A New Structural Damage Identification Method Based on Artificial Fish Swarm Optimization and Support Vector Machine

摘要

Structural damage identification is a key technology of structural health monitoring. However, there is the defect of low accuracy in the existing methods. In order to settle this issue, a new structural damage identification method based on artificial fish swarm algorithm (AFSA) and Support Vector Machine (SVM) named AF-SVM is presented in this paper. At first, AFSA is used to optimize the parameters of SVM, and then the optimized SVM model is adopted to identify the structural damage. An experiment of damage identification on a pile structure is provided to verify the effectiveness of the proposed method. Experiment results show that AF-SVM has higher identification accuracy than SVM model, PSO-SVM model and adaptive mutation PSO-SVM model.