煤炭自燃预测的非参数逐步判别方法及应用

运用在煤矿生成实践中积累的众多相关数据和资料,通过全面分析影响煤层自燃因素,基于非参数逐步判别分析理论,建立煤炭自燃预测的判别分析模型。选取影响煤炭自燃的主要因素如煤的自燃倾向性、煤层厚度、煤层倾角、煤的坚固性系数、工作面供风量、回采工作面推进度、采场回采丢煤率,作为判别因子,建立煤炭自燃预测的非参数逐步判别分析模型,利用某煤田的多个参数作为学习样本进行训练。经过训练后的模型回判的误判率为0。说明该模型在研究煤炭自燃预测中具有良好的实用性和有效性。

Application of nonparametric stepwise discriminant method to forecasting of coal spontaneous combustion

Although a lot of data and materials have been accumulated,coal spontaneous combustion is still a complicated physical-chemical and environmental process to be harnessed.Based on the principle of nonparametric stepwise discriminant analysis,a stepwise discriminant analysis model to predict the possibility of coal spontaneous combustion is established.The main control factors of coal spontaneous combustion,such as coal spontaneous combustion tendency,coal seam thickness,coal bed pitch,the consistent coefficient of distant coal,volume of blast in driving face,recovery rate of coal resources,the rate of coal lost are selected.These several main factors are regarded as the discriminant factors of the stepwise discriminant analysis model.A series of samples are taken as the training and testing samples,and the ratio of mistake-distinguish is zero after the stepwise discriminant analysis model is trained.The results show that the stepwise discriminant analysis model can be used to predict the possibility of coal spontaneous combustion in mining engineering,and the predicting result is reliable and the prediction accuracy is acceptable.