论文部分内容阅读
将随机森林(RF)方法运用到金属矿充填法开采岩层移动角选取问题中。选取影响岩层移动的7个主要因素(开采深度、开采厚度、矿体倾角、矿体上、下盘围岩普氏系数、稳固程度为模型输入,上/下盘岩层移动角为模型输出,在收集35组金属矿山开采岩层移动参数的基础上,利用RF强有力的模式识别功能,建立了充填回采的岩层移动参数预计模型。为提高随机森林模型的准确度和可靠度,采用五折交叉验证方法确定模型参数,并应用该模型预测了三山岛金矿开采岩层移动参数,工程实例验证结果表明,模型选取的因素合理,评估结果与实际结果吻合,为保障矿山安全提供了理论依据。
The random forest (RF) method is applied to the selection of the rock movement angle for metal mining method. The main factors influencing rock movement are mining depth, mining thickness, orebody dip angle, Plankton coefficient of surrounding rock of the ore body, the stability is the model input and the up / down rock formation movement angle is the model output. On the basis of collecting the movement parameters of 35 groups of metal mining rock strata, using the powerful pattern recognition function of RF, the prediction model of rock strata movement parameters was established.In order to improve the accuracy and reliability of stochastic forest model, The model parameters are determined and the model is used to predict the rock movement parameters of Sanshandao Gold Mine. The verification results of engineering examples show that the factors selected by the model are reasonable and the assessment results are in good agreement with the actual results, providing a theoretical basis for mine safety.