Application of Stepwise Discriminant Analysis with Nonparametric Method to Forecasting of Coal Spontaneous Combustion

Coal spontaneous combustion is one of the main engineering geological hazards and is affected by various factors. So it is an important issue to make precise forecast on both the date and the scale of spontaneous combustion in mining engineering. Although a lot of data and materials have been accumulated, coal spontaneous combustion is still an extremely complicated physical-chemical and environmental process to be harnessed. Based on the principle of stepwise discriminant analysis with nonparametric, 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 seam thickness, coal bed pitch, the consistent coefficient of distant coal are regarded as the discriminant factors in the stepwise discriminant analysis model. A series of samples of a coalfield are taken as the training, and testing samples, and the ratio of mistake-distinguish is considerably low 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. A new forecasting method of coal spontaneous combustion is presented.