Structural health monitoring (SHM) requires using active elements and a large of amount sensors to monitor a structure in succession and detect the damaging position and damage degree at an early stage. Monitor the healthy situation of the structure along with the time, and form a prognosis of the future safety and functionality of the structure. So that carries out the damage evaluation and life assessment of the structure. In this investigation, the external load is exerted on an aircraft wing box to imitate the structural damage. At the same time, different models are proposed to predict the external damage position which is an important subject for the SHM system, and the models are particle swarm optimization-support vector machine (PSO-SVM), grid search-support vector machine (GS-SVM) and genetic algorithm-support vector machine (GA-SVM) separately. Furthermore, in order to demonstrate the effectiveness of above algorithm, a structural health monitoring system based on an eight-point fiber Bragg grating (FBG) sensor network is designed to monitor the external static loading damage position. The results indicate that the proposed three methods can enhance the predicting precision greatly compared to the SVM model. It provides a certain reference significance for assess the healthy situation of the structure.