| 基于K折交叉验证的SVM隧道围岩分级判别 |
| |
| 引用本文： | 汪学清,刘爽,李秋燕,马凯彬.基于K折交叉验证的SVM隧道围岩分级判别[J].矿冶工程,2021,41(6):126-128. |
| |
| 作者姓名： | 汪学清 刘爽 李秋燕 马凯彬 |
| |
| 作者单位： | 1.中国矿业大学(北京) 力学与建筑工程学院，北京 100083;
2.齐齐哈尔大学 建筑与土木工程学院，黑龙江 齐齐哈尔 161006;
3.河南开放大学 建筑工程与智能建造学院，河南 郑州 450000 |
| |
| 基金项目： | 国家重点实验室开放基金(2021-HYSDDYB-001) |
| |
| 摘 要： | 针对隧道施工期间围岩分级因样本数较少存在分类结果可靠性较低的问题，建立基于K折交叉验证的支持向量机判别模型。依据TSP303系统确定判别指标并建立判别指标体系; 根据围岩勘测情况，将围岩分为4个等级，并作为输出变量; 选取40组样本数据训练模型、10组样本数据测试模型，结果表明，10组样本中仅1组样品判别错误，准确率达到90%。研究成果为隧道围岩的分级判别提供了新方法。
|
| 关 键 词： | 隧道围岩 围岩分级 分级判别 K折交叉验证 支持向量机 |
| 收稿时间： | 2021-07-14 |
Classification and Discrimination of Surrounding Rock of Tunnel Based on SVM of K-Fold Cross Validation |
| |
| WANG Xue-qing,LIU Shuang,LI Qiu-yan,MA Kai-bin.Classification and Discrimination of Surrounding Rock of Tunnel Based on SVM of K-Fold Cross Validation[J].Mining and Metallurgical Engineering,2021,41(6):126-128. |
| |
| Authors: | WANG Xue-qing LIU Shuang LI Qiu-yan MA Kai-bin |
| |
| Affiliation: | 1.School of Mechanics & Civil Engineering, China University of Mining & Technology (Beijing), Beijing 100083, China;
2.School of Architecture and Civil Engineering, Qiqihar University, Qiqihar 161006, Heilongjiang, China;
3.School of Building Engineering and Intelligent Construction, Henan Open University, Zhengzhou 450000, Henan, China |
| |
| Abstract: | A small number of samples available during tunnel construction for the surrounding rock classification leads to insufficient reliability of the classification results. Aiming at this problem, a discrimination model with support vector machine was established based on K-fold cross-validation. The discriminant indexes were determined and a discriminant index system was established on the basis of the TSP303 system. According to the survey situation, the surrounding rock is divided into four grades, which were used as the output variables. 40 sample data were chosen to train the model and another 10 sample data were chosen to test the model. It is shown from the results that only one of the 10 samples has discriminant error, indicating an accuracy rate of 90%, which provides a new method for the classification of surrounding rock of tunnel. |
| |
| Keywords: | surrounding rock of tunnel classification of surrounding rock classification and discrimination K-fold cross validation support vector machine (SVM) |
|
| 点击此处可从《矿冶工程》浏览原始摘要信息 |
|
点击此处可从《矿冶工程》下载全文 |
