Study on Height Prediction of Water Flowing Fractured Zone in Deep Mines Based on Weka Platform

Accurately predicting the height of water flowing fractured zone is great significance to coal mine safety mining. In recent years, most mines in China have entered deep Aiming at problem that it difficult accurately predict under condition large mining depth, mining, inclined length working face and coefficient hard rock lithology ratio are selected as main influencing factors zone. The relationship between various analyzed by SPSS software. Based on data tool Weka platform, Bayesian classifier, artificial neural network support vector machine model used analyze measured zone, detailed accuracy, confusion matrix node error rate compared. results show that, accuracy instance classification three models greater than 60%. highest lowest. general, training effect best. By engineering examples, prediction reaches 80%, a good obtained. system developed based VB language, which can provide reference for failure grade