【摘要】 针对传统经验公式法已不能适应复杂爆破施工环境条件下预报爆破地震动峰值,甚至完全失效的情况,探讨人工神经网络方法在爆破地震动峰值预报中的应用,建立爆破地震动峰值预报人工神经网络模型,并用C语言编制计算程序。在地下隧道爆破地震动强度测试基础上,应用获得爆破测试结果,进行地下隧道爆破地震动峰值速度的人工神经网络预报。通过垂向、水平径向、水平切向爆破地震动峰值速度实测值对人工神经网络进行训练,进而预报爆破地震动峰值速度,并对实测值和预报值进行对比和误差分析。预报值与实测值符合较好,证实人工神经网络能有效预报爆破地震动峰值。更多还原

【Abstract】 In view of the fact that the traditional empirical formula method is badly adaptable to predicting peak values of blasting vibration under complex construction circumstances and conditions,the application of the artificial neural network method in predicting blasting vibration peak values is studied,the artificial neural network model for predicting blasting vibration peak values is established and the correlative computational program is written in the C statements.On the basis of the vibration intensity measurement of an underground tunnel in blasting,the artificial neural network is used for the first time to predict the blasting vibration peak velocities of an underground tunnel.The artificial neural network is trained with the measured values of the vertical,horizontal radial and horizontal tangential blasting vibration peak velocities,then prediction of the blasting vibration peak velocity is achieved.The measured values and predicted values are compared and their errors are analyzed.The results indicate that the predicted values accord with the measured ones and the artificial neural network is reliable in predicting blasting vibration peak velocities.更多还原