当前位置: X-MOL 学术Int. J. Numer. Anal. Methods Geomech. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Three-dimensional slope stability predictions using artificial neural networks
International Journal for Numerical and Analytical Methods in Geomechanics ( IF 3.4 ) Pub Date : 2021-06-21 , DOI: 10.1002/nag.3252
Jingjing Meng 1 , Hans Mattsson 1 , Jan Laue 1
Affiliation  

To enable assess slope stability problems efficiently, various machine learning algorithms have been proposed recently. However, these developments are restricted to two-dimensional slope stability analyses (plane strain assumption), although the two-dimensional results can be very conservative. In this study, artificial neural networks are adopted and trained to predict three-dimensional slope stability and a program, SlopeLab has been developed with a graphical user interface. To reduce the number of variables, groups of dimensionless parameters to express stability of slopes in classic stability charts are adopted to construct the neural network architecture. The model has been trained with a dataset from slope stability charts for fully cohesive and cohesive-frictional soils. Furthermore, the impact of concave plan curvature on slope stability that is usually found by excavation in practice is investigated by introducing a dimensionless parameter, relative curvature radius. Slope stability analyses have been conducted with numerical calculations and the artificial neural networks are trained with dimensionless data. The performance of the trained artificial neural networks has been evaluated with the correlation coefficient (R) and root mean square error (RMSE). High accuracy has been found in all the trained models in which > 0.999 and RMSE < 0.15. Most importantly, the proposed program can help engineers to estimate 3D effects of a slope quickly from the ratio of the factors of safety, FS3D/FS2D. When FS3D/FS2D is large (such as larger than 1.2), a 3D numerical modelling on slope stability analyses that can consider complex 3D geometry and boundary condition is advised.

中文翻译:

使用人工神经网络进行三维边坡稳定性预测

为了有效地评估边坡稳定性问题,最近提出了各种机器学习算法。然而,这些发展仅限于二维边坡稳定性分析(平面应变假设),尽管二维结果可能非常保守。在这项研究中,人工神经网络被采用和训练来预测三维边坡稳定性,并开发了一个带有图形用户界面的程序 SlopeLab。为了减少变量的数量,在经典稳定性图中,采用无量纲参数组来表示斜坡稳定性,构建神经网络架构。该模型已经使用来自完全粘性和粘性摩擦土壤的斜坡稳定性图表的数据集进行了训练。此外,通过引入无量纲参数,相对曲率半径,研究了在实践中通常通过开挖发现的凹平面曲率对边坡稳定性的影响。边坡稳定性分析是通过数值计算进行的,人工神经网络是用无量纲数据训练的。训练好的人工神经网络的性能已经用相关系数(R ) 和均方根误差 ( RMSE )。在 > 0.999 和RMSE  < 0.15 的所有训练模型中都发现了高精度。最重要的是,提议的程序可以帮助工程师根据安全系数的比值FS3D/FS2D快速估计斜坡的 3D 效应。当FS3D/FS2D较大(如大于 1.2)时,建议对边坡稳定性分析进行 3D 数值建模,可以考虑复杂的 3D 几何和边界条件。
更新日期:2021-08-13
down
wechat
bug