基于距离判别分析理论的硫化矿石自燃倾向性等级划分

为建立硫化矿石自燃倾向性等级分类的统一标准，将距离判别分析理论应用到硫化矿石自燃倾向性等级划分的判定当中。结合已有的研究成果，选取最能反映硫化矿石自燃倾向性本质的室内低温氧化增重率、自热点温度、自燃点温度3项指标作为距离判别分析模型的基本判别因子。以15组典型硫化矿山矿样的实测数据作为训练样本进行分析计算，进而建立硫化矿石自燃倾向性等级划分的距离判别分析模型。采用交叉确认方法对判别结果进行了验证，其误判率为零；用所建立的距离判别分析模型对4个待检验矿样的自燃倾向性等级进行了划分，所得结果与矿山的实际情况完全相符。研究结果表明，距离判别分析模型分类性能好，误判率低，可以运用于硫化矿山矿石自燃倾向性等级的分类当中。

Grade classification of spontaneous combustion tendency for sulfide ores based on distance discriminant analysis theory

In order to establish the uniform criteria for assessing spontaneous combustion tendency of sulfide ores，Mahalanobis distance discriminant analysis theory was applied to classify spontaneous combustion tendency grade for sulfide ores.Combining with the existing research productions，three main indexes that most reflect spontaneous combustion tendency of sulfide ores were taken into account to regard as basic discriminant factors of the classification model，including the oxidation increment rate of ore sample under low temperature in laboratory，self heating point temperature，and ignition point temperature.Fifteen groups of measured data of ore samples from several typical sulfide mines were taken as training samples，and a corresponding model of distance discriminant analysis for classifying spontaneous combustion tendency grade of sulfide ores was built.The discriminant results were validated by cross validated method，and the misjudgment ratio was zero.This established model was used to determine spontaneous combustion tendency grade of four sulfide ore samples，and the prediction results were completely consistent with the actual.The research results show that classification model of distance discriminant analysis is excellent，and has high prediction accuracy；this formulated classification method can be usefully applied to evaluate the spontaneous combustion tendency grade of ores in any sulfide mine.