基于粗糙集和自适应神经网络集成理论的边坡稳定性分析

利用SOM网络--粗糙集-BP网络集成进行边坡稳定性预测的方案:首先应用SOM网络将边坡稳定性因素中的连续属性值离散化;然后基于粗糙集理论计算边坡稳定决策系统的约简,根据实际需要确定最优决策系统;最后在最优决策系统的基础上设计BP网络进行预测.边坡稳定性预测的实际结果验证了所提出的神经网络与粗糙集理论相结合的可行性,在数据充足的条件下,该方案可以推广到其它具有连续性值的情况.

ANALYSIS OF SLOPE STABILITY BASED ON THE THEORY OF ROUGH SETS WITH SELF-ORGANIZING MAP NETWORKS

Considering the ability of rough sets theory of reduction of decision and that of neural networks for clustering and nonlinear mapping, a new hybrid system of rough sets and networks for slope stability analysis is presented:Firstly, the continuous attributes in analysis decision system were discretized with self-organizig map neural network; Then, reducts were found based on rough sets theory, and the optimal diagnostic decision system was determined; Lastly, according to the optimal decision system, BP neural classifier was designed for the slope identity analysis. The slope stability analysis verifies the feasibility of the engineering application. With enough sample data, the solution can be applied to the state with continuous attributes.