ABSTRACT

The assessment of the stope stability is of great importance in the underground mine design process. The instability of stopes leads to serious economic and safety problems in mining operations. This paper aims to assist in the prediction of stope stability by making use of machine learning algorithms. For this purpose, a hybrid grid search-based Artificial Neural Network method is proposed. In the experiments, a total of 215 stope cases which have been collected from six underground mining operations located across Australia are used to prove the validity of the proposed method. Then, the performance of the proposed method is compared with k-nearest neighbour (kNN), naive Bayes (NB), support vector machine (SVM), decision tree (DT) and the stability graph method. Furthermore, several performance measures, such as accuracy, precision, specificity, recall, f-measure, and g-mean are considered during the performance comparison of the methods. The accuracy values are obtained as 91.63%, 81.86%, 77.21%, 76.74%, 73.95%, and 69.77% with the proposed hybrid grid search-based ANN method, SVM, DT, NB, kNN, and the stability graph method, respectively. The empirical results from the experiments indicated that the proposed hybrid approach outperformed the other aforementioned methods, which confirms that the proposed method is a useful tool to predict stope stability.

摘要

采场稳定性评估在地下矿山设计过程中具有重要意义。采场的不稳定性导致采矿作业中严重的经济和安全问题。本文旨在利用机器学习算法协助预测采场稳定性。为此，提出了一种基于混合网格搜索的人工神经网络方法。在实验中，从位于澳大利亚各地的六个地下采矿作业中收集的总共 215 个采场案例被用来证明所提出方法的有效性。然后，将所提出方法的性能与k-最近邻（kNN）、朴素贝叶斯（NB）、支持向量机（SVM）、决策树（DT）和稳定性图方法进行了比较。此外，一些性能指标，如准确度、精密度、特异性、在方法的性能比较过程中考虑了召回率、f-measure 和 g-mean。使用所提出的基于混合网格搜索的 ANN 方法、SVM、DT、NB、kNN 和稳定性图方法分别获得了 91.63%、81.86%、77.21%、76.74%、73.95% 和 69.77% 的准确度值. 实验的实证结果表明，所提出的混合方法优于上述其他方法，这证实所提出的方法是预测采场稳定性的有用工具。