This paper evaluates the performance of masonry buildings during the 20 and 27 December 2007 Bala (Ankara) earthquakes. Bala is a township located 50 km southeast from Ankara city in Turkey. The majority of the buildings in the affected region are built in masonry. Most of masonry buildings were formed with random or coursed stone and mud brick walls without any reinforcement. Many of these buildings were damaged or had collapsed. The cracking and failure patterns of the buildings are examined and interpreted according to current provisions for earthquake resistance of masonry structures. The damages are due to several reasons such as poor construction quality and poor workmanship of the buildings. In addition to these reasons, the two earthquakes hit the buildings within seven days, causing progressive damage.

Finite-element (FE) model updating is a very effective procedure for determining the uncertainty parameters in a structural model and minimize differences between experimentally and analytically identified dynamic characteristics. This procedure can be practiced with manual and global/local automatic model updating procedures. Automatic model updating is very popular because of its applicability to all kinds of engineering structures to minimize differences, and its damage localization and structural health monitoring. This paper considers a historical masonry bastion to obtain its dynamic characteristics numerically with the finite-element method and experimentally with ambient vibration tests (AVTs). Sensitivity analyses for the uncertainty parameters and manual and automated model updating to minimize differences are also performed. A castle bastion located in Trabzon, Turkey is selected as an application. The FE model of structure is developed in commercial software. The first three natural frequencies are obtained between 5 and 10 Hz, and AVTs are performed under natural excitation using enhanced frequency domain decomposition (EFDD) and subspace structural identification (SSI) techniques. The first three natural frequencies are obtained between 4 and 7 Hz. The comparison of analytically and experimentally identified dynamic characteristics shows a close agreement between mode shapes, but 26% difference in natural frequencies. To minimize the difference, the FE model of the bastion is updated using manual and global/local automated updating, changing its material properties of Young’s modulus and material density. The maximum differences are reduced from 27 to 3% with manual updating, and to 0.02% with automated model updating.