非线性时间序列分析及其在矿井涌水预测中的应用研究

Study of Non-linear Time Series Analysis and Its Use on Mine Water Inrush Prediction

根据梧桐庄煤矿涌水量数据,首先用R/S分析计算得到Hurst指数值为0.8627,表明该矿井涌水量变化趋势具有长期相关性和持续性;然后利用混沌时间序列的全域预测法对历年来的数据进行建模预测分析,计算得到了预测模型以及预测值,结果表明,预测数据和实际值误差较小。利用非线性时间序列分析可以揭示矿井涌水的非线性特征,并对其进行预测,从而为矿井涌水量的预测提供了一种新的方法。

According to the hydraulic discharge of Wutongzhuang coal mine, by using R/S method, the Hurst exponent obtained is 0.8627, it indicates that the mine＇s water inrush discharge variation trend is long-term related as well as durative. Then by using the whole domain method of chaos time serial method to analyze and create a forecast model, the prediction value is calculated. The result shows that the error between the prediction data and the real value is small. The use of non-linear time series analysis can disclose the non-linear characteristics of mine water inrush discharge and predict mine water inrush discharge. Finally, a new method for the prediction of mine water inrush discharge is presented in the paper.