• Title/Summary/Keyword: PointNet++

Search Result 630, Processing Time 0.027 seconds

Application of a deep learning algorithm to Compton imaging of radioactive point sources with a single planar CdTe pixelated detector

  • Daniel, G.;Gutierrez, Y.;Limousin, O.
    • Nuclear Engineering and Technology
    • /
    • v.54 no.5
    • /
    • pp.1747-1753
    • /
    • 2022
  • Compton imaging is the main method for locating radioactive hot spots emitting high-energy gamma-ray photons. In particular, this imaging method is crucial when the photon energy is too high for coded-mask aperture imaging methods to be effective or when a large field of view is required. Reconstruction of the photon source requires advanced Compton event processing algorithms to determine the exact position of the source. In this study, we introduce a novel method based on a Deep Learning algorithm with a Convolutional Neural Network (CNN) to perform Compton imaging. This algorithm is trained on simulated data and tested on real data acquired with Caliste, a single planar CdTe pixelated detector. We show that performance in terms of source location accuracy is equivalent to state-of-the-art algorithms, while computation time is significantly reduced and sensitivity is improved by a factor of ~5 in the Caliste configuration.

Fault-tolerant control system for once-through steam generator based on reinforcement learning algorithm

  • Li, Cheng;Yu, Ren;Yu, Wenmin;Wang, Tianshu
    • Nuclear Engineering and Technology
    • /
    • v.54 no.9
    • /
    • pp.3283-3292
    • /
    • 2022
  • Based on the Deep Q-Network(DQN) algorithm of reinforcement learning, an active fault-tolerance method with incremental action is proposed for the control system with sensor faults of the once-through steam generator(OTSG). In this paper, we first establish the OTSG model as the interaction environment for the agent of reinforcement learning. The reinforcement learning agent chooses an action according to the system state obtained by the pressure sensor, the incremental action can gradually approach the optimal strategy for the current fault, and then the agent updates the network by different rewards obtained in the interaction process. In this way, we can transform the active fault tolerant control process of the OTSG to the reinforcement learning agent's decision-making process. The comparison experiments compared with the traditional reinforcement learning algorithm(RL) with fixed strategies show that the active fault-tolerant controller designed in this paper can accurately and rapidly control under sensor faults so that the pressure of the OTSG can be stabilized near the set-point value, and the OTSG can run normally and stably.

Beryllium oxide utilized in nuclear reactors: Part I: Application history, thermal properties, mechanical properties, corrosion behavior and fabrication methods

  • Ming-dong Hou;Xiang-wen Zhou;Bing Liu
    • Nuclear Engineering and Technology
    • /
    • v.54 no.12
    • /
    • pp.4393-4411
    • /
    • 2022
  • In recent years, beryllium oxide has been widely utilized in multiple compact nuclear reactors as the neutron moderator, the neutron reflector or the matrix material with dispersed nuclear fuels due to its prominent properties. In the past 70 years, beryllium oxide has been studied extensively, but rarely been systematically organized. This article provides a systematic review of the application history, thermal properties, mechanical properties, corrosion behavior and fabrication methods of beryllium oxide. Data from previous literature are extracted and sorted out, and all of these original data are attached as the supplementary material, so that subsequent researchers can utilize this paper as a database for beryllium oxide research in reactor design or simulation analysis, etc. In addition, this review article also attempts to point out the insufficiency of research on beryllium oxide, and the possible key research areas about beryllium oxide in the future.

Fluidelastic instability of a curved tube array in single phase cross flow

  • Kang-Hee Lee;Heung-Seok Kang;Du-Ho Hong;Jong-In Kim
    • Nuclear Engineering and Technology
    • /
    • v.55 no.3
    • /
    • pp.1118-1124
    • /
    • 2023
  • Experimental study on the fluidelastic instability (FEI) of a curved tube bundle in single phase downward cross flow is investigated for the design qualification and analysis input preparation of helical coiled steam generator tubing. A 6×9 normal square curved tube array with equal and different vertical/horizontal pitch-to-diameter ratio was under-tested up to 6 m/s in term of gap flow velocity to measure the critical velocity for FEI. The critical velocity for FEI was measured at the turning point from the vibration amplitude plot along the gap flow velocity. Our test results were compared with straight tube results and published data in the design guideline. The applicability of the current design guidelines to a curved tube bundle is also assessed. We found that introducing frequency difference in a curved tube array increases the critical velocity for fluidelastic instability.

Sensitivity study of parameters important to Molten Salt Reactor Safety

  • Sarah Elizabeth Creasman;Visura Pathirana;Ondrej Chvala
    • Nuclear Engineering and Technology
    • /
    • v.55 no.5
    • /
    • pp.1687-1707
    • /
    • 2023
  • This paper presents a molten salt reactor (MSR) design parameter sensitivity study using a nodal dynamic modelling methodology with explicitly modified point kinetics equation and Mann's model for heat transfer. Six parameters that can impact MSR safety are evaluated. A MATLAB-Simulink model inspired by Thorcon's 550MWth MSR is used for parameter evaluations. A safety envelope was formed to encapsulate power, maximum and minimum temperature, and temperature-induced reactivity feedback. The parameters are perturbed by ±30%. The parameters were then ranked by their subsequent impact on the considered safety envelope, which ranks acceptable parameter uncertainty. The model is openly available on GitHub.

Multi-Modal Cross Attention for 3D Point Cloud Semantic Segmentation (3차원 포인트 클라우드의 의미적 분할을 위한 멀티-모달 교차 주의집중)

  • HyeLim Bae;Incheol Kim
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2023.05a
    • /
    • pp.660-662
    • /
    • 2023
  • 3차원 포인트 클라우드의 의미적 분할은 환경을 구성하는 물체 단위로 포인트 클라우드를 분할하는 작업으로서, 환경의 3차원적 구성을 이해하고 환경과 상호작용에 필수적인 시각 지능을 요구한다. 본 논문에서는 포인트 클라우드에서 추출하는 3차원 기하학적 특징과 함께 멀티-뷰 영상에서 추출하는 2차원 시각적 특징들도 활용하는 새로운 3차원 포인트 클라우드 의미적 분할 모델 MFNet을 제안한다. 제안 모델은 서로 이질적인 2차원 시각적 특징과 3차원 기하학적 특징의 효과적인 융합을 위해, 새로운 중기 융합 전략과 멀티-모달 교차 주의집중을 이용한다. 본 논문에서는 ScanNetV2 벤치마크 데이터 집합을 이용한 다양한 실험들을 통해, 제안 모델 MFNet의 우수성을 입증한다.

Temperature analysis of extra vessel electromagnetic pump cooling for a Micro nuclear reactor with an electric power of 20 MW

  • Tae Uk Kang;Hee Reyoung Kim
    • Nuclear Engineering and Technology
    • /
    • v.56 no.1
    • /
    • pp.275-282
    • /
    • 2024
  • Lead bismuth eutectic (LBE) is used as coolant for MicroURANUS, a small marine nuclear power plant, and this coolant is transported in the plant by an electromagnetic pump. Given the considerable heat generated by the electromagnetic pump, the cooling of the pump is essential. This study compared air cooling and water-cooling methods and found that the maximum temperatures during air and water cooling were 640 K and 372 K, respectively. These findings were utilized to design an electromagnetic pump with water-cooling. The maximum temperature of the pump was lower than the boiling point of water; thus, the pump did not require a separate pressurization. Consequently, the resistance problem of the coil and the deformation problem of the material caused by generated heat can be solved through water-cooling.

Functional Characterization of Mammary Gland of Holstein Cows under Humid Tropical Summer Climates

  • Lu, C.H.;Chang, C.J.;Lee, P.N.;Wu, C.P.;Chen, M.T.;Zhao, X.
    • Asian-Australasian Journal of Animal Sciences
    • /
    • v.16 no.7
    • /
    • pp.988-995
    • /
    • 2003
  • Physiological parameters were measured on six primiparous, non-pregnant Holstein cows prior to peak lactation over a 3-month summer season in southwestern Taiwan. The objectives were to characterize heat stress-induced change in functionality of mammary gland under natural climates of tropical summer and to establish physiological indices applicable to this environment in referring to this change. Environmental and physiological readings, milk and blood samples were taken at 15:00 h biweekly for totally five time points during the study. Climate readings showed that the afternoon humidex value reached the highest (53.5) around mid summer. Rectal temperature of cows taken simultaneously varied between $38.26^{\circ}C$ and $40.02^{\circ}C$ in parallel to humidex. Milk production declined drastically from 29.2 to 22.2 kg/d the first month entering summer but leveled up at end of the summer season suggesting effects exerted by heat stress rather than stages of lactation. Lactose content decreased linearly (p<0.05) with times in summer, from 4.69 to 4.38%. On the other hand, activity of N-acetylglucosaminidase (NAGase) in milk increased linearly to over two folds (p<0.05) during the same intervals. Elevations of fractional constituent of BSA in whey protein and serum cortisol level were also noticed in the course. Measurement of arteriovenous concentration (A-V) difference across the mammary gland demonstrated net uptake of glucose and net release of urea throughout the study period. The amount of urea released from mammary gland increased (p<0.05) progressively from 1.54 to 7.76 mg/dl during summer. It is concluded that gradual regression of mammary gland occurred along the humid tropical summer season. This regression is likely initiated through elevation of body temperature, which is irreversible above certain point. The increased release of urea from mammary gland during heat stress suggests its potential role as an early indicator of suboptimal mammary function.

A Theoretical Study on the Toyota Production System and Practical Example (도요타 생산방식(TPS)의 이론과 실제)

  • Lim, Jae-Hwa;Mok, Jin-Hwan
    • 한국산학경영학회:학술대회논문집
    • /
    • 2006.06a
    • /
    • pp.171-190
    • /
    • 2006
  • Toyota 2005 annual report said Toyota has six consecutive fiscal year positive revenues and record breaking revenues during recent four consecutive years. Net profit is 11% grower than last year. (\11,000,000,000,000). In the spotlight they have record breaking net profit every year, their strongest point is their unique production system which come up with MUDA(waste) free and ongoing improvement activity. Their basic production philosophy is value added through improve production efficiency which can be possible by eliminating MUDA(waste). This basic philosophy's key points are "Just in Time" and "Automation with human". Recently, Korean manufacturing companies and service companies have a growing interest in Toyota Production System. They try to find ways for appling Toyota system to their companies. Through observing Toyota production theory, understand Toyota Production System, Through studying practical application in industrial fields, examine application possibility for Korean industry and more detailed researches are required.

  • PDF

Development of a Windows-based Program for Discrete Event Simulation of Truck-Loader Haulage Systems in an Underground Mine (지하광산 트럭-로더 운반시스템의 이산 사건 시뮬레이션을 위한 Windows용 프로그램 개발)

  • Choi, Yosoon;Park, Sebeom;Lee, Sung-Jae;Baek, Jieun;Jung, Jihoo;Park, Han-Su
    • Tunnel and Underground Space
    • /
    • v.26 no.2
    • /
    • pp.87-99
    • /
    • 2016
  • We developed a Windows-based program for discrete event simulation of truck-loader haulage systems in an underground mine. The Daesung MDI limestone mine located in Samcheok City, Gangwon Province, Korea was selected as the study area to design the program. The developed program is composed of the graphic user interface (GUI) and simulation engine implemented by Visual Basic.NET 2012 and the GPSS/H simulation language, respectively. When a user sets up input parameters for the discrete event simulation through GUI, the program activates the simulation engine, and then simulation results are displayed on GUI. This paper describes the details of the program development as well as its applications to the study area to determine the optimal number of trucks dispatched at each loading point under different operating conditions.