基于QNM-BP神经网络边坡稳定性评价研究

Study on Slope Stability Evaluation Based on QNM-BP Neural Network

为了对边坡稳定性进行精准评价,选取容重、粘聚力、内摩擦角、边坡角、边坡高度和孔隙压力比为评价指标,77组工程实例为样本数据,采用拟牛顿法优化BP神经网络,建立边坡稳定性的QNM-BP神经网络模型,模型评价准确率达98.70%。将建好的模型应用到夏比公路边坡中进行稳定性评价,评价结果与实际情况一致,得到一种评价准确且应用价值广泛的边坡稳定性评价方法。

In order to accurately evaluate slope stability,bulk density,cohesion,internal friction angle,slope angle,slope height and pore pressure ratio were selected as evaluation indexes,and 77 engineering examples were used as sample data.BP neural network was optimized by using the Quasi-Newton method,and the QNM-BP neural network model of slope stability was established.The model evaluation accuracy reached 98.70%.The established model is applied to the slope stability evaluation of Charpy Road.The evaluation results are consistent with the actual situation,and an accurate and widely used slope stability evaluation method is obtained.