| 基于支持向量机的结构损伤程度识别研究 |
| |
| 引用本文： | 刘龙,孟光.基于支持向量机的结构损伤程度识别研究[J].强度与环境,2005,32(4):12-16. |
| |
| 作者姓名： | 刘龙 孟光 |
| |
| 作者单位： | 上海交通大学振动冲击噪声国家重点实验室,上海,200240 |
| |
| 基金项目： | 国家自然科学基金重点项目(50335030)，航天支撑技术基金项目资助 |
| |
| 摘 要： | 支持向量机(SupportVector Machine,SVM)是一种基于统计学习理论的机器学习算法,能够较好的解决小样本的学习问题,具有很优秀的回归特性。本文提出了一种基于支持向量机辨识结构损伤程度的方法,构造模态频率作为损伤标识量训练支持向量机对损伤程度进行预测,并以悬臂梁为例进行了仿真计算。结果表明:支持向量机是一种很有潜力的结构损伤识别方法,具有很好的应用前景。
|
| 关 键 词： | 损伤识别 支持向量机 模态频率 |
| 文章编号： | 1006-3919（2005）04-0012-05 |
| 收稿时间： | 2004-11-03 |
| 修稿时间： | 2004年11月3日 |
Structure damage severity identification based on support vector machine |
| |
| LIU Long,MENG Guang.Structure damage severity identification based on support vector machine[J].Structure & Environment Engineering,2005,32(4):12-16. |
| |
| Authors: | LIU Long MENG Guang |
| |
| Abstract: | The SVM(Support Vector Machine) is a machine learning algorithm based on statistical learning theory,and it is also a class of regression method with the good generalization ability.The feasibility of applying the SVM to structure damage identification is discussed in this paper.Firstly the SVM regression algorithms are briefly reviewed.Then a method of estimating the severity of the damage using the SVM is investigated: a few modal frequencies are used as inputs to train the SVM,and the damage's severity is predicted.Moreover,a cantilever is analyzed using this method.The results show that the SVM is a powerful method for damage identification. |
| |
| Keywords: | damage identification support vector machine(SVM) modal frequency |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
