矿井涌水量R/S灰色预测模型

R/S grey prediction model for mine discharge

基于矿井涌水量序列具有灰色和分形的特征,建立R/S灰色预测模型,以克服R/S方法无法进行定量预测以及灰色模型对于随机波动大的长时间序列预测效果差的缺点。以成庄煤矿为例,针对2008年1月—2013年12月矿井涌水量进行R/S分析,确定Hurst指数和平均循环周期,并在一个周期内进行灰色预测。结果表明:成庄矿涌水量序列的Hurst指数为0.839,涌水量有持续增加的趋势,其平均循环周期为18个月;与2014年1—4月实测涌水量对比,R/S灰色预测模型的预测精度为92.56%,高于灰色预测模型,为中长期时间序列的矿井涌水量预测提供了更有效的新方法。

Because mine discharge sequence has both fractal and gray characteristics,a R / S gray prediction model was established to overcome shortcomings that R / S method couldn＇t be quantitatively predicted and the prediction effect of gray model was poor for long time series of large random fluctuations. Firstly,mine discharge sequences from January 2008 to December 2013 of Chengzhuang mine were analyzed by using R / S gray prediction model analysis method,followed by the determination of the Hurst exponent and the average cycle.Then gray prediction was conducted in one cycle. The results showed that the Hurst exponent and the average cycle of mine discharge sequences of Chengzhuang mine were 0. 839 and 18 months,respectively. And prediction accuracy of the model was 92. 56% comparsion with the actual discharge from January to April 2014,which was higher than the grey prediction model. The R / S gray prediction model has provided a new approach for the mine discharge forecast of long-term time series.