In open-pit mines, the blast-induced flyrock is one of the most fundamental problems, therefore, a precision prediction of flyrock can be useful to design a proper blast pattern and reduce the undesirable effects of flyrock. The aim of this study is to develop a new integrated intelligent model to approximate flyrock based on an adaptive neuro-fuzzy inference system (ANFIS) in combination with a grasshopper optimization algorithm (GOA). In addition, a cultural algorithm (CA) is combined with ANFIS to predict flyrock. In the proposed models, the hyperparameters of ANFIS were tuned using CA and GOA. To achieve the objective of this study, a comprehensive database collected from three quarry sites, located in Malaysia, was used. The performance of both ANFIS-CA and ANFIS-GOA models was evaluated by calculation of the statistical functions such as the correlation of determination ( R 2 ). The comparison between the proposed models indicated the higher accuracy of using ANFIS-GOA ( R 2 = 0.974) as an efficient model to predict flyrock compared to the ANFIS-CA ( R 2 = 0.953).

中文翻译：

---

一种基于ANFIS-grasshopper优化算法逼近矿井爆破飞石距离的综合方法

在露天矿中，爆破引发的飞石是最基本的问题之一，因此，对飞石的精确预测有助于设计合适的爆破模式并减少飞石的不良影响。本研究的目的是基于自适应神经模糊推理系统 (ANFIS) 结合蚱蜢优化算法 (GOA)，开发一种新的集成智能模型来近似飞石。此外，文化算法 (CA) 与 ANFIS 相结合来预测飞石。在提出的模型中，ANFIS 的超参数使用 CA 和 GOA 进行了调整。为实现本研究的目标，使用了从位于马来西亚的三个采石场收集的综合数据库。ANFIS-CA 和 ANFIS-GOA 模型的性能都通过统计函数的计算来评估，例如确定的相关性 (R 2 )。所提出的模型之间的比较表明，与 ANFIS-CA (R 2 = 0.953) 相比，使用 ANFIS-GOA (R 2 = 0.974) 作为预测飞岩的有效模型具有更高的准确性。