检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:何启龙 邬晓光[2] 贺攀[2] 殷悦[2] HE Qi-long;WU Xiao-guang;HE Pan;YIN Yue(China Railway Major Bridge (Nanjing) Bridge and Tunnel Inspect&Retrofit Co. ,LTD. ,Nanjing 210061 ,China;Key Laboratory for Bridge and Tunnel of Shaanxi Province, Chang ~ an University, Xi ' an 710064, China)
机构地区:[1]中铁大桥(南京)桥隧诊治有限公司,南京210061 [2]长安大学桥梁与隧道陕西省重点实验室,西安710064
出 处:《内蒙古大学学报(自然科学版)》2018年第4期431-438,共8页Journal of Inner Mongolia University:Natural Science Edition
基 金:福建省交通运输厅2014年科技计划资助项目(Y-201400006)
摘 要:结合有限元法进行结构可靠度计算时,常采用响应面法和BP神经网络法拟合功能函数的隐式表达式,但这些方法对样本点数量的要求较高,在小样本下的拟合中效果并不理想.因此,结合SVM理论,验证了RBF-SVM法可用于小样本下的功能函数隐式拟合.研究结果表明:采用SVM法拟合的隐式函数,对规范设计值的预测偏小,但其预测误差符合工程精度要求,可以用于小样本下的拼宽桥隐式函数拟合及可靠度计算;拼宽可有效提高旧梁的结构可靠指标并对拼接附近的旧梁可靠指标增加最为有利.For the calculation of structural reliability with the finite element method,response surface and BP neural network method are usually used for the implicit expression of functional functions.But these methods have high requirements for the numbers of sample points,which may be not good for the fitting of little samples.RBF-SVM is proved to be used for the fitting of functional functions under little samples combined SVM theory.The results show that the predicted values by SVM are less than current standard,which prediction error meet the requirements of computational accuracy.It can be applied to the fitting of implicit function and reliability calculation under little samples.The project of widening can effectively increase the reliability index of old beams,and is good for the increase of reliability index for old beams which are near the split joint.
关 键 词:拼宽桥 支持向量 抗弯承载力 钢束二次力 T梁 可靠指标
分 类 号:U448.23[建筑科学—桥梁与隧道工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.249