A New Model Based on Artificial Neural Networks and Game Theory for the Selection of Underground Mining Method

被引:7
作者
Ozyurt, M. C. [1 ]
Karadogan, A. [1 ]
机构
[1] Istanbul Univ Cerrahpasa, Dept OfMin Engn, Istanbul, Turkey
关键词
Underground mining; method selection; artificial neural network; game theory; PREDICTION; SUBSIDENCE; SYSTEM; MINE;
D O I
10.1134/S1062739120016491
中图分类号
TD [矿业工程];
学科分类号
0819 ;
摘要
The aim of this study is to investigate the applicability of artificial neural networks (ANN) and game theory in the development of an underground mining method selection model. To realize this, six different ANN models that can evaluate geometric and rock mass properties of an underground mine, environmental factors and ventilation conditions to determine mining methods that satisfy the safety conditions for an underground mine were developed. Among the mining methods determined by ANNs, the optimal mining method was determined by the ultimatum games, in which a compromise between safety and economic conditions was simulated. By using a combination of developed ANN models and ultimatum games, a new model based on artificial neural networks and game theory for the selection of underground mining method was developed. This model can make predictions in the presence of lack of information by following technological developments and new findings obtained in scientific/sectoral studies if learning is continuous. Moreover, the model can evaluate all selection criteria and provide literature-based solutions. In the light of findings obtained within this study, it is revealed that artificial neural networks and game theory can be used in the selection of underground mining methods.
引用
收藏
页码:66 / 78
页数:13
相关论文
共 31 条
[1]   Regularization neural network for construction cost estimation [J].
Adeli, H ;
Wu, MY .
JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT, 1998, 124 (01) :18-24
[2]  
Alpay S, 2007, LECT NOTES ARTIF INT, V4570, P334
[3]   Prediction of subsidence due to underground mining by artificial neural networks [J].
Ambrozic, T ;
Turk, G .
COMPUTERS & GEOSCIENCES, 2003, 29 (05) :627-637
[4]   Design of blasting pattern in proportion to the peak particle velocity (PPV): Artificial neural networks approach [J].
Amnieh, H. Bakhshandeh ;
Siamaki, A. ;
Soltani, S. .
SAFETY SCIENCE, 2012, 50 (09) :1913-1916
[5]  
[Anonymous], 2018, UNDERGROUND IRON MIN
[6]   A new approach to mining method selection based on modifying the Nicholas technique [J].
Azadeh, Amir ;
Osanloo, M. ;
Ataei, M. .
APPLIED SOFT COMPUTING, 2010, 10 (04) :1040-1061
[7]  
Baghirli B, 2015, THESIS
[8]  
BITARAFAN MR, 2004, J S AFR I MIN METALL, P493
[9]  
[程磊 Cheng Lei], 2005, [中国安全科学学报, China Safety Science Journal], V15, P88
[10]  
Gelvez J.I.R., 2014, INT S ANALYTIC HIERA