• 제목/요약/키워드: FusionNet

검색결과 167건 처리시간 0.02초

Development of machine learning model for automatic ELM-burst detection without hyperparameter adjustment in KSTAR tokamak

  • Jiheon Song;Semin Joung;Young-Chul Ghim;Sang-hee Hahn;Juhyeok Jang;Jungpyo Lee
    • Nuclear Engineering and Technology
    • /
    • 제55권1호
    • /
    • pp.100-108
    • /
    • 2023
  • In this study, a neural network model inspired by a one-dimensional convolution U-net is developed to automatically accelerate edge localized mode (ELM) detection from big diagnostic data of fusion devices and increase the detection accuracy regardless of the hyperparameter setting. This model recognizes the input signal patterns and overcomes the problems of existing detection algorithms, such as the prominence algorithm and those of differential methods with high sensitivity for the threshold and signal intensity. To train the model, 10 sets of discharge radiation data from the KSTAR are used and sliced into 11091 inputs of length 12 ms, of which 20% are used for validation. According to the receiver operating characteristic curves, our model shows a positive prediction rate and a true prediction rate of approximately 90% each, which is comparable to the best detection performance afforded by other algorithms using their optimized hyperparameters. The accurate and automatic ELM-burst detection methodology used in our model can be beneficial for determining plasma properties, such as the ELM frequency from big data measured in multiple experiments using machines from the KSTAR device and ITER. Additionally, it is applicable to feature detection in the time-series data of other engineering fields.

쾌속 조형과 쾌속 툴링을 이용한 3차원 제품의 정형 가공에 관한 연구 (Investigation into Net-Shape Manufacturing of Three-Dimensional Parts by using RP and RT)

  • 안동규;이상호;김기돈;양동열;박승교
    • 한국소성가공학회:학술대회논문집
    • /
    • 한국소성가공학회 2001년도 춘계학술대회 논문집
    • /
    • pp.16-19
    • /
    • 2001
  • Rapid Prototyping (RP) and Rapid Tooling (RT) were introduced to reduce time-to-market and cost by shortening not only the development phase but also the production phase of the manufacturing process. RP generally builds up a prototype layer by layer, rapidly generating a fully three-dimensional free form shape. RT enables the manufacture of production tools. The integration of RP and RT has the potential for rapid net shaping of thee-dimensional parts, which have geometrical complexity. In this study, net shaping techniques for making three-dimensional parts using RP and RT are described and a sample part are shown. A three-dimensional metal part is manufactured by a new RP process, Variable Lamination Manufacturing by using Expandable Polystyrene Foam (VLM-S), and its application to RT for making a clover punch. In addition, we discussed the technology fusion between metal forming md RP/RT.

  • PDF

Audio and Video Bimodal Emotion Recognition in Social Networks Based on Improved AlexNet Network and Attention Mechanism

  • Liu, Min;Tang, Jun
    • Journal of Information Processing Systems
    • /
    • 제17권4호
    • /
    • pp.754-771
    • /
    • 2021
  • In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

Investigation on the thermal butt fusion performance of the buried high density polyethylene piping in nuclear power plant

  • Kim, Jong-Sung;Oh, Young-Jin;Choi, Sun-Woong;Jang, Changheui
    • Nuclear Engineering and Technology
    • /
    • 제51권4호
    • /
    • pp.1142-1153
    • /
    • 2019
  • This paper presents the effect of fusion procedure on the fusion performance of the thermal butt fusion in the safety class III buried HDPE piping per various tests performed, including high speed tensile impact, free bend, blunt notched tensile, notched creep, and PENT tests. The suitability of fusion joints and qualification procedures was evaluated by comparing test results from the base material and buttfusion joints. From the notched tensile test result, it was found that the fused joints have much lower toughness than the base material. It was also identified that the notched tensile test is more desirable than the high speed tensile impact and free bend tests presented in the ASME Code Case N-755-3 as a fusion qualification test method. In addition, with regard to the single low-pressure fusion joint performances, the procedure given by the ISO 21307 was determined to be better that the one specified in the Code Case N-755-3.

Estimation of the neutron production of KSTAR based on empirical scaling law of the fast ion stored energy and ion density under NBI power and machine size upgrade

  • Kwak, Jong-Gu;Hong, S.C.
    • Nuclear Engineering and Technology
    • /
    • 제54권6호
    • /
    • pp.2334-2337
    • /
    • 2022
  • Deuterium-tritium reaction is the most promising one in term of the highest nuclear fusion cross-section for the reactor. So it is one of urgent issues to develop materials and components that are simultaneously resistant to high heat flux and high energy neutron flux in realization of the fusion energy. 2.45 MeV neutron production was reported in D-D reaction in KSTAR and regarded as beam-target is the dominant process. The feasibility study of KSTAR to wide area neutron source facility is done in term of D-D and D-T reactions from the empirical scaling law from the mixed fast and thermal stored energy and its projection to cases of heating power upgrade and DT reaction is done.

CURRENT STATUS OF NUCLEAR FUSION ENERGY RESEARCH IN KOREA

  • Kwon, My-Eun;Bae, Young-Soon;Cho, Seung-Yon;Choe, Won-Ho;Hong, Bong-Geun;Hwang, Yong-Seok;Kim, Jin-Yong;Kim, Kee-Man;Kim, Yaung-Soo;Kwak, Jong-Gu;Lee, Hyeon-Gon;Lee, San-Gil;Na, Yong-Su;Oh, Byung-Hoon;Oh, Yeong-Kook;Park, Ji-Yeon;Yang, Hyung-Lyeol;Yu, In-Keun
    • Nuclear Engineering and Technology
    • /
    • 제41권4호
    • /
    • pp.455-476
    • /
    • 2009
  • The history of nuclear fusion research in Korea is rather short compared to that of advanced countries. However, since the mid-1990s, at which time the construction of KSTAR was about to commence, fusion research in Korea has been actively carried out in a wide range of areas, from basic plasma physics to fusion reactor design. The flourishing of fusion research partly owes to the fact that industrial technologies in Korea including those related to the nuclear field have been fully matured, with their quality being highly ranked in the world. Successive pivotal programs such as KSTAR and ITER have provided diverse opportunities to address new scientific and technological problems in fusion as well as to draw young researchers into related fields. The frame of the Korean nuclear fusion program is now changing from a small laboratory scale to a large national agenda. Coordinated strategies from different views and a holistic approach are necessary in order to achieve optimal efficiency and effectiveness. Upon this background, the present paper reflects upon the road taken to arrive at this point and looks ahead at the coming future in nuclear fusion research activities in Korea.

딥러닝에 의한 항공사진 구름 분류 및 탐지 비교 실험 (Comparative Experiment of Cloud Classification and Detection of Aerial Image by Deep Learning)

  • 송준영;원태연;조수민;어양담;박소영;신상호;박진수;김창재
    • 한국측량학회지
    • /
    • 제39권6호
    • /
    • pp.409-418
    • /
    • 2021
  • 항공사진 촬영량이 증가함에 따라 품질검사 자동화의 필요성이 대두되고 있다. 본 연구에서는 딥러닝 기법으로 항공사진 내 구름을 분류 또는 탐지하는 실험을 수행하였고, 또한 위성영상을 학습자료에 포함시켜 분류 및 탐지를 수행하였다. 실험에 사용한 알고리즘으로는 GoogLeNet, VGG16, Faster R-CNN과 YOLOv3을 적용하여 결과를 비교하였다. 또한 구름이 포함된 오류영상 확보의 현실적 제한을 고려하여 항공영상만 존재하는 학습 데이터세트에서 위성영상을 활용한 추가학습이 분류 및 탐지정확도에 영향을 미치는지도 분석하였다. 실험결과, 항공사진의 구름 분류와 탐지에서 각각 GoogLeNet과 YOLOv3 알고리즘이 상대적으로 우월한 정확도를 나타냈고, GoogLeNet은 구름에 대한 생산자정확도 83.8% 그리고 YOLOv3는 구름에 대한 생산자정확도 84.0%를 보여주었다. 또한, 위성영상 학습자료 추가가 항공사진 자료의 부족 시 대안으로 적용가능 함을 보여주었다.

Theoretical study of cross sections of proton-induced reactions on cobalt

  • Yigit, Mustafa
    • Nuclear Engineering and Technology
    • /
    • 제50권3호
    • /
    • pp.411-415
    • /
    • 2018
  • Nuclear fusion may be among the strongest sustainable ways to replace fossil fuels because it does not contribute to acid rain or global warming. In this context, activated cobalt materials in corrosion products for fusion energy are significant in determination of dose levels during maintenance after a coolant leak in a nuclear fusion reactor. Therefore, cross-section studies on cobalt material are very important for fusion reactor design. In this article, the excitation functions of some nuclear reaction channels induced by proton particles on $^{59}Co$ structural material were predicted using different models. The nuclear level densities were calculated using different choices of available level density models in ALICE/ASH code. Finally, the newly calculated cross sections for the investigated nuclear reactions are compared with the experimental values and TENDL data based on TALYS nuclear code.

Real-time Segmentation of Black Ice Region in Infrared Road Images

  • Li, Yu-Jie;Kang, Sun-Kyoung;Jung, Sung-Tae
    • 한국컴퓨터정보학회논문지
    • /
    • 제27권2호
    • /
    • pp.33-42
    • /
    • 2022
  • 본 논문에서는 운전자한테 실시간으로 블랙 아이스 경고를 보내기 위해서 도로 영상에서 블랙 아이스 영역 분할을 위한 다중 척도 팽창 컨볼루션 특징 융합에 기반한 딥러닝 모델을 제안한다. 제안한 다중척도 팽창 컨볼루션 특징 융합 네트워크는 인코더 블록에 서로 다른 팽창 비율 컨볼루션을 병렬로 추가하고, 서로 다른 해상도 특징 맵에서 서로 다른 팽창 비율을 설정하고, 다중 단계 특징 정보가 함께 융합된다. 다중 척도 팽창 컨볼루션 특징 융합은 수용 영역을 확장함과 동시에 공간의 세부 정보를 잘 보존하고 팽창 컨볼루션의 효과성을 높임으로써 기존 모델보다 성능을 향상시킨다. 실험 결과를 통해 본 논문 제안한 네트워크 모델은 병렬 평창 컨볼루션 수가 증가함에 따라 성능이 향상되는 것을 알 수 있었다. 제안한 방법의 mIoU 값은 96.46%로 U-Net, FCN, PSPNet, ENet, LinkNet 등 기존 네트워크보다 높았다. 그리고 파라미터는 1,858K개로, 기존 LinkNet모델보다 6배로 축소하였다. Jetson Nano에서 실험 결과 보면, 제안한 방법의 FPS는 3.63로 실시간으로 블랙 아이스 영역을 실시간으로 분할 할 수 있었다.

Neutronic investigation of waste transmutation option without partitioning and transmutation in a fusion-fission hybrid system

  • Hong, Seong Hee;Kim, Myung Hyun
    • Nuclear Engineering and Technology
    • /
    • 제50권7호
    • /
    • pp.1060-1067
    • /
    • 2018
  • A feasibility of reusing option of spent nuclear fuel in a fusion-fission hybrid system without partitioning was checked as an alternative option of pyro-processing with critical reactor system. Neutronic study was performed with MCNP 6.1 for this option, direct reuse of spent PWR fuel (DRUP). Various options with DRUP fuel were compared with the reference design concept; transmutation purpose blanket with (U-TRU)Zr fuel loading connected with pyro-processing. Performance parameters to be compared are transmutation performance of transuranic (TRU) nuclides, required fusion power and tritium breeding ratio (TBR). When blanket part is loaded only with DRUP, initial $k_{eff}$ level becomes too low to maintain a practical subcritical system, increasing the required fusion power. In this case, production rate of TRU nuclides exceeds the incineration rate. Design optimization is done for combining DRUP fuel with (U-TRU)Zr fuel. Reactivity swing is reduced to about 2447 pcm through fissile breeding compared to (U-TRU)Zr fuel option. Therefore, a required fusion power is reduced and tritium breeding performance is improved. However, transmutation performance with TRU nuclides especially $^{241}Am$ is degraded because of softening effect of spectrum. It is known that partitioning and transmutation should be accompanied with fusion-fission hybrid system for the effective transmutation of TRU.