论文信息 - A Model Based on SVM for Predicting Spontaneous Combustion of Coal

A Model Based on SVM for Predicting Spontaneous Combustion of Coal

Spontaneous combustion of coal mostly relates to the thickness of minimum float coal. Therefore, a new predictive model for spontaneous combustion of coal is presented based on support vector machines (SVM). Based on the intensity of the wind leak and the temperature of the coal mine measured in the gob of fully mechanized top-coal carving face, a predictive model using support vector machines is established. Then the minimum thickness of the mine layer is predicted using the model, and gotten early warning spontaneous combustion of coal. The practical examples show that the method outperforms the radial basis function networks on both the prediction precision and the generation ability.

Lu Wang | Jingyi Du

[1] Hou Yuan-bin. An RSNN-based Prediction Method for the Coal Mine Spontaneous Combustion , 2004 .

[2] Bernhard Schölkopf,et al. A tutorial on support vector regression , 2004, Stat. Comput..

[3] Bernhard Schölkopf,et al. New Support Vector Algorithms , 2000, Neural Computation.

[4] Chih-Jen Lin,et al. Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel , 2003, Neural Computation.

[5] Francis Eng Hock Tay,et al. Modified support vector machines in financial time series forecasting , 2002, Neurocomputing.

[6] F. Tay,et al. Application of support vector machines in financial time series forecasting , 2001 .

[7] Vladimir Vapnik,et al. Statistical learning theory , 1998 .

[8] Francis Eng Hock Tay,et al. ε-Descending Support Vector Machines for Financial Time Series Forecasting , 2002, Neural Processing Letters.