基于多方法耦合的矿井突水水源识别模型研究

Identification model of water inrush source based on multi-method coupling

为快速准确地判别矿井突水水源,减少矿井突水事故带来的危害,以保德矿为例,选取Ca^(2+)、Mg^(2+)、Na^(+)+K^(+)、SO_(4)^(2-)、Cl^(-)、HCO_(3)^(-)共6种水化学指标作为判别指标,通过分析各含水层水化学特征,确定了各含水层代表水样,以此为基础建立了耦合主成分分析-离群值检验-回归填补法-贝叶斯判别法的矿井突水水源判别模型,并将模型判别结果与PCA-Bayes模型判别结果做出对比.结果表明:保德矿采空区、二叠系砂岩含水层、石炭系砂岩含水层、奥灰含水层的水质类型分别为HCO_(3)^(-)Ca·Na·Mg型、HCO_(3)^(-)Na型、HCO_(3)-Na型和HCO_(3)·SO_(4)-Ca·Na·Mg型;保德矿水样主成分为Ca^(2+)、Mg^(2+)、Na^(+)+K^(+)、SO_(4)^(2-),可作为综合指标反映保德矿原始水样数据信息;待测水样中的异常值,可通过离群值检验和线性回归模型确定并校正;对比数据校正前后Bayes模型判别结果,校正后准确率为95%,判别准确度明显提升,可准确高效的识别突水水源.

In order to identify the water source of mine water inrush quickly and accurately,and reduce the harm caused by mine water inrush,Baode Mine was taken as an example,Ca^(2+),Mg^(2+),Na^(+)+K^(+),SO_(4)^(2-),Cl^(-),HCO_(3)^(-)were selected as the discrimination indexes.Through analyzing the representative water samples of each aquifer the chemical characteristics of water samples were determined.And then,the coupled Principal Component Analysis(PCA)-Outlier Tests(OT)-RegressionBayes model were used to identify the water source of Baode Mine,and compared with PCA-Bayes model.The results show that:the water quality types of the goaf,Permian sandstone aquifer,Carboniferous sandstone aquifer and Ordovician limestone aquifer in Baode Mine were HCO_(3)^(-)Ca·Na·Mg,HCO_(3)-Na,HCO_(3)^(-)Na,HCO_(3)·SO_(4)-Ca·Na·Mg.The main components of Baode Mine water samples are Ca^(2+),Mg^(2+),Na^(+)+K^(+),SO_(4)^(2-),which can be used as comprehensive indicators to reflect the original water sample data information.The outliers in the tested water samples were determined and corrected by outliers test and regression model.After data correction,the accuracy was significantly improved,and reached 95%.