A Monte Carlo simulation approach for effective assessment of flyrock based on intelligent system of neural network

• Published in: Engineering with computers Vol. 36; no. 2; pp. 713 - 723
• Main Authors: Zhou, Jian, Aghili, Nasim, Ghaleini, Ebrahim Noroozi, Bui, Dieu Tien, Tahir, M. M., Koopialipoor, Mohammadreza
• Format: Journal Article
• Language: English
• Published: London Springer London 01.04.2020; Springer Nature B.V
• Subjects: Artificial neural networks; CAE) and Design; Calculus of Variations and Optimal Control; Optimization; Classical Mechanics; Computer Science; Computer simulation; Computer-Aided Engineering (CAD; Control; Environmental effects; Hazards; Math. Applications in Chemistry; Mathematical and Computational Engineering; Mathematical models; Monte Carlo simulation; Multiple regression analysis; Neural networks; Original Article; Parameters; Risk assessment; Surface mines; Systems Theory; ANN; Flyrock phenomenon; Sensitivity analysis; Risk assessment; Monte Carlo simulation
• DOI: 10.1007/s00366-019-00726-z
• ISSN: 0177-0667

One of the undesirable phenomena in the surface mines, which results in various hazards for human and facilities, is flyrock. It seems that the careful study of the subject and its effects on the environment can affect the control of flyrock hazards in the studied area. Therefore, the use of intelligent models and methods which are capable of predicting and simulating the risk of flyrock can be considered as an appropriate solution in this regard. The current research was conducted using nonlinear models and Monte Carlo (MC) simulation. The data used in this study consist of 260 samples of rock thrown from a mine in Malaysia. The parameters used in these models include hole’s diameter (D), hole’s depth (HD), burden to spacing (BS), stemming (ST), maximum charge per delay (MC), and powder factor (PF). At first, multiple regression analysis (MRA) and artificial neural network (ANN) models were used in order to develop a non-linear relationship between dependent and independent parameters. The ANN model was an appropriate predictor of flyrock in the mine. Then using the best implemented model of ANN, the flyrock environmental phenomenon was simulated using MC technique. MC simulation showed a proper level of accuracy of flyrock ranges in the mine. Using this simulation, it can be concluded with 90% accuracy that the Flyrock phenomenon does not exceed 331 m. Under these conditions, this simulation can be used for various areas requiring risk assessment. Finally, a sensitive analysis was carried out on data. This analysis showed MC has the greatest effect on flyrock.