BP神经网络动态预测方法在巷道底板岩爆中的应用

The Application of BP Neural Network Dynamic Prediction Method in Rock Burst of Roadway Floor

针对庞庄矿张小楼井复杂地质条件,首次提出了岩爆关键触发层的概念,采用BP神经网络和FLAC3D数值模拟技术,实现对75215风巷底板岩爆的动态预测,预测结果与现场观测结果一致,验证了该方法的有效性,同时该方法可为75215机巷以及其它巷道的安全快速掘进提供参考。

According to the complicated geological conditions of Zhangxiaolou well in Pangzhuang Coal Mine, the paper creatively puts forward the concept of the rock burst of key trigger layer. By the BP neural network and FLAC3D technology, the dynamic prediction of 75215 airway floor is realized. The prediction results are consistent with the results of field observation, which verifies the validity of the method. This method can provide reference for safe and fast excavation in 75215 machine roadway and other roadways.