首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|资料|样刊邮寄查询|常见问题解答|联系我们
张 研,邝贺伟. 基于主成分分析-相关向量机的高速公路路基沉降量预测[J]. 科学技术与工程, 2020, 20(1): 312-319.
ZHANG Yan,KUANG He-wei.Settlement Prediction of Highway Subgrade Based on Principal Component Analysis-Relevance Vector Machine[J].Science Technology and Engineering,2020,20(1):312-319.
基于主成分分析-相关向量机的高速公路路基沉降量预测
Settlement Prediction of Highway Subgrade Based on Principal Component Analysis-Relevance Vector Machine
投稿时间:2019-05-15  修订日期:2019-09-07
DOI:
中文关键词:  主成分分析  相关向量机  高速公路  路基沉降  预测
英文关键词:principal  component analysis  relevance vector  machine highway  subgrade settlement  prediction
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目)
     
作者单位
张 研 桂林理工大学土木与建筑工程学院
邝贺伟 桂林理工大学土木与建筑工程学院
摘要点击次数: 135
全文下载次数: 34
中文摘要:
      为解决高速公路路基沉降量难以获取的难题,提出一种基于主成分分析(PCA)的相关向量机(RVM)路基沉降量预测方法。通过主成分分析法将多个易获取的土体常规物理参数降维成少数且独立的变量,借助相关向量机模型反映路基沉降量与4个主成分变量之间的非线性映射关系,建立基于PCA-RVM的高速公路路基沉降量预测模型。将该模型应用于工程实例,在同样学习样本情况下与4种神经网络预测模型对比分析,结果表明:PCA-RVM预测模型通过分析各因素的相关性与贡献率,将多个影响因素合理化为少数主成分变量,在信息筛选方面明显优于其余4种模型;各模型预测结果显示,在路基沉降量预测结果的相对误差及均方差方面,PCA-RVM预测模型均占据较大优势。PCA-RVM模型具有精度高、离散性小、可靠度高等优点,为高速公路路基沉降量预测提供了一种新方法。
英文摘要:
      In order to solve the problem that the settlement of highway subgrade is difficult to obtain, a method of predicting the settlement of subgrade was proposed based on principal component analysis (PCA) for relevance vector machine (RVM). The dimension of conventional physical parameters for soil that can be easily obtained was reduced to a few independent variables using PCA method. RVM was used to reflect the nonlinear mapping relationship between the subgrade settlement and the four principal component variables, then the PCA-RVM model for predicting the highway subgrade settlement was established. The proposed model was applied to the engineering project and compared to four neural network prediction models based on the same learning samples. The results show that the PCA-RVM model is superior to the other four models in information screening, because it reasonably reduces many influencing factors to few principal component variables through analyzing the correlation and contribution rate of each factor. The prediction results of each model show that the PCA-RVM model has more advantages for the relative error and mean square error. The PCA-RVM model has the merits of high precision, small dispersion, and high reliability. It provides a new method for predicting the settlement of highway subgrade.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第28151753位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号