基于人工神经网络的滑坡稳定性评估研究

Study of Landslide Stability Evaluation Based on Neural Network

由于滑坡组成的地质条件、岩土体物理力学性质、环境因素等具有不确定性、模糊性等特点,要想准确地预测滑坡的稳定性程度是非常困难的。采用人工神经网络方法,对滑坡稳定性评估方法进行了探讨,建立了滑坡稳定性评估指标,并应用实例对该方法进行了验证。结果证明:该方法是一种具有较高分析准确率的方法;避免了其它滑坡稳定性分析计算方法的冗长繁琐,具有重要的工程应用前景。

Because the geological conditions, mechanical properties of rock mass, environmental factors etc., posses uncertainty and fuzzing features, it is very difficult to predict the strength of stability of a landslide correctly. On the basis of the evaluation methods discussed for landslide stability and its evaluation indices established, the artifidal neural network method to evaluate landslide stability was established and the method was verified by an engineering case. The result shows that the artifidal neural network method for evaluating landslide stability is one with high accuracy in analysis, can avoid the redundany of calculation method and has a good prospects of application.