基于GA-BP神经网络在围岩参数反分析中的应用

Study on Back Analysis of Surrounding Rock Parameter Based on GABP Neural Network

针对围岩参数优化反分析较低的计算效率和神经网络初值依赖性问题,研究了基于遗传算法优化BP神经网络的围岩参数反分析,引入位移释放率的概念,根据监测围岩变形量计算围岩真实变形量,对西北地区某隧道进行了围岩参数反分析,结果表明本文方法在围岩参数反演分析方面效率和精度较高,可应用于工程实际.

In order to optimize the problem of back analysis of surrounding rock parameters,such as low computational efficiency and initial value dependency of neural network,the back analysis of surrounding rock parameter based on GA-BP neural network is studied and the concept of displacement release rate is introduced.According to the monitoring of the surrounding rock deformation,the real deformation value is calculated.The method is applied to a tunnel in the northwest region for the back analysis of surrounding rock parameters.The results show that this method has faster speed and higher precision and it can be applied to the practice.