隧道掘进爆破地震峰值神经网络预报研究

Study on neural network prediction of peak amplitude of blasting ground vibration for tunneling

结合某抽水蓄能电站尾水隧道掘进爆破地面振动监测结果,建立了基于BP神经网络隧道掘进爆破振动速度峰值的预报模型。并对铁路运输安全进行预报,与现场实际较好地吻合。将神经网络模型预报的结果与传统方法(经验公式法)预报的结果相比,前者的预报结果有明显的改善。对于指导隧道掘进爆破设计,优化爆破参数,确保安全具有重要的意义。

Based on monitoring data from Tai’an Pumped-storage Power Station, a BP neural network prediction model of peak amplitude of the tunneling blasting ground vibration is built. The model is applied to predicting railway transportation-safety, and the predicting results coincided with practical results precisely. Comparing the results calculated in empirical formula with the results simulated from BP neural network prediction model, the later results are obviously improved. Then this is of great significance for guiding the blasting design, optimizing the blasting parameters and ensuring the construction safety.