支持向量回归算法在梁结构损伤诊断中的应用研究

STUDY ON DAMAGE DIAGNOSIS OF BEAM-LIKE STRUCTURES BY SUPPORT VECTOR REGRESSION

支持向量机算法具有很优秀的回归特性,所以将其应用于梁结构的损伤诊断方面。以模态频率作为特征参数,训练支持向量机实现对损伤的定位和程度标识,并通过对悬臂梁的损伤识别仿真计算进行了验证。结果表明:支持向量机在结构损伤诊断领域中具有很好的应用前景。

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 generaliztion ability.This paper introduces the support vector regression,which isapplied to the structure damage monitoring.Damage features formed by vibration modal frequencies are used as characteristic parameters to train the SVM to realize locating the damage and its level identifing.The SVM is used to verify the simulation for the damage identification of a cantilever beam and the results show that the SVM is very applicable to the damage dianosis of structures.