieniawski, Z. T., & Van Heerden, W. L. (1975). The significance of in situ tests on large rock specimens. International Journal of Rock Mechanics and Mining Sciences and Geomechanics Abstracts, 12(4), 101–113.
[6]. York, G. (1998). Numerical modelling of the yielding of a stabilising pillar/foundation system and a new design consideration for stabilising pillar foundations. The Journal of The South African Institute of Mining and Metallurgy, 98(6), 281-298.
[7]. Hustrulid, W. (1976). A review of coal pillar strength formulas. Rock Mechanics, 8, 115–145.
[8]. Hoek, E., & Brown, E. T. (1980). Underground Excavations in Rock. Institution of Mining and Metallurgy, 527.
[9]. Salamon, A., & Munro, M. (1967). A study of the strength of coal pillars. Journal of The South African Institute of Mining and Metallurgy, 68, 55–67.
[10]. Hedley, D. G. F., & Grant, F. (1972). Stope-and-pillar design for the Elliot Lake Uranium Mines. Canadian Institute of Mining, Metallurgy and Petroleum. 74-78.
[11]. Bieniawski, Z. T. (1968). The effect of specimen size on compressive strength of coal. International Journal of Rock Mechanics and Mining Sciences and Geomechanics Abstracts, 5(4), 325–335.
[12]. Zhou, J., Li, X., & Mitri, H.S. (2015). Comparative performance of six supervised learning methods for the development of models of hard rock pillar stability prediction. Natural Hazards, 79(1), 291–316.
[13]. Ahmad, M., Al-Shayea, N.A., Tang, X. W., Jamal, A., M. Al-Ahmadi, H., & Ahmad, F. (2020). Predicting the pillar stability of underground mines with random trees and C4.5 decision trees. Applied Sciences, 10(18), 6486.
[14]. Zhou, J., Chen, Y., Chen, H., Khandelwal, M., Monjezi, M., & Peng, K. (2023). Hybridising five neural-metaheuristic paradigms to predict the pillar stress in bord and pillar method. Frontiers in Public Health, 11, 1119580.
[15]. Li, X., Kim, E., & Walton, G. (2019). A study of rock pillar behaviours in laboratory and in-situ scales using combined finite-discrete element method models. International Journal of Rock Mechanics and Mining Sciences, 118, 21–32.
[16]. Jaiswal, A., Sharma, S. K., & Shrivastva, B. K. (2004). Numerical modelling study of asymmetry in the induced stresses over coal mine pillars with the advancement of the goal line. International Journal of Rock Mechanics and Mining Sciences, 41(5), 859–864.
[17]. Ahmed, S. S., Gunzburger, Y., Renaud, V., & AlHeib, M. (2017). The initialisation of highly heterogeneous virgin stress fields within the numerical modelling of large-scale mines. International Journal of Rock Mechanics and Mining Sciences, 99, 50-62.
[18]. Li, X., Kim, E., & Walton, G. (2019). A study of rock pillar behaviours in laboratory and in-situ scales using combined finite-discrete element method models. International Journal of Rock Mechanics and Mining Sciences, 118, 21-32.
[19]. Li, C., Zhou, J., Armaghani, D. J., & Li, X. (2021). Stability analysis of underground mine hard rock pillars via a combination of finite difference methods, neural networks, and Monte Carlo simulation techniques. Underground Space, 6(4), 379-395.
[20]. Salih, A., & Abdul Hussein, H. (2022). Lost circulation prediction using decision tree, random forest, and extra trees algorithms for an Iraqi oil field. Iraqi Geological Journal, 55(2E), 111–127.
[21]. Nilsson, J. N. (2005). Introduction to machine learning. Department of Computer Science, Stanford University Stanford, CA 94305, 209.
[22]. Tawadrous, A. S., & Katsabanis, P. D. (2007). Prediction of surface crown pillar stability using artificial neural networks. International Journal for Numerical and Analytical Methods in Geomechanics, 31(7), 917–931.
[23]. Ding, H., Li, G., Dong, X., Lin, Y. (2018). Prediction of pillar stability for underground mines using the stochastic gradient boosting technique. IEEE Access: Practical Innovations, Open Solutions, 6, 69253–69264.
[24]. Wolpert, D.H. (1992). Stacked Generalisation. Neural Networks. 5(2), 241-259.
[25]. Breiman, L. (1996). Bagging predictors. Machine learning, 24(2), 123–140.
[26]. Smyth, P., & Wolpert, D. (1997). Stacked Density Estimation. Neural Information Processing Systems, 10, 668–674.
[27]. Li, Q., Wu, Z., Wen, Z., & He, B. (2020). Privacy-preserving gradient boosting decision trees. Proceedings of the AAAI Conference on Artificial Intelligence, 34(1), 784–791.
[28]. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.Y. (2017). LightGBM: A highly efficient Gradient Boosting Decision Tree. Neural Information Processing Systems, 3146–3154.
[29]. Fafalios, S., Charonyktakis, P., Tsamardinos, I. (2020). Gradient Boosting Trees. Gnosis Data Analysis PC. 1, 1–3.
[30]. Liang, W., Luo, S., Zhao, G., & Wu, H. (2020). Predicting hard rock pillar stability using GBDT, XGBoost, and LightGBM algorithms. Mathematics, 8(5), 765.
[31]. Zhang, Z., & Jung, C. (2019). GBDT-MO: Gradient boosted decision trees for multiple outputs. Computer Vision and Pattern Recognition, 32, 3156-3167.
[32]. Eslami, E., Salman, A.K., Choi, Y., Sayeed, A., & Lops, Y. (2020). A data ensemble approach for real-time air quality forecasting using extremely randomised trees and deep neural networks. Neural Computing and Applications, 32(11), 7563–7579.
[33]. Ghazwani, M., & Begum, M.Y. (2023). Computational intelligence modelling of hyoscine drug solubility and solvent density in supercritical processing: gradient boosting, extra trees, and random forest models. Scientific Reports, 13(1), 10046.
[34]. Schonlau, M., & Zou, R.Y. (2020). The random forest algorithm for statistical learning. The Stata Journal, 20(1), 3–29.
[35]. Hastie, T., Tibshirani, R., Friedman, J., & Franklin, J. (2005). The elements of statistical learning: data mining, inference and prediction. The Mathematical Intelligencer, 27(2), 83–85.
[36]. Chen, T., Xu, J., Ying, H., Chen, X., Feng, R., Fang, X., Gao, H., & Wu, J. (2019). Prediction of extubation failure for intensive care unit patients using light gradient boosting machine. IEEE Access: Practical Innovations, Open Solutions, 7, 150960–150968.
[37]. Dietterich, T.G. (2000). Ensemble Methods in Machine Learning. International Workshop on Multiple Classifier Systems, 1–15.
[38]. Freund, Y., & Schapire, R.E. (1997). A decision-theoretic generalisation of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139.
[39]. van der Laan, M., Polley, E., & Hubbard, A. (2008). Super Leaner. UC Berkeley Division of Biostatistics Working Paper Series., 222, 1-20 | ||
|
آمار تعداد مشاهده مقاله: 203 تعداد دریافت فایل اصل مقاله: 208 |
||