摘要
边坡工程是一个动态的、模糊的、开放的复杂非线性系统,传统的分析方法有时难以对复杂边坡的稳定性做出符合实际的评价。影响边坡稳定性的因素复杂且具有随机性和模糊性。由于神经网络方法不仅能考虑定量因素,而且能考虑定性因素的影响,因而神经网络方法适用于解决非确定性的边坡稳定性评价问题。综合考虑影响边坡稳定性的各方面因素,建立了基于遗传算法的模糊神经网络模型,并利用大量工程资料对网络进行训练和测试。预测结果表明,该模型的预测精度明显高于目前同类方法。
Slope engineering is a dynamic, fuzzy, open and complicated nonlinear system, which makes it difficult to evaluate complicated slopes conforming to reality by the traditional analysis method. The factors which control and affect slope stability are random and fuzzy variables. As artificial neural network can consider both quantitative and qualitative factors, it is suitable to solve the uncertain problems, such as the estimation of slope stability. In consideration of influencing factors of the slope stability, a fuzzy neural network model based on genetic algorithm is established to predict slope stability, and many engineering data are collected to train and examine the model. Compared with the BP neural network, the presented model has higher predicting accuracy.
出处
《岩土力学》
EI
CAS
CSCD
北大核心
2007年第12期2643-2648,共6页
Rock and Soil Mechanics
基金
国家自然科学研究基金(No.50379046)资助研究项目
关键词
遗传算法
模糊神经网络
边坡稳定性
评价
genetic algorithm
fuzzy neural network
slope stability
evaluation