Previsão de subsidência de minas usando programação de expressão gênica baseada em regressão simbólica multivariável

Autores

DOI:

https://doi.org/10.5935/jetia.v7i29.755

Resumo

A previsão precisa de subsidência de superfície torna-se um desafio significativo para empresas industriais ativas em campos de mineração de carvão devido à importância dos impactos econômicos da subsidência induzida por mineração longwall. Este artigo explora uma nova variante da programação genética, a saber, a programação de expressão gênica (GEP). O método baseado em GEP é utilizado para apresentar uma nova fórmula matemática para previsão de subsidência na mineração de carvão longwall. O modelo derivado inclui variáveis ​​geométricas e geológicas. O conjunto de dados consiste em medições de campo obtidas através de 37 painéis longwall da mina de carvão Ulan, NSW, Austrália. O modelo baseado em GEP concluiu resultados de previsão de subsidência satisfatórios em comparação com outros métodos empíricos, como NCB, DMR, ACARP e IPM. A capacidade preditiva dos modelos baseados no GEP, que captura os efeitos não lineares complexos dos fatores críticos sobre a magnitude da subsidência, resultou em uma melhora estatisticamente significativa na capacidade preditiva em comparação com os métodos empíricos mencionados. Os resultados da análise de sensibilidade indicaram que a largura do painel e a espessura da cobertura com 31% e 23% foram os parâmetros mais influentes no modelo proposto. Além disso, a espessura da emenda extraída, a localização da camada espessa e a espessura da camada espessa tiveram 19%, 16% e 11% de impacto no modelo proposto pelo GEP, respectivamente.

Downloads

Os dados de download ainda não estão disponíveis.

Referências

National Coal Board, “Subsidence engineers handbook”, 2nd edition, Mining Department, London, UK, pp. 04-10, 1975.

L. Holla, “Surface Subsidence Prediction in the Newcastle Coalfield”, Department of Mineral Resources, NSW, Australia, pp. 13-23, 1987.

MAN-001/1, “Summary of the Modified ACARP 2003 Empirical Model”, Ditton Geotechnical Services, NSW, Australia, https://majorprojects.planningportal.nsw.gov.au, pp. 1-152, 2013.

MSEC 309, “The Prediction of Subsidence Parameters of Proposed Austar Longwalls A6 to A17”, Mine Subsidence Engineering Consultants, NSW, Australia, https://majorprojects.planningportal.nsw.gov.au, pp. 21-27, 2008.

M. Hood, R.T. Evy, and L.R. Riddle, “Empirical methods of subsidence prediction, a case study from Illinois”, International Journal of Rock Mechanics, 20 (4), pp. 153-170, 1983.

C. He, J. Xu, “Subsidence prediction of overburden strata and surface based on the Voussoir beam structure”, Advance in Civil Engineering, 1, pp. 1-14, 2018.

Z. Li, J. Xu, “The effects of the rotational speed of voussoir beam structures formed by key strata on the ground pressure of stopes”, International Journal of Rock Mechanics, 108, pp. 67-79,2018.

C. Liu, “Voussoir beam model for lower strong roof strata movement in longwall mining”, J. Rock Mech. Geotech. Eng. 9 (6), pp. 1171–1176, 2018.

C. Ferreira, “Gene expression programming, Mathematical modelling by an artificial intelligence”, vol.21, Springer, United Kingdom, pp. 1-492, 2006.

C. Ferreira, “Gene expression programming: a new adaptive algorithm for solving problems”, Complex Systems, 13(2), pp. 87–129, 2001.

https://www.britannica.com/technology/coal-mining, Last accessed 03/20/2017.

J. Yue, W. Cheng, and L. Fan, “The Study on mathematical model of urban land subsidence based on statistical analysis”, International Conference on Management and Service Science, Wuhan, China, pp. 20–22, September 2009.

G. Yu, W. Mi, D. Wang, L. Gao, and S. Lu, “Research on the relationship between the surface dynamic subsidence and overburden separated strata of coal mine and its model”, Procedia Eng,, 191, pp. 196–205,2017.

B. Wang, J. Xu, and D. Xuan, “Time function model of dynamic surface subsidence assessment of grout-injected overburden of a coal mine”, Int. J. Rock Mech. Min. Sci, 104, pp. 1–8,2018.

H. Li, J. Zha, G. Guo, “A new dynamic prediction method for surface subsidence based on numerical model parameter sensitivity”, J. Clean Prod, 233, pp. 1418–1424, 2019.

P. Tzampoglou, C. Loupasakis, “ Numerical simulation of the factors causing land subsidence due to overexploitation of the aquifer in the Amyntaio open coal mine”, Greece, Hydro Research, 1, pp. 8 –24, 2019.

A. Zingano, A. Weiss, “ Subsidence over room and pillar retreat mining in a low coal seam”, Int. J. Min. Sci. Technol, 29, pp. 51–57, 2019.

Y. Cha, W. Choi, and O. Buyukozturk, “Deep learning-based crack damage detection using convolutional neural networks”, Comput. Aided Civ. Infrastruct. Eng, 32, pp. 361–378, 2017.

M.E. Yetkin, M.K. Ozfirat, “Selection of thick coal seam mining method using analytic hierarchy process”, JETIA, vol. 5, no. 20, pp. 06-11, Dec. 2019.

M. Juszczyk, A. Le’sniak, “Modelling construction site cost index based on neural network ensembles”, Symmetry, 11, pp. 411, 2019.

V. Singh, S. Bano, A.K. Yadav, and S. Ahmad, “Feasibility of artificial neural network in civil engineering”, Int. J. Trend Sci. Res. Dev, 3, pp. 724–728, 2019.

B.S. Narendra, P.V. Sivapullaiah, S. Suresh, and S.N. Omkar, “Prediction of unconfined compressive strength of soft grounds using computational intelligence techniques: a comparative study”, Computers and Geotechnics, Vol. 33, pp. 196-208, 2006.

C. Kayadelen, O. Naydın, M. Fener, A. Demir, and A. Ozvan,“Modeling of the angle of shearing resistance of soils using soft computing systems”, Expert Systems with Applications, Vol. 36, pp. 18- 26, 2009.

M.N. Amar, “Prediction of hydrate formation temperature using gene expression programming”, Journal of Natural Gas Science and Engineering, 87, pp. 24-36, 2021.

I. Azim, J. Yang, M.F. Iqbal, M.F., Z. Mahmood, F. Wang, and Q.F. Liu, “Prediction model for compressive arch action capacity of RC frame structures under column removal scenario using gene expression programming”, Structures, 25, pp. 212-228, 2020.

A. Fathi, M. Mazari, and M. Saghafi, “Multivariate global sensitivity analysis of rocking responses of shallow foundations under controlled rocking”, Eighth International Conference on case histories in geotechnical engineering, Geo- Congress, GSP 307, pp. 490-498, 2019.

T. Hong, K. Jong, and Ch. Koo, “An optimized gene expression programming model for forecasting the national CO2 emissions in 2030 using the metaheuristic algorithms”, Applied Energy, 228, pp. 208-220, 2018.

A.I. Lawal, S. Kwon, O.S. Hammed, and M.A. Idris, “Blast-induced ground vibration prediction in granite quarries: An application of gene expression programming, ANFIS, and sine cosine algorithm optimized ANN”, International Journal of Mining Science and Technology, 31, pp. 265-277, 2021.

H. Majidfar, B. Jahangiri, W.G. Buttlar, and A.H. Alavi, “New machine learning-based prediction models for fracture energy of asphalt mixtures”, Measurement 135, pp. 438–451, 2019.

S.M. Mousavi, P. Aminian, A.H. Gandomi, A.H. Alavi, and H. Bolandi, “A new predictive model for compressive strength of HPC using gene expression programming”, Advances in Engineering Software, 45, pp. 105-114, 2012.

S. Moyano, O. Reyes, H. Fardun, and S. Ventura, “Performing multi-target regression via gene expression programming-based ensemble models”, Neurocomputing, 432, pp. 275-287, 2021.

Y.Z. Murad, R. Hunifat, and W. Al-Bodour, (2020): Interior Reinforced Concrete Beam-to-Column Joints Subjected to Cyclic Loading: Shear Strength Prediction using Gene Expression Programming. Case Studies in Construction Materials, 13, pp. 1-9, 2020.

ULA 3367, “Subsidence assessment of Ulan coal mine”, Strata Control Technology, NSW, Australia, https://www.glencore.com.au/operations-and-projects/coal/current-operations/ulan-coal/reporting-documents, pp. 1-119, 2009.

ULA 3370, “Subsidence assessment, North 1 underground mining area”, Strata Control Technology, NSW, Australia, https://www.glencore.com.au/operations-and-projects/coal/current-operations/ulan-coal/reporting-documents, pp. 3-19, 2009.

ULA, “Analysis of subsidence results from longwall W2, comparison with predictions”, Strata Control Technology, NSW, Australia, https://www.glencore.com.au/operations-and-projects/coal/current-operations/ulan-coal/reporting-documents, pp. 1-92, 2009.

ULA 4510, “2015 annual review of subsidence monitoring at Ulan west mine”, Strata Control Technology, NSW, Australia, https://www.glencore.com.au/operations-and-projects/coal/current-operations/ulan-coal/reporting-documents, pp. 1-33, 2009.

ULN SD PLN 0103, “Ulan West Extraction Plan for longwalls LW1 to LW4”, Ulan Coal GLENCORE, NSW, Australia, https://www.glencore.com.au/operations-and-projects/coal/current-operations/ulan-coal/reporting-documents, pp. 11-29, 2015.

https://www.glencore.com.au/operations-and-projects/coal/current-operations/ulan-coal, NSW, Australia, Last accessed 07/14/2019.

WHT/1, Mine subsidence impact assessment for the proposed longwall panels LWs 1 to 14, No.4 underground area, Moolarben coal project, NSW, Australia, http://www.moolarbencoal.com.au/icms-docs/259060-response-to-submissions-appendices-8-9.pdf, pp. 30-47, September 2006.

Downloads

Publicado

2021-06-30

Edição

Seção

Articles

Como Citar

Previsão de subsidência de minas usando programação de expressão gênica baseada em regressão simbólica multivariável. (2021). ITEGAM-JETIA, 7(29), 13-24. https://doi.org/10.5935/jetia.v7i29.755