多元回归分析在煤层瓦斯含量预测中的应用

Application of multivariate Regression Analysis in Coal Seam Gas Content Prediction

根据某矿影响煤层瓦斯含量的大量参数值,运用多元回归分析的数学模型,建立了煤层瓦斯含量预测的多元回归方程,并对方程及其系数的显著性作了检验,进行了学生化残差分析。通过此数学模型能够直观地反映煤层埋深、煤层厚度、地质构造、煤的顶底板岩性及煤的变质程度对煤层瓦斯含量的影响关系。结果证明预测的准确性较高,此方法可为矿井预测瓦斯含量提供一种有效途径。

Based on a large number of parameters of coal seam gas content in a mine and by using the mathematical model of multivariate regression analysis, a multivariate regression equation for the prediction of seam gas content was established, the significance of the equation and its coefficient were tested and the studentized residual analysis was carried out. This equation can objectively reflect the influence relation of the buried depth and thickness of coal seams, the geological structure, the roof and floor lithology of the seam and the metamorphic grade of coal with the seam gas content. The results indicated that this method has very high accuracy and can provide an effective way for the prediction of seam gas content in a mine.