| 基于GA与SVM的最危险滑动面识别 |
| |
| 引用本文： | 赵洪波.基于GA与SVM的最危险滑动面识别[J].岩土力学,2006,27(11):2011-2014. |
| |
| 作者姓名： | 赵洪波 |
| |
| 作者单位： | 1.中国科学院岩土力学重点实验室，武汉 430071；2.绍兴文理学院 土木系，绍兴 312000 |
| |
| 基金项目： | 中国科学院重点实验室基金;浙江省高校青年敦师资助计划项目 |
| |
| 摘 要： | 结合支持向量机与遗传算法，提出了一种边坡最危险滑动面识别的新方法。这种方法基于正交设计和极限平衡分析获得学习样本，通过支持向量机学习，从而获得最危险滑动面与安全系数之间的非线性映射关系，再用遗传算法从全局空间上搜索，进行最危险滑动面的识别，并同时获得对应的最小安全系数，该方法计算速度快、效率高。给出了两个算例，结果是令人满意的。
|
| 关 键 词： | 支持向量机 位移反分析 遗传算法 有限元 |
| 文章编号： | 1000-7598-（2006）11-2011-04 |
| 收稿时间： | 2005-06-06 |
| 修稿时间： | 2005-08-25 |
Recognition of critical slip surface based on GA and SVM |
| |
| ZHAO Hong-bo.Recognition of critical slip surface based on GA and SVM[J].Rock and Soil Mechanics,2006,27(11):2011-2014. |
| |
| Authors: | ZHAO Hong-bo |
| |
| Institution: | 1. Key Laboratory of Rock and Soil Mechanics, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China; 2. Department of Civil Engineering, Shaoxing University, Shaoxing 312000, China |
| |
| Abstract: | A new approach to recognize critical slip surface is proposed by combining the support vector machine and genetic algorithm.The learning and testing samples produced in orthogonal experiment are used to train the support vector machine. Thusl the support vector machine is used to describe the relationship between slip surface and factor of safety. Then genetic algorithm is adopted to search critical slip surface in their global ranges. This approach was applied to two examples. The results are satisfactory. |
| |
| Keywords: | slope critical slip surface support vector machine genetic algorithm limit equilibrium analysis |
| 本文献已被 CNKI 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 |
