| 基于概率神经网络的岩土边坡稳定性预测方法 |
| |
| 引用本文： | 李守巨,王吉喆,刘迎曦.基于概率神经网络的岩土边坡稳定性预测方法[J].岩土力学,2006,27(Z2):311-315. |
| |
| 作者姓名： | 李守巨 王吉喆 刘迎曦 |
| |
| 作者单位： | 1.大连理工大学 工业装备结构分析国家重点实验室，大连116024; 2.大连医科大学 附属第二医院,大连116024 |
| |
| 基金项目： | 家自然科学基金资助项目（No.10472025） |
| |
| 摘 要： | 基于数据挖掘技术和智能系统，提出应用概率神经网络预测边坡稳定性的数值方法。根据大量边坡稳定或者失稳案例记录的数据库资料，采用数据挖掘方法能够从中提炼出有价值的分类模式。将岩土边坡的力学参数和几何形状作为神经网络的输入训练和测试神经网络。实际应用显示所建立的概率神经网络预测边坡稳定的实用性。与传统的极限平衡分析方法和极大似然估计方法相对比，所提出的概率神经网络具有更高的预测精度。
|
| 关 键 词： | 边坡稳定分析 概率神经网络 数据挖掘 无导师学习 |
| 收稿时间： | 2006-05-27 |
Application of probabilistic neural networks to slope stability prediction |
| |
| LI Shou-ju,WANG Ji-zhe,LIU Ying-xi.Application of probabilistic neural networks to slope stability prediction[J].Rock and Soil Mechanics,2006,27(Z2):311-315. |
| |
| Authors: | LI Shou-ju WANG Ji-zhe LIU Ying-xi |
| |
| Institution: | 1. State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology, Dalian 116024, China; 2. The second Affiliated Hospital, Dalian Medical University, Dalian 116024, China |
| |
| Abstract: | Probabilistic neural network is applied to facilitate slope stability estimation by making use of data mining technique and intelligent system. Data mining can draw attention to meaningful structures in the archives of such slope stability data. The soil mechanical characteristics and the slope shape with significant influence on slope stability are used to train and test the neural network. Validation is performed to show the efficiency of probabilistic neural network for estimation of slope stability. The simulation results show that probabilistic neural network model generate higher predicting precision than the conventional linear regression, limit equilibrium method and maximum likelihood estimation. |
| |
| Keywords: | slope stability analysis probabilistic neural network data mining non-supervised learning |
|
| 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 |
