Forecast of seismic damage in masonry buildings by means of neural expert systems

The procedure commonly employed to assess the seismic vulnerability of buildings uses simplified qualitative and quantitative observations obtained from the measured data entered into report forms. Schematic data collected in these report forms are suitable for a large-scale survey but they make uncertain the estimate of the vulnerability of structural systems. The strong uncertainty and heterogeneity of the information makes particularly interesting, in order to predict the seismic damage of structural systems, the employment of expert systems based on neural intelligence techniques.