论文部分内容阅读
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。
In order to improve the prediction accuracy of coal and gas outburst, according to the hypothesis of combined effect of coal and gas outburst, mining depth, gas pressure, initial rate of gas emission, Platts coefficient of coal and type of coal failure are selected as discriminant indexes. By using 20 measured data from typical domestic outburst mines as training samples, a Fisher discriminant analysis model for predicting the degree of danger of coal and gas outburst is established and applied to the prediction of other pending samples. The results show that Fisher discriminant analysis model can reflect the influence of many factors on the coal and gas outburst, the classification performance is good, and the false positive rate is low. With the help of SPSS software, Fisher discriminant analysis model has the characteristics of simple calculation and is an effective method to forecast coal and gas outburst .