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.

中文翻译：

---

基于神经网络智能系统的飞石有效评估蒙特卡罗模拟方法

露天矿中的一种不良现象是飞石，它对人员和设施造成各种危害。似乎对该主题及其对环境的影响的仔细研究可以影响研究区域飞石危害的控制。因此，使用能够预测和模拟飞石风险的智能模型和方法可以被认为是这方面的合适解决方案。目前的研究是使用非线性模型和蒙特卡罗 (MC) 模拟进行的。本研究中使用的数据包括 260 个从马来西亚矿场抛出的岩石样本。这些模型中使用的参数包括孔的直径 (D)、孔的深度 (HD)、间距负荷 (BS)、堵塞 (ST)、每次延迟的最大电荷 (MC) 和粉末系数 (PF)。首先，多元回归分析 (MRA) 和人工神经网络 (ANN) 模型被用于开发相关参数和独立参数之间的非线性关系。ANN 模型是矿井飞石的合适预测器。然后使用最佳实现的人工神经网络模型，使用MC技术模拟飞石环境现象。MC 模拟显示矿井中飞石范围的准确度水平适当。使用该模拟，可以以 90% 的准确率得出 Flyrock 现象不超过 331 m 的结论。在这些条件下，该模拟可用于需要风险评估的各个领域。最后，对数据进行了敏感分析。该分析表明 MC 对飞石的影响最大。