Fisher判别法在煤与瓦斯突出危险程度预测中的应用

为了提高煤与瓦斯突出的预测精度,根据煤与瓦斯突出的综合作用假说,选取开采深度、瓦斯压力、瓦斯放散初速度、煤的普氏系数以及煤体破坏类型作为判别指标。利用国内典型突出矿井20个实测数据作为训练样本,建立煤与瓦斯突出危险程度预测的Fisher判别分析模型,并应用于其他待判样本的预测。结果表明:Fisher判别分析模型能够反映多因素对煤与瓦斯突出的影响,分类性能良好,误判率低,借助SPSS软件实现,具有计算简单的特点,是煤与瓦斯突出预测的一种有效方法。

The Application of Fisher Discriminant in Predicting Dangerous Level of Coal and Gas Outburst

In order to improve the forecast accuracy of coal and gas outburst dangerous level,according to comprehensive function hypothesis of coal and gas outburst mechanism,and by selecting mining depth,gas pressure,initial speed of methane diffusion,consistent coefficient of coal,and destructive style of coal as the judging indexes,a Fisher discriminant analysis model for predicting coal and gas outburst dangerous level was set up by using the 20 observed measure data from typical outburst mines at home as the training samples.And then it was applied to the forecast of other samples ready for prediction.The demonstration shows that the Fisher discriminant model can reflect the effect of multiple factors on coal and gas outburst,and possesses the characteristic of good classification performance with low rate of mis-discrimination and the advantages of simple computation process by using SPSS.Therefore,it is an efficient method to predict coal and gas outburst.