摘要
边坡稳定性涉及到诸多因素,引入人工神经网络预测边坡稳定性的方法———误差逆传播学习算法效果显著。边坡稳定性预测系统的输入信息包括岩土体参数、几何参数等,而输出信息则是网络预测的稳定系数和稳定状态。土质边坡主要以圆弧滑移破坏为主,通过人工神经网络预测的结果与实际监测结果的对比分析,证实了BP神经网络在评价土质边坡稳定性方面的效果显著;并在此基础上分析了土质边坡影响因素对边坡稳定性的影响程度。
Slope stability estimation is an engineering issue that involves several parameters. The effect is remarkable through the use of computational tools called neural networks, one of which is the back- propagation learning algorithm. The input data for slope stability estimation consist of values of geotechnical and geometrical input parameters. As an output, the network estimates the factor of safety （F. S）, or the stability status （S） ; the circular failure take places mainly on soft slope; and the wedge failure take places mainly rock slope. Comparison between actual values of FS and S and the values predicted from ANN, it was demonstrated that the BP is an ideal method for the slope stability estimation; moreover, the influence degree of different parameters was studied in this paper.
出处
《地质灾害与环境保护》
2007年第2期89-93,共5页
Journal of Geological Hazards and Environment Preservation
关键词
人工神经网络
稳定系数
边坡稳定
圆弧滑移破坏
artificial neural networks
factor of safety
slope stability
circular failure
