| 基于SOFM神经网络的边坡稳定性评价 |
| |
| 引用本文： | 薛新华,张我华,刘红军.基于SOFM神经网络的边坡稳定性评价[J].岩土力学,2008,29(8):2236-2240. |
| |
| 作者姓名： | 薛新华 张我华 刘红军 |
| |
| 作者单位： | 1. 浙江大学,软弱土与环境土工教育部重点实验室,杭州,310027
2. 中国海洋大学,环境科学与工程学院,青岛,266003 |
| |
| 摘 要： | 针对边坡工程稳定性分析中参数的不确定性,在分析自组织特征映射神经网络(SOFM)基本学习算法的基础上,从提高算法收敛速度和性能出发,将自组织特征映射神经网络基本学习算法加以改进,据此建立了评价边坡稳定状态的SOFM神经网络模型.然后用收集到的边坡稳定工程实例作为样本,对该模型进行训练和检验,并与BP神经网络判别结果对比.结果表明,SOFM神经网络性能良好、预测精度高,是边坡稳定性评价的一种有效方法.
|
| 关 键 词： | 自组织特征映射 神经网络 边坡稳定 评价 |
| 收稿时间： | 2006-12-08 |
Evaluation of slope stability based on SOFM neural network |
| |
| XUE Xin-hua,ZHANG Wo-hua,LIU Hong-jun.Evaluation of slope stability based on SOFM neural network[J].Rock and Soil Mechanics,2008,29(8):2236-2240. |
| |
| Authors: | XUE Xin-hua ZHANG Wo-hua LIU Hong-jun |
| |
| Institution: | 1. Key Laboratory of Soft Soils and Geoenvironmental Engineering, Ministry of Education, Zhejiang University, Hangzhou 310027, China; 2. Department of Geoenvironmental Engineering, Ocean University of China, Qingdao 266003, China |
| |
| Abstract: | Considering uncertainty of parameter in slope stability analysis, an improved algorithm for self-organizing feature map(SOFM) neural network is presented to increase the convergence speed and capability, and a SOFM neural network model for evaluating the status of the slope stability is established based on the improved algorithm. Then, the SOFM neural network model is trained and checked with the collected slope analyzing examples, and compared with results obtained by the BP neural network. The results show that the SOFM neural network presents excellent network performance, high prediction accuracy; and it is an effective way to evaluate the stability of slopes. |
| |
| Keywords: | self-organization feature map neural network slope stability evaluation |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《岩土力学》浏览原始摘要信息 |
| 点击此处可从《岩土力学》下载免费的PDF全文 |
|
