基于SVM的斜拉桥拉索可靠度分析  

Cable Reliability Analysis of Cable Stayed Bridge Based on Support Vector Machine

作　　者：侍永生 SHI Yongsheng(Hunan Provincial Transportation Science Research Institute Co.,Ltd.,Changsha,Hunan 410015,China)

机构地区：[1]湖南省交通科学研究院有限公司,湖南长沙410015

出　　处：《黑龙江交通科技》2024年第8期82-85,90,共5页Communications Science and Technology Heilongjiang

摘　　要：为解决传统斜拉桥拉索应力可靠度的功能函数难以显式表示的问题,提出了一种基于GWO(灰狼算法)-SVM(支持向量机)的拉索可靠度求解方法。首先阐述了SVM以及GWO基本原理,融合SVM以及GWO的特点,建立了采用GWO-SVM的桥梁结构可靠度求解模型。以海黄大桥为算例,通过选取随机变量并构建斜拉索应力可靠度的功能函数,基于GWO-SVM得到了各斜拉索可靠度,并分析了影响斜拉索应力可靠度的随机变量敏感性,研究表明:斜拉索离主塔越近,其应力可靠度越大;对斜拉索应力可靠度影响最大的随机变量为拉索弹性模型,其次为随机变量汽车荷载,随机变量斜拉索单索面积以及主塔弹性模量均对斜拉索应力可靠度有不同程度的影响;基于灰狼算法优化支持向量机计算得到的各斜拉索应力可靠度指标最大为5.87,最小为3.74,满足规范要求。In order to solve the problem that the functional function of cable stress reliability of traditional cable-stayed bridges is difficult to express explicitly,a method based on GWO(Gray Wolf Optimization algorithm)and SVM(Support Vector Machine)is proposed to solve the cable reliability.First of all,the basic principles of SVM and GWO are described,the characteristics of SVM and GWO are integrated,and the reliability solving model of bridge structure based on GWO-SVM is established.Taking the Haihuang Bridge as an example,the reliability of each cable-stayed cable was obtained by selecting random variables and constructing functional functions of the stress reliability of the cable-stayed cable based on GWO-SVM.The sensitivity of random variables affecting the stress reliability of the cable-stayed cable was analyzed.The research shows that the closer the cable-stayed cable is to the main tower,the greater the stress reliability of the cable-stayed cable is.The elastic modulus of the cable is the random variable that has the greatest influence on the stress reliability of the cable,followed by the random variable automobile load,the area of the cable and the elastic modulus of the main tower have different degrees of influence on the stress reliability of the cable.The maximum stress reliability index of each cable is 5.87 and the minimum is 3.74 based on SVM optimized by GWO algorithm,which meets the specification requirements.

关 键 词：斜拉桥 可靠度 支持向量机 灰狼算法 敏感性分析 

分 类 号：U448.2[建筑科学—桥梁与隧道工程]