Search

Using Unmanned Aerial Systems (UASs) for bridge visual inspection automation necessitates the implementation of Deep Convolutional Neural Networks (DCNNs) to process efficiently the large amount of data collected by the UASs sensors. However, these networks require massive training datasets for the defects recognition and detection tasks. In an effort to expand existing concrete defects datasets, particularly concrete cracks in bridges, this paper proposes a public benchmark annotated image dataset containing over 6900 images of cracked and non cracked concrete bridges and culverts. The presented dataset includes some challenging surface conditions and covers concrete cracks with different sizes and patterns. The authors analyzed the proposed dataset using three state of the art DCNNs in Transfer Learning mode. The three models were used to classify the cracked and non cracked images and the best testing accuracy obtained reached 95.89%. The experimental results showcase the potential use of this dataset to train deep networks for concrete crack recognition in bridges. The dataset is publicly available at https://github.com/MCBDD-ZRE/Concrete-Bridge-Crack-Dataset- for academic purposes.

The stereotomy (bricklaying pattern) of masonry arches is not only a characteristic of the architecture of these structures, but also an important revealing element of mechanical safety when degradations appear in the complex material of masonry. This paper presents the effect of randomness of this parameter on the bearing capacity of masonry arch bridges based on reliability of structures. Different mechanical models that are classically used for the analysis of the bearing capacity of masonry arches can support a reliability analysis. In this paper, a rigid block model and finite-element model are presented and compared. Then, focusing on the rigid block method, stereotomy has been integrated as a geometrical parameter influencing the mechanical behavior. To this end, the stereotomy function is presented as a parameter that can be influenced by the possible degradations affecting the blocks and/or mortar joints, thus justifying its randomness and consequently integrating it in a reliability study. The reliability study carried out in this work focused on the case of a single-span masonry arch bridge located in Morocco. The reliability analysis demonstrated the importance of joints orientation and the possible perturbations that it can undergo around the classical radial configuration. The effect of these perturbations is shown for the failure multiplier, which represents the bearing capacity of the studied arch. Masonry arch bridges are a heritage of great architectural and economic importance for many countries worldwide. This is due to the historical value of these ancient constructions, but also to their durability that allowed them to still fulfil their economic role. Nevertheless, the preservation of the safety of masonry arch bridges depends on a good maintenance approach that takes into account the different hazards affecting these constructions. The uncertainties affecting the geometry are among the hazards to be taken into account by the roadway and railway managers. In this paper, the authors study the effects of uncertainties related to the bricklaying pattern of masonry blocks on the mechanical behavior of the arch bridge. For this purpose, probability-based methods are applied in conjunction with mechanical calculation techniques. The results obtained highlight the importance of considering the stereotomy parameter, which represents the bricklaying pattern of masonry blocks in the arch in maintenance operations. [ABSTRACT FROM AUTHOR]

Rammed earth (RE) construction is an ancestral technique that allows for the building of durable and resistant constructions. RE buildings are sustainable and environment-friendly, and ensure energy optimization during the construction cycle. For these reasons, many of the following RE characteristics are studied: mechanical strength, seismic resistance, and thermal performance. However, the mix design of RE soils has been rarely studied. There is practically no scientific approach that allows for defining precise dosages of clay, silt, sand, and gravel used in RE materials. The broader aim of this article is to determine a scientific mix design method to find an optimal RE granular mixture. The compressible packing model (CPM) is applied to study the effect of every granular class on compactness and define the optimum mixture. Many tests have been conducted such as the Modified Proctor, compression test, and ultrasonic velocity pulse test to evaluate the relevance of this model. The results suggest many granular corrections for RE material that considerably enhance compactness and unconfined compressive strength (UCS). It was found that one granular correction provides a 137% increase in the initial UCS. Therefore, this approach enables the defining of which granular class is to be added or reduced to optimize the mechanical properties of RE. [ABSTRACT FROM AUTHOR]

Bridges deteriorate over time, which requires the continuous monitoring of their condition. There are many digital technologies for inspecting and monitoring bridges in real-time. In this context, computer vision has extensively studied cracks to automate their identification in concrete surfaces, overcoming the conventional manual methods that rely on human judgment. The general framework of vision-based techniques consists of feature extraction using different filters and descriptors and classifier training to perform the classification task. However, training can be time-consuming and computationally expensive, depending on the dimension of the features. To address this limitation, dimensionality reduction techniques are applied to extracted features, and a new feature subspace is generated. This work used histograms of oriented gradients (HOGs) and uniform local binary patterns (ULBPs) to extract features from a dataset containing over 3000 uncracked and cracked images covering different patterns of cracks and concrete surface representations. Nonlinear dimensionality reduction was performed using kernel principal component analysis (KPCA), and three machine learning classifiers were implemented to conduct the classification. The experimental results show that the classification scheme based on the support-vector machine (SVM) model and feature-level fusion of the HOG and ULBP features after KPCA application provided the best results as an accuracy of 99.26% was achieved by the proposed classification framework. [ABSTRACT FROM AUTHOR]

Conventional practices of bridge visual inspection present several limitations, including a tedious process of analyzing images manually to identify potential damages. Vision-based techniques, particularly Deep Convolutional Neural Networks, have been widely investigated to automatically identify, localize, and quantify defects in bridge images. However, massive datasets with different annotation levels are required to train these deep models. This paper presents a dataset of more than 6900 images featuring three common defects of concrete bridges (i.e., cracks, efflorescence, and spalling). To overcome the challenge of limited training samples, three Transfer Learning approaches in fine-tuning the state-of-the-art Visual Geometry Group network were studied and compared to classify the three defects. The best-proposed approach achieved a high testing accuracy (97.13%), combined with high F1-scores of 97.38%, 95.01%, and 97.35% for cracks, efflorescence, and spalling, respectively. Furthermore, the effectiveness of interpretable networks was explored in the context of weakly supervised semantic segmentation using image-level annotations. Two gradient-based backpropagation interpretation techniques were used to generate pixel-level heatmaps and localize defects in test images. Qualitative results showcase the potential use of interpretation maps to provide relevant information on defect localization in a weak supervision framework. [ABSTRACT FROM AUTHOR]