Data Mining-based Structural Damage Identification of Composite Bridge using Support Vector Machine

A structural health monitoring system contains two components: a data collection approach comprising a network of sensors for recording the structural responses and an extraction methodology in order to achieve the beneficial information on the structural health condition. In this regard, data mining, which is one of the emerging computer-based technologies, can be employed for extraction of valuable information from the sensor databases obtained. On the other hand, the data inverse analysis scheme, as a problem-based procedure, is developing rapidly. Therefore, the aforesaid scheme and data mining should be combined in order to satisfy the increasing demand of data analysis, especially in complex systems such as bridges. In this work, we develop a damage detection methodology based on these strategies. To this end, an inverse analysis approach using data mining is applied for a composite bridge. In order to aid the aim, the support vector machine algorithm is utilized to generate the patterns by means of the vibration characteristic dataset. In order to compare the robustness and accuracy of the predicted outputs, four kernel functions including the linear, polynomial, sigmoid, and radial basis functions are applied to build the patterns. The results obtained point out the feasibility of the proposed method for detecting damage in the composite slab-on-girder bridges.