煤与瓦斯突出预测的支持向量机(SVM)模型

基于支持向量机(SVM)分类算法,考虑影响煤与瓦斯突出的主要因素,建立了煤与瓦斯突出预测的SVM模型。该模型选取开采深度、瓦斯压力、瓦斯放散初速度、煤的坚固性系数以及地质破坏程度5个指标作为模型输入量,同时将煤与瓦斯突出程度划分为无突出、小型突出、中型突出和大型突出4个等级,进而使其评判结果更为细化。以实测数据作为学习样本进行训练,建立相应判别函数对待判样本进行预测。通过算例分析,表明该模型的方法对煤与瓦斯突出预测的合理性与有效性,可以在实际工程中推广。

Prediction Model for the Outburst of Coal and Gas Based on SVM

Based on the classification algorithm of support vector machine(SVM),model is established according to main factors with important influence on outburst of coal and gas,The factors such as mining depth,gas pressure,liberation initial velocity of gas,firmness coefficient of coal,geological destructiveness are selected as the inputs of the model;the outburst grades are classified as the non-outburst,slight outburst,medium outburst and serious outburst in the evaluating model;so the evaluation results can be more precise. The discrimination functions are obtained through training a large of samples on outburst of coal and gas. The theoretical model is successfully applied to evaluating outburst of coal and gas in practical engineering;and the rationality and effectiveness of this method is demonstrated through examples.