基于支持向量机的煤与瓦斯突出预测研究

煤与瓦斯突出已经成为影响煤矿生产最严重的安全问题和经济问题之一.在国内外有多种用于预测煤与瓦斯突出的方法,包括动态和静态预测,但是这些方法大多只考虑单一的参数,因此它们对煤与瓦斯突出的预测效果并不是很理想.对于近年来应用较为广泛的神经网络,由于其固有的缺陷,对于高维、小样本的情况具有不太理想的预测效果.作者综合考虑了多个因素,并将支持向量机(Support Vector Machine)这一方法应用到煤与瓦斯突出预测中.经过仿真试验,证明这种方法能够取得较好的预测效果.

The Prediction of Coal and Gas Outburst Based on Support Vector Machine

Coal and gas outburst is one of the most serious safe and economic problems in the coal industry.In China and abroad,there are many ways to predict the coal and gas outburst,including dynamic prediction and static prediction.But most of them only consider one parameter,so that the result is not always satisfying.The neural network,because of it's inherent limitationit isn't suitable for the high dimension and the small sample number.In this paper,several parameters are considered together,and the arithmetic Support Vector Machine is used in the prediction.Through simulation test,it is proved that SVM can work efficiently on the coal and gas outburst prediction.