|
|||||
|
|
| 高斯过程机器学习在边坡稳定性评价中的应用 | |
| 引用本文： | 苏国韶,宋咏春,燕柳斌.高斯过程机器学习在边坡稳定性评价中的应用[J].岩土力学,2009,30(3):675-679. |
| 作者姓名： | 苏国韶 宋咏春 燕柳斌 |
| 作者单位： | 1. 中国科学院武汉岩土力学研究所,岩土力学与工程国家重点实验室,武汉,430071;广西大学,土木建筑工程学院,南宁,530004 2. 广西大学,机械工程学院,南宁,530004 3. 广西大学,土木建筑工程学院,南宁,530004 |
| 基金项目： | 中国科学院岩土力学重点实验室开放基金，国家自然科学基金 |
| 摘 要： | 针对边坡工程是复杂的非线性系统，采用常规的理论分析和数值计算方法难以满足对边坡稳定性评价的高精度与快速性的要求，为此，提出对处理非线性复杂问题具有很好的适应性一种有概率意义的核学习机——高斯过程机器学习方法来解决边坡稳定性的合理评价问题，建立了相应的边坡稳定性预测模型。工程应用研究结果表明，采用高斯过程机器学习方法进行边坡稳定性评价是科学可行的，该方法能很好地表达边坡稳定性与各影响因素之间的非线性映射关系，能方便快捷地给出合理可靠且具有概率意义的边坡稳定状态评价结果，为实现边坡快速设计的工程实践要求提供了一条新的途径。 |
| 关 键 词： | 岩土力学 边坡稳定 高斯过程 机器学习 |
| 收稿时间： | 2007-07-02 |
Application of Gaussian process machine learning to slope stability evaluation |
|
| SU Guo-shao,SONG Yong-chun,YAN Liu-bin.Application of Gaussian process machine learning to slope stability evaluation[J].Rock and Soil Mechanics,2009,30(3):675-679. | |
| Authors: | SU Guo-shao SONG Yong-chun YAN Liu-bin |
| Institution: | 1. State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China; 2. College of Architecture and Civil Engineering, Guangxi University, Nanning 530004, China; 3. College of Mechanical Engineering, Guangxi University, Nanning 530004, China |
| Abstract: | The results with high precision are hard to achieve rapidly by means of conventional method such as theoretical analysis and numerical calculation; slope engineering is a highly complicated nonlinear system. A new prediction method based on Gaussian process (GP), as a probabilistic kernel leaning machine and a powerful tool for solving highly nonlinear problems, is proposed for slope stability evaluation. The GP model for slope stability evaluation is established and applied to the practical engineering. The results show that the method can find the nonlinear mapping relationship between classifications of slope stability and influencing factors easily. Furthermore, the reasonable, reliable and probabilistic results of slope stability evaluation can be obtained quickly by using the method. In conclusion, the method is feasible, effective and simple to implement slope stability evaluation and to provide a new way for fast design of slope engineering. |
| Keywords: | rock and soil mechanics slope stability Gaussian process machine learning |
| 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 | |