神经网络预测矿震危险性

Influence of data on the quality of mine tremors hazard assessment using neural networks

开采冲击危险煤层时,需要对能量大于等于104 J矿震发生的时间和地点进行预测。但目前所预测的结果不能满足现场要求。依据波兰一个长壁工作面的矿震事件,研究了神经网络系统中输入数据类型和形式对矿震预测效果的影响,确定了提高预测效果的方法。实践证明,采用神经网络技术可以对矿震危险性进行预测。

During hard coal mining operations conducted under conditions of rockburst hazard, one of the most important preventive measures can be the prediction of occurrence time and location of the strong seismic mine tremors of energy E≥t 10^4 J. This is a very difficult task and the way it is being performed usually appears to be unsatisfactory. Therefore, attempts have been made to use neutral networks, specifically trained for this application. The paper presents an approach for determining an influence of the type and shape of the input data on the effectiveness of such a prediction. The considerations are based on a selected example of the seismic activity recorded during longwall mining operations conducted in one of the Polish mines.