• Computers and Concrete
• /
• v.32 no.6
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.35-42
• /
• 2020

In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).

• Ecology and Resilient Infrastructure
• /
• v.8 no.4
• /
• pp.253-265
• /
• 2021

In this study, crop cultivation filed was extracted by using Unmanned Aerial Vehicle (UAV) imagery and deep learning models to overcome the limitations of satellite imagery and to contribute to the technological development of understanding the status of crop cultivation field. The study area was set around Chungbuk Goesan-gun Gammul-myeon Yidam-li and orthogonal images of the area were acquired by using UAV images. In addition, study data for deep learning models was collected by using Farm Map that modified by fieldwork. The Attention U-Net was used as a deep learning model to extract feature of UAV in this study. After the model learning process, the performance evaluation of the model for corn cultivation extraction was performed using non-learning data. We present the model's performance using precision, recall, and F1-score; the metrics show 0.94, 0.96, and 0.92, respectively. This study proved that the method is an effective methodology of extracting corn cultivation field, also presented the potential applicability for other crops.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• Nuclear Engineering and Technology
• /
• v.52 no.4
• /
• pp.700-707
• /
• 2020

This study is concerned with the investigation of the half-space albedo problem for "İnönü-linear-quadratic anisotropic scattering" by the usage of Modified FN method. The method is based on Case's method. Therefore, Case's eigenfunctions and its orthogonality properties are derived for anisotropic scattering of interest. Albedo values are calculated for various linear, quadratic and İnönü anisotropic scattering coefficients and tabulated in Tables.

• Nuclear Engineering and Technology
• /
• v.49 no.4
• /
• pp.700-709
• /
• 2017

This work looks at the effect of changes in kinetic parameters on simultaneous reactivity insertions and beam tube flooding in a typical material testing reactor-type research reactor with low enriched high density ($U_3Si_2-Al$) fuel. Using a modified PARET code, various ramp reactivity insertions (from $0.1/0.5 s to $1.3/0.5 s) plus beam tube flooding ($0.5/0.25 s) accidents under uncontrolled conditions were analyzed to find their effects on peak power, net reactivity, and temperature. Then, the effects of changes in kinetic parameters including the Doppler coefficient, prompt neutron lifetime, and delayed neutron fractions on simultaneous reactivity insertion and beam tube flooding accidents were analyzed. Results show that the power peak values are significantly sensitive to the Doppler coefficient of the system in coupled accidents. The material testing reactor-type system under such a coupled accident is not very sensitive to changes in the prompt neutron life time; the core under such a coupled transient is not very sensitive to changes in the effective delayed neutron fraction.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2276-2282
• /
• 2023

We deploy artificial neural networks to unfold neutron spectra from measured energy-integrated quantities. These neutron spectra represent an important parameter allowing to compute the absorbed dose and the kerma to serve radiation protection in addition to nuclear safety. The built architectures are inspired from convolutional neural networks. The first architecture is made up of residual transposed convolution's blocks while the second is a modified version of the U-net architecture. A large and balanced dataset is simulated following "realistic" physical constraints to train the architectures in an efficient way. Results show a high accuracy prediction of neutron spectra ranging from thermal up to fast spectrum. The dataset processing, the attention paid to performances' metrics and the hyper-optimization are behind the architectures' robustness.

• Nuclear Engineering and Technology
• /
• v.48 no.2
• /
• pp.351-359
• /
• 2016

The Korean Prototype Gen-IV sodium-cooled fast reactor (PGSFR) is supposed to be loaded with a relatively-costly low-enriched U fuel, while its envisaged transuranic fuels are not available for transmutation. In this work, the U-enrichment reduction by improving the neutron economy is pursued to save the fuel cost. To improve the neutron economy of the core, a new reflector material, PbO, has been introduced to replace the conventional HT9 reflector in the current PGSFR core. Two types of PbO reflectors are considered: one is the conventional pin-type and the other one is an inverted configuration. The inverted PbO reflector design is intended to maximize the PbO volume fraction in the reflector assembly. In addition, the core radial configuration is also modified to maximize the performance of the PbO reflector. For the baseline PGSFR core with several reflector options, the U enrichment requirement has been analyzed and the fuel depletion analysis is performed to derive the equilibrium cycle parameters. The linear reactivity model is used to determine the equilibrium cycle performances of the core. Impacts of the new PbO reflectors are characterized in terms of the cycle length, neutron leakage, radial power distribution, and operational fuel cost.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.160-168
• /
• 2022

In this paper, we propose a 3D mesh reconstruction method from a single image using deep learning and a sphere shape transformation method. The proposed method has the following originality that is different from the existing method. First, the position of the vertex of the sphere is modified to be very similar to the 3D point cloud of an object through a deep learning network, unlike the existing method of building edges or faces by connecting nearby points. Because 3D point cloud is used, less memory is required and faster operation is possible because only addition operation is performed between offset value at the vertices of the sphere. Second, the 3D mesh is reconstructed by covering the surface information of the sphere on the modified vertices. Even when the distance between the points of the 3D point cloud created by correcting the position of the vertices of the sphere is not constant, it already has the face information of the sphere called face information of the sphere, which indicates whether the points are connected or not, thereby preventing simplification or loss of expression. can do. In order to evaluate the objective reliability of the proposed method, the experiment was conducted in the same way as in the comparative papers using the ShapeNet dataset, which is an open standard dataset. As a result, the IoU value of the method proposed in this paper was 0.581, and the chamfer distance value was It was calculated as 0.212. The higher the IoU value and the lower the chamfer distance value, the better the results. Therefore, the efficiency of the 3D mesh reconstruction was demonstrated compared to the methods published in other papers.

• Nuclear Engineering and Technology
• /
• v.54 no.1
• /
• pp.226-233
• /
• 2022

In the present work, a phase-field model was developed to investigate the influence of recrystallization on bubble evolution during irradiation. Considering the interaction between bubbles and grain boundary (GB), a set of modified Cahn-Hilliard and Allen-Cahn equations, with field variables and order parameters evolving in space and time, was used in this model. Both the kinetics of recrystallization characterized in experiments and point defects generated during cascade were incorporated in the model. The bubble evolution in recrystallized polycrystalline of U-Mo alloy was also investigated. The simulation results showed that GB with a large area fraction generated by recrystallization accelerates the formation and growth of bubbles. With the formation of new grains, gas atoms are swept and collected by GBs. The simulation results of bubble size and distribution are consistent with the experimental results.