| 基于FLAC及神经网络的初始地应力场反演 |
| |
| 引用本文： | 马震岳 金长宇 张运良. 基于FLAC及神经网络的初始地应力场反演[J]. 水电能源科学, 2005, 23(3): 44-45,i005 |
| |
| 作者姓名： | 马震岳 金长宇 张运良 |
| |
| 作者单位： | 大连理工大学,土木水利学院,辽宁,大连,116024 |
| |
| 基金项目： | 国家自然科学基金资助项目(50279003) |
| |
| 摘 要： | 分别采用RBF网络和BP网络，利用FLAC进行正分析计算。依据测点的应力数据反演了计算区域的初始地应力场。结果表明，在样本数量相同的情况下，RBF神经网络反演分析的精度以及学习、收敛速度均优于采用BP网络的反演算法。
|
| 关 键 词： | 初始地应力场 有限差分法 RBF神经网络 反演 |
| 文章编号： | 1000-7709(2005)03-0044-02 |
Back Analysis of Mechanical Parameters and Initial Stress Field of Rock Masses Based on Finite Difference Method and RBF Neural Network |
| |
| MA Zhenyue. Back Analysis of Mechanical Parameters and Initial Stress Field of Rock Masses Based on Finite Difference Method and RBF Neural Network[J]. International Journal Hydroelectric Energy, 2005, 23(3): 44-45,i005 |
| |
| Authors: | MA Zhenyue |
| |
| Abstract: | Using RBF NN and BP NN respectively authors of this paper identified initial stressesaccording to measured normal stresses of some specific points. Direct computations based on Fast LagrangianAna lysisof Continuum (FLAC)wereperformed to get enough trai ning samples for RBF NN and BP NN. An example shows that combination of RBF NN has faster convergence and is more effective than application of BP NN. |
| |
| Keywords: | initial stress field finite difference method RBF NN back analysis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
