Detecting cracks is vital for inspecting and maintaining concrete structures, enabling early intervention and preventing potential damage. The advent of computer vision and image processing in civil engineering has ushered in deep learning-based semi-automatic/automatic techniques, replacing traditional visual inspections. These methods, driven by autonomous diagnosis, have applications across various sectors, fostering rapid progress in civil engineering. In this study, we present an approach that combines vision transformers and convolutional neural networks (CNN) for autonomously diagnosing cracks in bridges, roads, and walls. Performance enhancement was achieved through transfer learning, data augmentation, and optimized hyperparameters, utilizing popular CNN and ViT architectures. The proposed method was tested on the SDNET2018 dataset, comprising over 56,000 images. Experimental results demonstrated the approach's effectiveness, achieving high accuracy in detecting road cracks at 96.41%, wall cracks at 92.76%, and bridge cracks at 92.81%. These findings highlight the promising potential of deep learning in this field.

So far, little attention has been paid to the investigation on the seismic failure mechanisms of flexible concrete pile groups embedded in the layered soft soil profiles considering the material non-linearities of soil and concrete piles. The purpose of this study is to investigate seismic failure mechanism models of flexible concrete piles with varied groups in silt layered loose sand profiles under horizontal strong ground motions. Three-dimensional finite element models of the pile–soil interaction systems, which include nonlinearities of soil and concrete piles as well as coupling interactions between the piles and soil, were created for Models I, II, and III of the soil domains, encompassing 1x1, 2x2, and 3x3 flexible pile groups with diameters of 0.80 m and 1.0 m. Model I consists of a homogenous sand layer and a bedrock, Models II and III are composed of a five-layered domain with homogeneous sand and silt soil layers of different thicknesses. The linear elastic perfectly plastic constitutive model with a Mohr–Coulomb failure criterion is considered to represent the behavior of the soil layers, and the Concrete Damage Plasticity (CDP) model is used for the nonlinear behavior of the concrete piles. The interactions between the soil and the pile surfaces are modeled by defining tangential and normal contact behaviors. The models were analyzed for the scaled acceleration records of the 1999 Düzce and Kocaeli earthquakes, considering peak ground accelerations of 0.25 g, 0.50 g, and 0.75 g. The numerical results indicated that failure mechanisms of flexible concrete groups occur near the silt layers, and the silt layers have led to a significant increase in the spread area of the damaged zone and the number of damaged elements.

Following recent earthquakes in Van, Istanbul, Izmir, and Kahramanmaraş, concerns have once again been raised regarding whether existing buildings possess adequate seismic performance and the necessity of strengthening those that do not. A common theme in all related discussions is how to improve the seismic resilience of the existing building stock most efficiently and cost-effectively. In particular, seismic retrofitting efforts should be accelerated for residential buildings in areas where urban transformation has not been feasible due to low added value, as well as for public buildings in smaller settlements and school or dormitory structures in rural towns and villages. In this study, the seismic performance of a reinforced concrete (RC) frame was evaluated using the nonlinear single-mode pushover analysis method in accordance with the Turkish Building Earthquake Code (TBEC). For frames with inadequate performance, a retrofitting method was proposed using glued laminated timber (glulam), a renewable and sustainable material, as diagonal bracing. This intervention aimed to improve the structural performance to an acceptable level specified by the code. The results indicated that glulam braces can effectively enhance the seismic performance of RC buildings and may be considered a viable solution for this purpose.

Roller compacted concrete (RCC) is a dry concrete mixture often utilized in the construction of large dams. The interlayer of the RCC dam, which is the weakest plane of the structure, can easily fail under hydraulic shear load, geological impact, earthquake force and environmental impact. In this study linear and performance analyzes were carried out for eight different scenarios for foundation effect, gravity effect and empty and full reservoir situations. In analyses, the earthquake response and performance of the Akçakoca RCC Dam, taking into account the interaction between the dam and the water. The reservoir water behavior is simulated using the Eulerian-Lagrangian coupled (CEL) approach with finite elements modeling. Linear analyses reveal that hydrodynamic pressure leads to increased displacements and principal stresses. The earthquake performance evaluation of the Akçakoca RCC dam indicates that critical concrete damages are expected based on linear time-history analyses conducted for both empty and full reservoir scenarios. Besides, according to this study, gravity effect clearly increases the earthquake performance of the dam.