一种基于Kriging法的煤层冲击倾向性分类图

A new empirical chart for coal burst liability classification using Kriging method

冲击地压是一种由多种确定性和不确定性因素共同作用的地质灾害,目前已探索出多种冲击地压灾害预警方法。然而,传统的评价模型或经验方法常面临建模过程复杂和分类准确率低等问题。为此,本文通过147组包含弹性能量指数(Wet)和冲击能量指数(Ke)的煤层冲击倾向性数据,提出了基于Kriging空间插值的冲击地压分类经验模型。该模型中,运用2D分类图展示样本冲击倾向性的空间分布并对其分类边界予以拟合,并用43组测试样本验证了Kriging模型的分类表现。结果表明:Kriging模型的分类准确性为91%,优于其他的不确定性评价模型。本文构建的Kriging模型能为煤矿冲击地压灾害预警和采矿设计提供有力依据。

Coal burst is a catastrophic event that induced by a large variety of certainty and uncertainty factors,and many methods have been proposed to evaluate the risk of this hazard.Conventional evaluation models or empirical criteria are influenced by the complex modelling process or undesirable accuracy.In this study,a total of 147 groups of coal burst records were used to establish the empirical classification model based on elastic energy index(Wet)and impact energy index(Ke).The classification boundaries of coal burst liabilities(CBLs),which was fitted to quantitatively analyze the risk level,and its distribution characteristics are displayed on 2D chart using Kriging method.Additionally,43 groups of test samples were collected to further validate the reliability of the constructed spatial interpolation model.The results revealed that the classification performance of Kriging model outperforms other uncertainty-based method with accuracy 91%.It can be a valuable and helpful tool for designers to conduct the geological hazard prevention and initial design.