基于支持向量机的桁架桥可靠度评估  

Reliability Evaluation of Truss Bridges Using Support Vector Machine

作　　者：陈铁冰[1] 

机构地区：[1]深圳职业技术学院建筑与环境工程学院,广东深圳518055

出　　处：《交通科技与经济》2014年第1期7-11,共5页Technology & Economy in Areas of Communications

基　　金：深圳职业技术学院校级重点科技资助项目(2210K3080015)

摘　　要：针对桁架桥结构极限状态方程一般难以显式表达的特点,提出基于支持向量机的桁架桥可靠度评估方法。通过抽样,采用桁架桥有限元计算,利用支持向量机的非线性映射和泛化能力,建立随机变量与结构响应之间的函数关系,模拟结构极限状态方程,采用优化算法计算桁架桥可靠指标。研究表明:该方法对于评估桁架桥可靠度具有较高的计算精度,但随车辆荷载随机变量的离散性增加,桁架桥的失效概率显著增大。An approach evaluating the reliability of truss bridges using support vector machine （SVM） is proposed in this paper when implicit limit state functions are normally encountered in truss bridges. Random variables such as material properties, physical dimensions and loads are sampled by uniform sampling. The SVM can be trained using a small set of numerical values obtained from the deterministic finite element analysis for truss bridges and sample data mentioned above. The trained SVM can map the structural responses and random variables and the limit state functions of truss bridges can be approximated using SVM. Then the reliability index of truss bridges can be calculated by solving an optimization problem. A numerical example is given. The results show that the accuracy of the proposed approach is validated. The failure probability of truss bridges will significantly increase when the variance of stochastic variable such as vehicular load becomes augmented.

关 键 词：支持向量机 桁架桥 可靠度 隐式极限状态方程 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] U448.27[自动化与计算机技术—控制科学与工程]