采用BP神经网络反演隧道围岩力学参数

BACK ANALYSIS ON ROCK MECHANICS PARAMETERS FOR HIGHWAY TUNNEL BY BP NEURAL NETWORK METHOD

采用BP神经网络对公路隧道新奥法施工过程中围岩力学参数的反演分析进行了研究,通过隧道有限元方法得到了网络训练样本。对京珠高速公路坪石隧道围岩力学参数的仿真分析证明了该方法的有效性。

The back analysis is made by means of the BP neural network algorithm on the mechanics parameters of surrounding rock masses in a highway tunnel construction project by NATM. The weight value matrices and tolerance vectors in accordance with input neurons and outputs can be obtained by training a set of specimens,which comes from a FEM analysis for a highway tunnel, the Pingshi Tunnel of the Beijing-Zhuhai expressway. The analogy results of the BP network produce a good agreement with the FEM calculations.