Distortion data research of bridge structure health monitoring based on LS-SVM classification

As one of the most important monitoring parameters in bridge structure health monitoring and evaluation, distortion data contains abundant information about bridge structure. The paper mainly researches the data classification based on LS-SVM. In order to verify the accuracy of data classification, the stronger generalization capability and faster computation rate of LS-SVM is used with parameters setting, different sample data construction, sample capability and the count of parameters change. The result shows that the classification accuracy of LS-SVM is higher and LS-SVM is a good and effective way to research the classification of distortion data.