Damage locating of cable-stayed bridges based on dynamic measurement and neural network technique

Taking cable-stayed Kap Shui Mun Bridge as an example, this paper presents a new damage locating method for cable-stayed bridges based on the combination of cable tension index and neural network technique. By using BP network, damage localization for 12 potential damage cases are simulated based on a high-precision FE model. Taking cable tension indices as inputs of neural network for both training and testing, damage locations are indicated by the outputs of the network. The outstanding feature of the method is that a good result can be obtained by using only fundamental natural frequencies of a few stayed cables. Because measurement of fundamental natural frequencies of a few stayed cables is much easier than some other damage-oriented measurement, the method has great practical value. The method can be easily used for damage locating of cable suspension bridges.