Classification of Seismic Damages in Buildings Using Fuzzy Logic Procedures

Abstract eng:
It is well known that damage observations on buildings after severe earthquakes exhibit interdependence with the seismic intensity parameters, like peak ground acceleration, response-spectra, Arias intensity and strong motion duration. Numerical elaboration of structural systems quantified the interrelation degree by correlation coefficients. In addition, the seismic response of buildings is directly depended on the ground excitation. Consequently, the seismic response of buildings evaluated by a numerical analysis is directly depended on the used accelerogram and its intensity parameters. Among the several response quantities, the focus is on the overall damage indices (DIs) because they summarize the post-earthquake status of buildings on a single value, which can be easily handled. The Maximum Inter-Storey Drift Ratio (MISDR) and the damage index as defined by Park/Ang (DIG,PA) characterize effectively the structural damages caused to buildings during earthquakes. Intervals for the values of the damage indices are defined to classify the damage degree in low, medium, large and total. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) for the classification of seismic damages. The structural damage is presented by means of the two previously mentioned damage indices (MISDR and DIG,PA). The seismic excitations are simulated by a set of artificial accelerograms and their intensity is described by a set of wellknown seismic parameters. The proposed system was trained (using nonlinear dynamic analyses) and tested on an eighth-story reinforced concrete structure. The numerical results have shown that the fuzzy technique that is implemented in the proposed method contributes to the development of an efficient blind prediction of the seismic damage potential that an accelerogram possesses. The recognition scheme achieves correct classification rates over 90%.

• Export as: BibTeX | MARC | MARCXML | DC | EndNote | NLM | RefWorks
• Add to your basket