First-Level Pre-earthquake Assessment of Buildings Using Fuzzy Logic

This paper discusses the performance of a fuzzy logic–based rapid visual screening procedure that results in the categorization of buildings into five different types of possible damage with respect to the potential occurrence of a major seismic event. In order to provide results representing expected damage, adaptive neural networks were used to train the method according to information obtained from the vulnerability of 102 buildings stricken by the Athens earthquake of 1999. The precision of the method was thereby enhanced, implying an improvement in efficiency and presenting remarkable advantages when compared to probabilistic approaches to rapid visual screening. Due to the small size of the database used for the training procedure, however, the prospects of the method remain to be discussed. Nonetheless, by using information from larger databases, the method has the potential for self-improvement, a fact that underlines a good prospect for the formation of reliable and robust pre-earthquake assessment methods.