• Computers and Concrete
• /
• 제32권6호
• /
• 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.

• 한국컴퓨터정보학회논문지
• /
• 제25권10호
• /
• pp.35-42
• /
• 2020

본 연구에서는 비지도 이상 탐지 방법을 변형한 U-Net 기반의 이미지 복원 기법을 통해 한정적인 데이터를 활용한 균열 탐지 방안을 제안한다. 콘크리트 균열은 다양한 원인으로 인해 발생하며, 장기적으로 구조물의 심각한 손상을 초래할 수 있는 요소이다. 일반적으로 균열 조사는 검사원의 육안으로 판단하는 외관 검사법을 사용하는데, 이는 판단에 객관성이 떨어지며 인적 오류 발생 가능성이 크다. 따라서 객관적이고 정확한 이미지 분석 처리를 통한 방법이 요구된다. 최근에는 균열을 신속하고 정밀하게 탐지할 수 있도록 딥러닝을 활용한 기술들이 연구되고 있다. 하지만 일반적인 균열자료에 비해 점검 대상물에 대한 데이터는 한정적이므로 이를 활용한 기존 균열 탐지 모델의 성능은 제한적인 경우가 많다. 따라서 본 연구에서는 비지도 이상 탐지 방법을 사용해 점검 대상물에 대한 데이터를 증강하여 해당 데이터를 사용하여 학습한 결과, 정확도 98.78%, 조화평균(F1_Score) 82.67%의 성능을 확인하였다.

• Ecology and Resilient Infrastructure
• /
• 제8권4호
• /
• pp.253-265
• /
• 2021

본 연구에서는 위성영상 촬영 한계를 극복하고 재배 필지 현황 파악 기술 발전에 기여하고자 무인기 영상 및 딥러닝 모형을 이용하여 옥수수 재배 필지 추출 방법을 제안하였다. 연구대상지역은 충북 괴산군 감물면 이담리 일대로 설정하고, 무인기 촬영을 통해 해당지역의 정사영상을 취득하였다. 모형에 필요한 학습자료는 현장조사 자료와 팜맵을 이용하여 구축하였다. 본 연구에 적용한 딥러닝 모형은 의미론적 분할 모형인 Attention U-Net을 이용하였다. 모형의 성능 평가는 학습과정을 거친 후 비학습 자료를 이용하여 옥수수 재배 필지 추출에 대해서 실시 하였다. 모형 성능평가 결과 정밀도는 0.94, 재현율은 0.96 및 F1-Score는 0.92로 나타났다. 본 연구에 적용한 Attention U-Net방법은 옥수수 재배 필지를 효과적으로 추출할 수 있는 방법임을 확인하였다. 따라서 본 연구 방법은 옥수수는 물론 다른 작물에 대한 재배 필지 구분에도 유용하게 활용될 수 있을 것으로 기대된다.

• Smart Structures and Systems
• /
• 제31권4호
• /
• 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
• /
• 제52권4호
• /
• 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
• /
• 제49권4호
• /
• 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
• /
• 제55권6호
• /
• 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
• /
• 제48권2호
• /
• 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.

• 전기전자학회논문지
• /
• 제26권2호
• /
• pp.160-168
• /
• 2022

본 논문에서는 딥러닝과 구체의 형태 변형 방법을 이용한 단일 이미지에서의 3D mesh 재구축 기법을 제안한다. 제안한 기법은 기존의 방식과 다른 다음과 같은 독창성이 있다. 첫 번째, 기존의 근처의 가까운 점들을 연결하여 모서리 또는 면을 구축하는 방식과 다르게 딥러닝 네트워크을 통하여 구체의 꼭짓점의 위치를 사물의 3D 포인트 클라우드와 매우 유사하게 수정한다. 3D 포인트 클라우드를 이용하므로 메모리가 적게 필요하며 구체의 꼭짓점에 오프셋 값 사이에 덧셈 연산만을 수행하기 때문에 더 빠른 연산이 가능하다. 두 번째, 수정한 꼭짓점에 구체의 면 정보를 씌워 3D mesh를 재구축한다. 구체의 꼭짓점의 위치를 수정하여 생성한 3D 포인트 클라우드의 점들의 간격이 일정하지 않을 때에도 이미 점들 사이의 연결 여부를 나타내는 구체의 면 정보라는 3D mesh의 면 정보를 가지고 있어 표현의 단순화나 결손을 방지할 수 있다. 제안하는 기법의 객관적인 신뢰성을 평가하기 위해 공개된 표준 데이터셋인 ShapeNet 데이터셋을 이용하여 비교 논문들과 같은 방법으로 실험한 결과, 본 논문에서 제안하는 기법의 IoU 값이 0.581로, chamfer distance 값은 0.212로 산출되었다. IoU 값은 수치가 높을수록, chamfer distance 값은 수치가 낮을수록 우수한 결과를 나타내므로 다른 논문에서 발표한 기법들보다 3D mesh 재구축의 결과에서 성능의 효율성이 입증되었다.

• Nuclear Engineering and Technology
• /
• 제54권1호
• /
• 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.