基于分形和支持向量机矿井涌水量的预测

Mine water inrush prediction based on fractal and support vector machines

针对矿井涌水量预测问题,提出一种新的非线性预测方法。首先利用分形理论对矿井涌水量的时间序列进行相空间重构,应用自相关系数法确定最小嵌入维数,并以最小嵌入维数作为支持向量机的输入节点,根据支持向量机原理建立矿井涌水量的预测模型。将河南鹤壁四矿1982—1997年的矿井涌水量作为时间序列的训练样本,在Matlab环境下,利用所建立的预测模型预测不同嵌入维数时2000和2001年的矿井涌水量。结果表明:与其他维数相比,当嵌入维数为4时,井筒涌水量的预测值误差最小,预测精度最高。为检验该方法预测的可靠性,分别将不同维数下井筒、巷道和工作面涌水量1988—2001年的预测值与观测值进行对比,发现预测值与观测值较一致。

A new nonlinear method was proposed for predicting the mine water inrush. According to the fractal theory,the phase space of time series obtained from the mine water inrush was reconstructed. And the minimum embedding dimension was determined by autocorrelation coefficient,then the minimum embedding dimension was used for the input node of the support vector machines. The prediction model of time series was established based on the support vector machines. The mine water inrush of the 4th Minein Hebi in the years from 1982 to 1997 were taken as training samples of time series,under the Matlab environment,the mine water inrush in 2000 and 2001 years were forecasted with the established model in different dimensions. The results show that when the embedding dimension is four,the errors of predicted values of shaft water inrush are the minimum,and their precisions are the highest. For testing the prediction reliability of this method,in different dimensions the prediction values were compared with the observed ones of three kinds of water inrush from 1988 to 2001 respectively,it shows that they coincide with each other better.