In recent years, the number of human-induced earthquakes in Groningen, a large gas field in the north of the Netherlands, has increased. The majority of the buildings are built by using unreinforced masonry (URM), most of which consists of cavity (i.e. two-leaf) walls, and were not designed to withstand earthquakes. Efforts to define, test and standardize the metal ties, which do play an important role, are valuable also from the wider construction industry point of view. The presented study exhibits findings on the behavior of the metal tie connections between the masonry leaves often used in Dutch construction practice, but also elsewhere around the world. An experimental campaign has been carried out at Delft University of Technology to provide a complete characterization of the axial behavior of traditional connections in cavity walls. A large number of variations was considered in this research: two embedment lengths, four pre-compression levels, two different tie geometries, and five different testing protocols, including monotonic and cyclic loading. The experimental results showed that the capacity of the connection was strongly influenced by the embedment length and the geometry of the tie, whereas the applied pre-compression and the loading rate did not have a significant influence.
As part of the American Society of Civil Engineers E-Newsletter at page 5&6.
Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly manually inspected which is a laborious, costly and subjective process. With developments in computer vision, there is an opportunity to use digital images to automate the visual inspection process. The aim of this study is to examine deep learning techniques for crack detection on images from masonry walls. A dataset with photos from masonry structures is produced containing complex backgrounds and various crack types and sizes. Different deep learning networks are considered and by leveraging the effect of transfer learning crack detection on masonry surfaces is performed on patch level with 95.3% accuracy and on pixel level with 79.6% F1 score. This is the first implementation of deep learning for pixel-level crack segmentation on masonry surfaces. Codes, data and networks relevant to the herein study are available in: github.com/dimitrisdais/crack_detection_CNN_masonry.
