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.
DOCUMENT
This paper aims to quantify the evolution of damage in masonry walls under induced seismicity. A damage index equation, which is a function of the evolution of shear slippage and opening of the mortar joints, as well as of the drift ratio of masonry walls, was proposed herein. Initially, a dataset of experimental tests from in-plane quasi-static and cyclic tests on masonry walls was considered. The experimentally obtained crack patterns were investigated and their correlation with damage propagation was studied. Using a software based on the Distinct Element Method, a numerical model was developed and validated against full-scale experimental tests obtained from the literature. Wall panels representing common typologies of house façades of unreinforced masonry buildings in Northern Europe i.e. near the Groningen gas field in the Netherlands, were numerically investigated. The accumulated damage within the seismic response of the masonry walls was investigated by means of representative harmonic load excitations and an incremental dynamic analysis based on induced seismicity records from Groningen region. The ability of this index to capture different damage situations is demonstrated. The proposed methodology could also be applied to quantify damage and accumulation in masonry during strong earthquakes and aftershocks too.
DOCUMENT
This paper aims to quantify the cumulative damage of unreinforced masonry (URM) subjected to induced seismicity. A numerical model based on discrete element method (DEM) has been develop and was able to represented masonry wall panels with and without openings; which are common typologies of domestic houses in the Groningen gas field in the Netherlands. Within DEM, masonry units were represented as a series of discrete blocks bonded together with zero-thickness interfaces, representing mortar, which can open and close according to the stresses applied on them. Initially, the numerical model has been validated against the experimental data reported in the literature. It was assumed that the bricks would exhibit linear stress-strain behaviour and that opening and slip along the mortar joints would be the predominant failure mechanism. Then, accumulated damage within the seismic response of the masonry walls investigated by means of harmonic load excitations representative of the acceleration time histories recorded during induced seismicity events that occurred in Groningen, the Netherlands.
DOCUMENT