Intelligent Seismic Acceleration Signal Processing for Damage Classification in Buildings

Three new pattern recognition methods, based on fuzzy logic techniques that are suitable for seismic acceleration signal classification, are proposed in this paper. The classification of unknown signals is carried out according to the structural or architectural damage that is produced by the seismic signals. A set of 400 natural accelerograms, which have been recorded in various regions with well-known strong seismic activity, has been used for evaluation of the proposed methods. The seismic accelerograms are first treated as graphs; the similarity between them is exploited in order to perform the classification. In the second approach, a set of parameters are derived from each signal through computer analysis. These describe effectively the intensity measure of the seismic excitation, and they are used instead of the accelerograms. Similarity between them is appropriately utilized. Finally, a method that depends purely on fuzzification of the accelerograms parameters is also described. Classification results are presented for each method, and correct classification rates up to approximately 85% are recorded. The contribution of this paper to seismic signal classification lies in the methodology that allows for classification of seismic signals according to the damage in buildings. This process depends strongly on the structural parameters of the specific building, and therefore, given a building and a seismic signal, each signal can be classified into one of the four well-defined and scientifically approved damage classes. Consequently, the proposed paper contributes an effective method for engineers to test the response of a building to seismic signals, produced by earthquakes.