• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.211-212
• /
• 2022

In this study, the cracking control performance of ultra-low shrinkage concrete was investigated by the field application. As a result, drying shrinkage crack occurred in normal concrete wall, but no crack occurred in ultra-low shrinkage concrete wall. It is determined that the drying shrinkage crack control effect of the ultra-low shrinkage concrete is excellent.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• Proceedings of the KSME Conference
• /
• 2001.06a
• /
• pp.447-452
• /
• 2001

An automated system is developed to perform fatigue crack growth tests under constant effective stress intensity factor range ${\Delta}K_{eff}$. In the system, crack length and crack opening load are measured in real-time by using the unloading elastic compliance method. The system consists of two personal computers, an analogue electrical subtraction circuit, a stepping motor, a stepping motor driver, a PIO board, and the application software used to integrate the whole system. The performance of the developed system was tested and discussed performing constant ${\Delta}K_{eff}$ crack growth tests on a CT specimen of 7075-T6 aluminum alloy. The performance of the system is found to be strongly dependent on the accuracy of measurements of crack opening load. Besides constant ${\Delta}K_{eff}$ testing, the system is expected to be successfully applied for automation of various fatigue tests.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.

• Structural Engineering and Mechanics
• /
• v.23 no.3
• /
• pp.217-232
• /
• 2006

A crack model for the fracture in concrete based on meshless method is proposed in this paper. The cracks in concrete are classified into micro-cracks or macro-cracks respectively according to their widths, and different numerical approaches are adopted for them. The micro-cracks are represented with smeared crack approach whilst the macro-cracks are represented with discrete cracks that are made up with additional nodes and boundaries. The widely used meshless method, Element-free Galerkin method, is adopted instead of finite element method to model the concrete, so that the discrete crack approach is easier to be implemented with the convenience of arranging node distribution in the meshless method. Rotating-Crack-Model is proved to be preferred over Fixed-Crack-Model for the smeared cracks of this composite crack model due to its better performance on mesh bias. Numerical examples show that this composite crack model can take advantage of the positive characteristics in the smeared and discrete approaches, and overcome some of their disadvantages.

• Journal of Korean Association for Spatial Structures
• /
• v.15 no.2
• /
• pp.69-77
• /
• 2015

Ultra High Performance Fiber Reinforced Concrete (UHPFRC) has a outstanding tensile hardening behaviour after a crack develops, which gives ductility to structures. Existing shear strength model for fiber reinforced concrete is entirely based on crack opening behavior(mode I) which comes from flexural-shear failure, not considering shear-slip behavior(mode II). To find out the mode I and mode II behavior on a crack in UHPFRC simultaneously, maximum shear strength of cracked UHPFRC is investigated from twenty-four push-off test results. The shear stress on a crack is derived as variable of initial crack width and fiber volume ratio. Test results show that shear slippage is proportional to crack opening, which leads to relationship between shear transfer strength and crack width. Based on the test results a hypothesis is proposed for the physical mechanics of shear transfer in UHPFRC by tensile hardening behavior in stead of aggregate interlocking in reinforced concrete. Shear transfer strength based on tensile hardening behavior in UHPFRC is suggested and this suggestion was verified by comparing direct tensile test results and push-off test results.

• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.135-151
• /
• 2023

Using 3D asphalt pavement surface data, a deep and multiscale network named CrackNet-M is proposed in this paper for pixel-level crack detection for improvements in both accuracy and robustness. The CrackNet-M consists of four function-specific architectural modules: a central branch net (CBN), a crack map enhancement (CME) module, three pooling feature pyramids (PFP), and an output layer. The CBN maintains crack boundaries using no pooling reductions throughout all convolutional layers. The CME applies a pooling layer to enhance potential thin cracks for better continuity, consuming no data loss and attenuation when working jointly with CBN. The PFP modules implement direct down-sampling and pyramidal up-sampling with multiscale contexts specifically for the detection of thick cracks and exclusion of non-crack patterns. Finally, the output layer is optimized with a skip layer supervision technique proposed to further improve the network performance. Compared with traditional supervisions, the skip layer supervision brings about not only significant performance gains with respect to both accuracy and robustness but a faster convergence rate. CrackNet-M was trained on a total of 2,500 pixel-wise annotated 3D pavement images and finely scaled with another 200 images with full considerations on accuracy and efficiency. CrackNet-M can potentially achieve crack detection in real-time with a processing speed of 40 ms/image. The experimental results on 500 testing images demonstrate that CrackNet-M can effectively detect both thick and thin cracks from various pavement surfaces with a high level of Precision (94.28%), Recall (93.89%), and F-measure (94.04%). In addition, the proposed CrackNet-M compares favorably to other well-developed networks with respect to the detection of thin cracks as well as the removal of shoulder drop-offs.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.5 no.4
• /
• pp.496-502
• /
• 2017

The purpose of this study is to investigate the applicability of surface-wave techniques for the evaluation of the crack-repairing performance of an epoxy injection method in concrete. In this study, box-shaped concrete specimens with four different crack depths were made with identical mix proportions. The specimens with different crack depths were completely repaired using the same epoxy injection method. The spectral energy transmission ratio of surface waves is used as an index to differentiate the effects of crack depth and crack-repairing performance. The decrease of spectral energy transmission ratio in accordance with the increase of crack depth was identified before repairing. Furthermore, the spectral energy transmission ratio increased after the crack-repairing process in all specimens. The spectral energy transmission ratio is considered as a great indicator for estimating the crack-repairing performance of the epoxy injection method; the ratio was recovered up to almost 95% of the uncracked condition.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.609-615
• /
• 2006

Crack and seat method has been used in United States to prevent reflection cracks of overlay that may be caused by excessive movement at discontinuity of old concrete pavement. This method provide optium space of discontinuity by generating additional discontinuity in old concrete pavement. In this study the effect of various factors on the performance such as IRI and distress at after applying crack and seat method were investigated by using LTPP data.

• Journal of Construction Engineering and Project Management
• /
• v.5 no.2
• /
• pp.44-52
• /
• 2015

Various approaches have been used in crack preparations and each of the approaches has advantages and disadvantages. Although the routing method has been widely used and seems to be the best approach among the approaches, it is not a complete solution for crack preparation. This paper compares and evaluates a pneumatic crack cleaning device (CCD) developed by Robotics and Intelligent Construction Automation group at Georgia Tech, over existing devices. Surveys were conducted to discover factors that affect the performance of crack/joint preparation work. Then, data for such information were collected via field tests for devices such as router, heat lancer, air blower and CCD. Performed field test results and follow-up interviews demonstrated that the utilization of CCD has potential to offer improvements in productivity, safety, and maintenance cost. An analytic hierarchical procedure (AHP) and economic analyses were conducted. The AHP analysis considered three factors including safety, quality and productivity while the economic analyses examined the alternatives in various ways. The results indicated that the CCD was ranked first and second for the AHP analysis and economic analysis, respectively. In conclusion, the field tests and results revealed that the utilization of CCD achieved satisfactorily in performance, quality, safety and control, and showed that it has high potential in crack cleaning practice.