基于支持向量机的大跨度拱桥损伤识别方法研究

PDF(1270 KB)

振动与冲击 ›› 2010, Vol. 29 ›› Issue (7) : 174-178.

论文

基于支持向量机的大跨度拱桥损伤识别方法研究

刘春城1,2;刘佼1

作者信息 +

Study on the Damage Identification of Long-span Arch Bridge Based on Support Vector Machine

LIU Chun-cheng1, 2; LIU Jiao1

Author information +

文章历史 +

摘要

作为一种新兴的机器学习算法，支持向量机在损伤识别中已显示出其回归能力的优越性。将模态曲率改变率作为损伤识别特征参数，提出了基于支持向量机的大跨度拱桥损伤识别方法。首先应用模态曲率改变率进行损伤定位识别，然后重新构造训练样本，利用最小二乘支持向量机方法进行大跨度拱桥的损伤程度识别，该方法在较少的样本条件下，取得了非常接近目标值的识别效果。通过与RBF神经网络的训练结果进行对比，验证了本文方法的精确性。

Abstract

As a new machine learning algorithm, the method of Support Vector Machine(SVM) has shown its superiority of the ability of regression in the fields of damage identification. Through setting variation ratio of curvature mode to the feature parameters of damage identification, the method of the damage identification of long-span arch bridge based on SVM is presented. At first, the variation ratio of curvature mode is used to carry on damage location identification, then, the training sample is reconstructed. After that the method of least square support vector machine is used to long-span arch bridge damage extent identification, and the identification results of this method which are very close to target are obtained under the condition of small sample. To compare with results from the RBF neural network, the precision of the method in this paper is verified.

导出引用

刘春城;刘佼. 基于支持向量机的大跨度拱桥损伤识别方法研究[J]. 振动与冲击, 2010, 29(7): 174-178

LIU Chun-cheng;;LIU Jiao. Study on the Damage Identification of Long-span Arch Bridge Based on Support Vector Machine[J]. Journal of Vibration and Shock, 2010, 29(7): 174-178