基于数据挖掘技术的瓦斯涌出量预测方法分析-采矿工程专业论文.docxVIP

内蒙 内蒙古科技大学硕士学位论文 PAGE PAGE IV Abstract Gas disaster is one of the major disasters of the coal mine, which not only caused the great threat to the safety of the staff, but also brought a lot of property damage. It is essential to prevent and control the gas. So, how to predict the gas emission is the important part of that and it would be a large impact of production safety. Therefore, it has great significance to select the best method to predict the gas emission according to the different situations in coal mines. It used the theories and methods of data mining in the paper to forecast the gas emission and analysis the reasons. Also, it used Poly Analyst and MATLAB to build and calculate the model. Correlation analysis and gray relational analysis were used to analyze the gas emission and the impact factors, and it could be known that: ①gas emission was into a positive correlation with the amount of gas content of coal seam, depth, seam thickness, mining intensity and the gas content of the adjacent layers; Gas emission was into a negative correlation with advance speed and the out rate of workface. ②the absolute value of the correlation coefficient with the influencing factors and gas emission was over 0.71, it was significantly related of highly correlated. ③ it could be determined that the influencing factors were the amount of gas content of coal seam, depth, seam thickness, mining intensity and the gas content of the adjacent layers. Poly Analyst support vector was used to predict the gas emission and two parameters of kernel function were selected to predict the test data. It could be know through the results: ①when the polynomial kernel function parameters and the degree of the polynomial was 5, the minimum average relative error was 0.91%. ②when the Gaussian kernel function parameters and the standard deviation was 2.1, the minimum average relative error was 8.59%. By predicting the test data which calculated through the two nuclear functions