2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements

Słoński, Marek; Tekieli, Marcin

doi:10.3390/ma13163527

Cited by 30 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed FRCNN-FED model is 10 times faster but less accurate than Mask RCNN. The authors in [86] combined Faster RCNN with 2D digital image correlation (DIC) for concrete crack detection using 1058 images. In the prosed system, Faster RCNN helps in the detection and localization of the crack region, while the DIC helps in the estimation of the deformation field on the concrete surface and measurement of crack width.…”

Section: Object Detection Modelsmentioning

confidence: 99%

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

et al. 2022

View full text Add to dashboard Cite

The use of deep learning (DL) in civil inspection, especially in crack detection, has increased over the past years to ensure long-term structural safety and integrity. To achieve a better understanding of the research work on crack detection using DL approaches, this paper aims to provide a bibliometric analysis and review of the current literature on DL-based crack detection published between 2010 and 2022. The search from Web of Science (WoS) and Scopus, two widely accepted bibliographic databases, resulted in 165 articles published in top journals and conferences, showing the rapid increase in publications in this area since 2018. The evolution and state-of-the-art approaches to crack detection using deep learning are reviewed and analyzed based on datasets, network architecture, domain, and performance of each study. Overall, this review article stands as a reference for researchers working in the field of crack detection using deep learning techniques to achieve optimal precision and computational efficiency performance in light of electing the most effective combination of dataset characteristics and network architecture for each domain. Finally, the challenges, gaps, and future directions are provided to researchers to explore various solutions pertaining to (a) automatic recognition of crack type and severity, (b) dataset availability and suitability, (c) efficient data preprocessing techniques, (d) automatic labeling approaches for crack detection, (e) parameter tuning and optimization, (f) using 3D images and data fusion, (g) real-time crack detection, and (h) increasing segmentation accuracy at the pixel level.

show abstract

Section: Object Detection Modelsmentioning

confidence: 99%

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

et al. 2022

View full text Add to dashboard Cite

show abstract

“…DIC is widely used in many fields of science, e.g., biomechanics, astronautics, microelectronics and now also in civil engineering [ 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 ]. In the experiments, the commercial ARAMIS system was used which is presented in detail in [ 19 , 39 ].…”

Section: Test Setup and Instrumentationmentioning

confidence: 99%

Analysis of Crack Width Development in Reinforced Concrete Beams

2021

View full text Add to dashboard Cite

The reliability and durability of reinforced concrete structures depend on the amount of concrete cracking. The risk associated with cracks generates a need for diagnostic methods for the evaluation of reinforced concrete structures. This paper presents the results of a study of 10 single-span reinforced concrete beams to follow the process of crack formation and changes in their width. The beams were loaded to failure with two forces in a monotonic manner with unloading and in a cyclic manner. Continuous observation of the crack formation process was provided by the digital image correlation system. The simplified method for estimating the maximum crack width is proposed. The presented results confirmed the stochastic character of the process of crack formation and development. The maximum crack widths calculated on the basis of the proposed formula were on the safe side in relation to those calculated according to Eurocode 2. It was also confirmed that the distances between cracks do not depend on the loading manner. Hence the density function describing the distribution of distances between cracks can be used to assess the condition of reinforced concrete elements. The research has also shown the suitability of the DIC system (ARAMIS) for testing concrete elements.

show abstract

“…Three measurement methods were used simultaneously in all 4PB tests: (1) extensometer for the crack width displacement (CMOD), (2) extensometer for the vertical deformation, (3) digital image correlation (DIC) to measure the strain field on the side surface of the specimens ( Figure 4 ). For DIC method the CivEng Vision system (Cracow, Poland) was used [ 25 , 26 ].…”

Section: Experimental Researchmentioning

confidence: 99%

Polymer Flexible Joint as a Repair Method of Concrete Elements: Flexural Testing and Numerical Analysis

et al. 2020

Self Cite

View full text Add to dashboard Cite

Polymer Flexible Joint (PFJ) is a method for repairs of concrete elements, which enables carrying loads and large deformations effectively. This article presents the possibility of applying PFJ on beams subjected to bending and describes the influence of such joints on concrete elements. An experimental investigation was conducted to determine the behavior of concrete in a four-point bending test. The research program included flexural tests of plain concrete elements with a notch, as well as tests of elements which were repaired with PFJ after failure. Based on the experimental results, the numerical characteristics of analyzed polymer and concrete were calibrated. A nonlinear numerical model is developed, which describes the behavior of concrete elements and polymer in the experiments. The model is used to numerically analyze deformations and stresses under increasing load. The influence of flexible joint on concrete elements is described and behavior of elements repaired with PFJ is compared to original elements. Particular attention was paid to the stress redistribution in concrete. The application of flexible joint positively influences load capacity of the connected concrete elements. Furthermore, because of stress redistribution, connected elements can bear larger deformations than original ones. PFJ can therefore be considered an efficient repair method for connecting concrete elements.

show abstract

2D Digital Image Correlation and Region-Based Convolutional Neural Network in Monitoring and Evaluation of Surface Cracks in Concrete Structural Elements

Cited by 30 publications

References 29 publications

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

Analysis of Crack Width Development in Reinforced Concrete Beams

Polymer Flexible Joint as a Repair Method of Concrete Elements: Flexural Testing and Numerical Analysis

Contact Info

Product

Resources

About