---

Concrete bridge deck damage detection by measurement and monitoring variables related to vibration signatures is one of the main tasks of any Bridge Health Monitoring System (BHMS). Generally damage puts some detectable/discoverable signs in the parameters of bridge vibration behavior. However, differences between frequency and mode shape before and after damage are not remarkable as vibration signatures. Therefore most of the introduced methods of damage detection cannot be used practically. Among many methods it seems that models based on artificial intelligence which apply soft computing methods are more attractive for specific structures. In this paper an Adaptive Neuro-Fuzzy Inference System (ANFIS) is used to detect the damage location in a concrete bridge deck modeled by finite element method. Some damage scenarios are simulated in different locations of the deck and accelerations as representatives of response at some specific points are calculated. Excitement is done by applying an impact load at the center of the deck. In the proposed ANFIS damage detection model accelerations are inputs and location of the damage is output. Trained model by simulated data can show the location of the damage very well with a few training data and scenarios which are not used in training stage. This system is capable to be included in real-time damage detection systems as well.

---

It is well known that damaged structural members may alter the behaviour of the structures considerably. Careful observation of these changes has often been viewed as a means to identify and assess the location and severity of damages in structures. Among the responses of a structure, natural frequencies and natural modes are both relatively easy to obtain and independent from external excitation, and therefore, can be used as a measure of the structural behaviour before and after an extreme event which might have led to damage in the structure. This paper applies Charged System Search algorithm to the problem of damage detection using vibration data. The objective is to identify the location and extent of multi-damage in a structure. Both natural frequencies and mode shapes are used to form the required objective function. To moderate the effect of noise on measured data, a penalty approach is applied. Varity of numerical examples including beams, frames and trusses are examined. The results show that the present methodology can reliably identify damage scenarios using noisy measurements and incomplete data.