Realtime Damage Detection in Buildings Using Filter Based Radial Basis Function Network Mapping

Radial Basis Function networks are extremely fast and require relatively small training data sets compared to other neural network methods such as back propagation. They are also less susceptible to problems with non-stationary inputs because of the behavior of the radial basis function hidden units. This makes RBF methods very attractive for realtime structural health monitoring (SHM) and damage detection. In this study, the aforementioned merits of the the RBF network will be exploited to perform realtime damage detection in buildings which are subjected to both sinusoidal and earthquake gound motion.