论文部分内容阅读
为分析冲击地压发生前的电磁辐射前兆规律,以鹤岗南山矿237工作面“1.12冲击”电磁辐射前兆序列为实例,运用SAS统计分析软件检验序列的随机性和平稳性,建立了适用于该序列的ARMA拟合模型,并预测了序列未来12期的监测值.结果表明,该序列是一个平稳非白噪声序列,可以用AR(3)模型来拟合和预测,模型预测值和真实值的相似程度在66%左右,一致性较高.ARMA模型能够提取电磁辐射序列中的前兆信息,定量描述序列的变化趋势.
In order to analyze the precursory law of electromagnetic radiation before rockburst, taking the example of precursor of “1.12 impact” electromagnetic radiation in 237 Face of Hegang Mine at Nanshan Mine, the randomness and stationarity of the series were tested by SAS statistical analysis software to establish Which is suitable for the ARMA fitting model of the sequence and predicts the monitoring value of the sequence in the future 12. The result shows that the sequence is a stationary non-white noise sequence, which can be fitted and predicted by the AR (3) model, the model predictive value The similarity degree with real value is about 66%, and the consistency is high.ARMA model can extract precursor information in electromagnetic radiation sequence and quantitatively describe the trend of sequence change.