Vibration-based damage assessment in steel frames using neural networks

This paper describes a procedure for damage assessment in a two-storey steel frame and steel-concrete composite floors structure. The procedure is based on a multi-layer perceptron (MLP). A simplified finite element model is used to generate the training data. This model was previously updated through another MLP using two natural frequencies as inputs and the stiffness of the beams and masses as updating parameters. The different combinations of damage at the ends of the longitudinal beams are used as damage scenarios. The training data for the MLP are generated by varying at random the stiffness of the longitudinal beams. Two natural frequencies and mode shapes are used as inputs, and three different definitions of damage (sections, bars and floors) are tried as outputs. MLPs are trained through the error back-propagation algorithm. Finally, the performance of the procedure is evaluated through the experimental data. Only the approach of damage at floor level gives reasonable results.