Prediction of Water Inrush Through Coal Floors Based on Data Mining Classification Technique

Based on data mining classification technique, the neural network and the decision tree algorithms were studied to build a prediction system of water inrushes through coal floors. The back propagation neural network and the probabilistic neural network were compared to select features and algorithms. Rules of water inrushes through coal floors were obtained by the C4.5 decision tree and the classification and regression tree. The water inrush prediction system was built using the probabilistic neural network and the classification and regression tree. The result shows a prediction system which based on data mining classification technique is a practical and workable system.