Using ANN in Process of Seismic Damage Prediction for Residential Buildings

摘要

With the aim of planning preventive measures of seismic protection, estimation of possible damages on building constructions plays an important role. In order to predict the category of damage, a data base was formed out of the data from reports submitted by the commission of the Faculty of Technical Sciences in Novi Sad. The paper presents the research on the influence of the number and structure of input data and the comparative results of prediction of damage category on building constructions for two models of ANN (ANN-1 and ANN-2).