Bu çaly?mada mevcut betonarme (BA) yapylaryn performanslarynyn de?erlendirilmesi için yapay zekâ tabanly analitik bir yöntem geli?tirilmi?tir. Çaly?mada BA bina performansyny etkiledi?i dü?ünülen içerisinde binanyn beton basynç dayanymy da olan 23 parametreye göre kat sayylary 4 ile 10 arasynda de?i?en 66 BA binanyn performans analizi yapylarak ilgili binalaryn olasy deprem durumunda TDY-2007'de belirtilen 4 kademeli performans seviyeleri bulunmu?tur. Böylece çözümü yapylan binalar için girdi verilerine ba?ly bir çykty performans veri grubu olu?turulmu?tur. Bu çaly?mada geli?tirilen yapay zekâ tabanly söz konusu hyzly de?erlendirme algoritmasy sayesinde ülkemizdeki 4 ve 10 katly mevcut BA binalaryn, çok kysa bir sürede ve ekonomik bir ?ekilde de?erlendirilmesi yakla?yk %80 do?ruluk oranynda yapylmy?tyr. Çaly?manyn ikinci kysmynda ise yapay zeka tabanly algoritma verilerine beton parametresi dahil edilmemi? algoritma bu ?ekilde e?itilip test edilmi?tir. Beton parametresi olmaksyzyn elde edilen do?ruluk orany yakla?yk %74 oranynda bulunmu?tur.

In this study, an artificial intelligence-based (ANN based) analytical method has been developed for analyzing earthquake performances of the reinforced concrete (RC) buildings. In the scope of the present study, 66 real RC buildings with four to ten storeys were subjected to performance analysis according to 23 parameters including concrete compressive strength thought to be effective on the performance of RC buildings. In addition, level of performance possible to be shown by these buildings in case of an earthquake was determined on the basis of the 4-grade performance levels specified in Turkish Earthquake Code-2007 (TEC-2007). Thus, an output performance data group was created for the analyzed buildings, in accordance with the input data. Thanks to the ANN-based fast evaluation algorithm mentioned above and developed within the scope of the proposed project study, it will be possible to make an economic and rapid evaluation of four to ten-storey RC buildings in Turkey with great accuracy (about 80%). In the second step of the paper, concrete compressive strength has not been included to ANN-based algorithms and then the prediction accuracy of ANN has been found about 74%.