摘要
以FLAC差分程序作为模拟隧道开挖的正演工具,结合BP神经网络程序,对云岭隧道软弱岩层施工过程中量测的围岩位移进行反分析,确定围岩物理力学参数。将反分析结果代入FLAC程序进行正分析计算,计算位移与实测位移符合很好,证明了基于FLAC的隧道BP神经网络位移反分析的可行性。结果表明,反分析所得围岩物理力学参数改进了原勘测资料中的建议值,对隧道围岩稳定性评价及信息化设计具用实际意义。
With FLAC program as a tool of forward process in the simulation of tunnel excavating and combined with the program of BP Neural networks, a back analysis on the unsteady surrounding rock displacements was carried out and the physical and mechanical parameters of the surrounding rock were determined. The forward analysis was conducted with the application of the back analysis results in FLAC program. It is found that the results agree with each other very well for the calculated and the measured displacements. So, the back analysis is proved to be feasible, which combines with BP Neural networks and FLAC program. The results show that the physical and mechanical parameters gotten through the back analysis can improve on the proposed parameters and the analytical results are important to the stability analysis of the tunnel surrounding rock and to informational design.
出处
《华中科技大学学报（城市科学版）》
CAS
2007年第2期78-80,共3页
Journal of Huazhong University of Science and Technology
