The Damage Detection Based on the Fuzzy Clustering and Support Vector Machine

In this paper, a damage detection algorithm based on the fuzzy clustering and support vector machine is presented. First, the acceleration data are decomposed by the wavelet packet transform to extract the wavelet packet component energy, which is used as the damage index. Second, the damage extent of the spatial truss structure is classified by fuzzy clustering. Finally the damage extent is identified using the support vector machine. The numerical example shows that the method can be effectively used to identify the damage of spatial truss structure, and the effect of noise on the algorithm is also studied.