The prediction of caving sequence in bord and pillar workings using Random Forest algorithm
DOI:
https://doi.org/10.18311/jmmf/2022/30426Keywords:
Depillaring with caving, grid search, feature selection, local fall, machine learning, main fall, random forest, roof fall riskAbstract
Depillaring of coal seams is of prime importance for coal mining industry in view of depleting superior quality coal reserve and increasing import of foreign coal. Depillaring in conjunction with caving is the most hazardous operation due to sudden roof fall. Some researchers have focused their work on roof fall risk assessment using statistical methods with a view to safety of men and machinery and to minimize accidents, down time and loss of production. Extensive research has not been done to predict roof caving sequence which is the basic requirement for successful caving operation for achieving production with zero harm potential. Roof caving is the result of interactions of all geotechnical and mining parameters including extraction area which is its main cause and contributory parameter. In this research, Random Forest, a supervised ensemble machine learning algorithm along with grid search and cross-validation is used to process the interactions among various parameters and to predict the sequential occurrence of roof caving and characterize the same as local or main fall with considerable and reliable accuracyDownloads
Metrics
Downloads
Published
How to Cite
Issue
Section
Accepted 2022-06-09
Published 2022-06-10
References
Bradley A.E (1997): The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition, 1997, 30(7), 1145–1159.
Breiman L. (2001): Random Forests. Statistics Department University of California Berkeley, CA 94720, Jan,1–33.
Chase F., Mark C and Heasley K. (2002): Deep cover pillar extraction in the U.S. Coalfields. In: Proceedings of the 21st International Conference on Ground Control in Mining. Morgantown, West Virginia University, USA; 2002, 69-80.
Chen R.C., Dewi C., Huang S.W. and Caraka, R.E.(2020): Selecting critical features for data classification based on machine learning methods. J. of Big Data, 2020, 7:52,1– 26. https://doi.org/10.1186/s40537-020-00327-4
DGMS(1993) Cir. (Tech.) Sapicom 3/1993 & 6/1993.
Dixit M and Mishra K. (2010): A unique experience of on shortwall mining in Indian coal mining industry.In:Bose LK, Bhattacharya BC, Ghatak GP, Editors. Proceedings of the Third Asian Mining Congress. Kolkata : MGMI; 2010, 25–37.
Duzgun H.S.B and Einstein H.H. (2004): Assessment and management of roof fall risks in underground coal mines.Safety Science (2004),42,23–41. https://doi.org/ 10.1016/S0925-7535(02)00067-X
Ghasemi E., Ataei M., Shahriar K., Sereshki F and Esmaeil S. (2012): Assessment of roof fall risk during retreat mining in room and pillar coal mines. International Journal of Rock Mechanics and Mining Sciences, 54, 80–89. https:/ /doi.org/10.1016/j.ijrmms. 2012.05.025
Goutte C and Gaussier E (2005): A Probabilistic Interpretation of Precision, Recall and F-score, with Implication for Evaluation. Lect Notes in Comput Sci, 2005, 3408 (April), 345–359.
Gupta R.N and Prajapati R.B. (1997): Improvement of roof control by laterally confined fully grouted bolts. In: Proceedings of the 27th International Conference of Safety in Mines Research Institute, New Delhi., 2 (February, 1997), pp 729-741.
Harshitha P., Dixith H.S., Krithi, Rajeeva N and Shashikala (2020): Coal Mine Disaster Prediction. Int. Journal of Engineering Research & Technology (IJERT), 2020, ISSN: 2278-0181, 9(07), 1447–1451.
Jackins V., Vimal S., Kaliappan M and Lee, M. (2021): AI based smart prediction of clinical disease using random forest classifier and Naive Bayes. The Journal of Supercomputing, 2021, 77(5), 5198–5219. https://doi.org/ 10.1007/s11227-020-03481-x
Maiti J. and Khanzode V.V. (2009): Development of a relative risk model for roof and side fall fatal accidents in underground coal mines in India. Safety Science, 47(8), 1068–1076. https://doi.org/10.1016/j.ssci. 2008.12.003
Mandal P., Singh R., Singh A., Kumar R. and Sinha A (2006): State of art vis-a-vis Indian scenario of application of continuous miner based mass production technology. Journal of Mines Metals and Fuels, 2006, 54(12), 332–336.
Mark C. (2010): Pillar design for deep cover retreat mining: ARMPS version 6 (2010). In: Proceedings of the 29th International Conference on Ground Control in Mining. Morgantown, West Virginia University, USA; 2010., 104–20.
Mark C., Chase F and Pappas D (2003): Reducing the risk of ground falls during pillar recovery. Society of Mining, Metallurgy, and Exploration, Inc., Vol. 314 (January 2003), 153–160.
Mohammadi S., Ataei M., Kakaie R., Mirzaghorbanali A., Rad Z. and Aziz, N. (2020): A roof cavability classification system and its use for estimation of main caving interval in longwall mining. Coal Operators’ Conference, Faculty of Engineering and Information Sciences, University of Wollongong, 2020, 104–115.
Motwani B (2020): Data Analytics using Python (First ed). Wiley India Pvt. Ltd.
Sarantsatsral N., Ganguli R., Pothina R. and Tumen-Ayush B.A.(2021). A Case Study of Rock Type Prediction Using Random Forests:Erdenet Copper Mine, Mongolia. Minerals, 2021, 11 (1059), 1–12.
Singh R., Mandal P.K., Singh A.K., Kumar R and Sinha A. (2011): Coal pillar extraction at deep cover/ : With special reference to Indian coalfields Bay of Bengal. Int. J. of Coal Geology, 2011, 86 (2–3), 276–288. https://doi.org/10.1016/ j.coal. 2011.03.003
Singh R., Mandal P., Singh A., Kumar A and Sinha A. (2008): Optimal underground extraction of coal at shallow cover beneath surface/subsurface objects: Indian practices. Int J Rock Mech Rock Eng. 2008, 41(3), 421– 444.
Singh R., Singh A.K., Maiti J., Mandal P. K., Singh R. and Kumar R.(2011): An observational approach for assessment of dynamic loading during underground coal pillar extraction. International Journal of Rock Mechanics and Mining Sciences, 48(5), 794–804. https:// doi.org/10.1016/j.ijrmms.2011.04.003