• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• pp.18-31
• /
• 2023

Exploring artificial intelligence and machine learning for nuclear safety has witnessed increased interest in recent years. To contribute to this area of research, a machine learning model capable of accurately predicting nuclear power plant response with minimal computational cost is proposed. To develop a robust machine learning model, the Best Estimate Plus Uncertainty (BEPU) approach was used to generate a database to train three models and select the best of the three. The BEPU analysis was performed by coupling Dakota platform with the best estimate thermal hydraulics code RELAP/SCDAPSIM/MOD 3.4. The Code Scaling Applicability and Uncertainty approach was adopted, along with Wilks' theorem to obtain a statistically representative sample that satisfies the USNRC 95/95 rule with 95% probability and 95% confidence level. The generated database was used to train three models based on Recurrent Neural Networks; specifically, Long Short-Term Memory, Gated Recurrent Unit, and a hybrid model with Long Short-Term Memory coupled to Convolutional Neural Network. In this paper, the System Engineering approach was utilized to identify requirements, stakeholders, and functional and physical architecture to develop this project and ensure success in verification and validation activities necessary to ensure the efficient development of ML meta-models capable of predicting of the nuclear power plant response.

• Journal of Power Electronics
• /
• 제11권4호
• /
• pp.408-417
• /
• 2011

The plug-in hybrid electric vehicles (PHEVs) are specialized hybrid electric vehicles that have the potential to obtain enough energy for average daily commuting from batteries. The PHEV battery would be recharged from the power grid at home or at work and would thus allow for a reduction in the overall fuel consumption. This paper proposes an integrated power electronics interface for PHEVs, which consists of a novel Eight-Switch Inverter (ESI) and an interleaved DC/DC converter, in order to reduce the cost, the mass and the size of the power electronics unit (PEU) with high performance at any operating mode. In the proposed configuration, a novel Eight-Switch Inverter (ESI) is able to function as a bidirectional single-phase AC/DC battery charger/ vehicle to grid (V2G) and to transfer electrical energy between the DC-link (connected to the battery) and the electric traction system as DC/AC inverter. In addition, a bidirectional-interleaved DC/DC converter with dual-loop controller is proposed for interfacing the ESI to a low-voltage battery pack in order to minimize the ripple of the battery current and to improve the efficiency of the DC system with lower inductor size. To validate the performance of the proposed configuration, the indirect field-oriented control (IFOC) based on particle swarm optimization (PSO) is proposed to optimize the efficiency of the AC drive system in PHEVs. The maximum efficiency of the motor is obtained by the evaluation of optimal rotor flux at any operating point, where the PSO is applied to evaluate the optimal flux. Moreover, an improved AC/DC controller based Proportional-Resonant Control (PRC) is proposed in order to reduce the THD of the input current in charger/V2G modes. The proposed configuration is analyzed and its performance is validated using simulated results obtained in MATLAB/ SIMULINK. Furthermore, it is experimentally validated with results obtained from the prototypes that have been developed and built in the laboratory based on TMS320F2808 DSP.

• 한국실내디자인학회논문집
• /
• 제21권1호
• /
• pp.78-85
• /
• 2012

The relevance between organisms and their external environment covers everything including humans, natural and artificial surroundings, regarding which academic and scientific understanding has continued. Relevant elements established by inter-dependence between humans and environment and the unity of life should be translated from the perspective of a whole, not of unit elements or reduction. That is, a space is formed by its own program and assumes sustainable relevance based on interactions between internal and external spaces, not building an independent system. The present study aims to present the feasibility of a potential mutant space formed by invisible arenas between individuals and evolutionary space formation based on an ecological paradigm Accordingly, this study suggested that evolutionary attributes as the major power source of biological changes could verify the virtual multiplicity of a new space formation, and that the potential form generation of hybrid mutant space of emergence and infinite formative capability could be supported. The suggestions made here will hopefully contribute to extending applicability of evolutionary space generation in the field of space design. To derive the potential mutant forms from biological space, a preliminary study was conducted regarding the characteristics of evolutionary form generation. For the purpose of this study, three evolutionary perspectives of reproduction, mutation (variation) and selection were taken. First, the theory of evolution was defined and characterized. Also, the relevance between the characteristics generated and hybrid mutant space was analyzed to consider relevant characteristics. The present study helped to understand that the hybrid mutant space had an evolutionary space structure based on a biological paradigm. It was also found that the mutant space structure built by mutant polymorphism assumed a systematic correlation between space and environment.

• 한국산학기술학회논문지
• /
• 제15권5호
• /
• pp.3139-3145
• /
• 2014

본 논문에서는 가유전체 기판을 이용하여 소형화한 마이크로파 대역의 링 하이브리드 커플러 설계에 대하여 기술한다. 가유전체 기판은 다수의 비어홀을 제 2기판에 삽입하여 유효 커패시턴스를 크게 증가시킨 구조를 갖는다. 가유전체 기판의 유효유전율은 표준형 기판에 비하여 크게 증가하게 되는데, 이에 의하여 동일한 전기적 길이 대비 물리적 길이가 크게 감소하므로 마이크로파 전송선로를 소형화시킬 수 있다. 이런 원리를 마이크로파 무선회로 설계에 적용한 사례를 보이기 위하여 가유전체 기판을 이용하여 3GHz대 링 하이브리드 커플러를 설계하고 실제로 제작 및 측정한 결과를 제시한다. 설계된 소형화된 링 하이브리드 커플러는 표준형에 비하여 전기적 성능은 유사하면서도 65%의 크기를 가진다. 측정된 전력분배비는 각각 -3.05dB와 -3.135dB이며, 두 출력간의 위상차는 동위상일 때 3도, 역위상일 때 176도로 이상적인 값과 매우 유사하다. 이로써 가유전체 기판구조로 소형화된 링 하이브리드 커플러의 설계가 타당함을 보인다.

• 한국산학기술학회논문지
• /
• 제14권6호
• /
• pp.2588-2595
• /
• 2013

기존의 유압식 엘리베이터에서 엘리베이터 카의 하강행정 동안 손실 되는 유압 에너지를 회수하여 재사용하기 위하여 개발한 유압식 엘리베이터용 하이브리드 형 에너지 저감 장치에 대한 성능 특성에 관하여 연구하였다. 회수된 에너지는 축전지에 저장하여 재사용할 수 있도록 구성되어 있으며, 엘리베이터의 구동 조건에 따른 에너지 저감장치의 출력 특성, 효율 및 에너지 회수율 등에 관하여 실험을 통하여 규명하고자 하였다. 본 연구의 결과들은 하강행정 동안 버려지는 에너지의 회수율이 최대 약 54%로 에너지 저감 장치의 압력, 유량, 출력 전압과 전류, 효율 및 에너지 회수율 등과 같은 성능 특성들이 안정적이고 양호하다는 것을 보여주고 있으며, 본 연구를 통하여 유압식 엘리베이터의 에너지 저감 장치를 통하여 하강행정 동안 회수된 에너지를 재사용하데 매우 유용하며, 상용화 가능성이 충분하다는 것을 확인하였다.

• 한국자동차공학회논문집
• /
• 제23권2호
• /
• pp.153-160
• /
• 2015

Hybrid Electric Vehicles(HEVs) have seriously come into prevalence recently as car manufacturers and consumers have become more aware of the environmental and economic problems of conventional vehicles. For the alternative power-train and battery cooling systems in HEVs, an effective thermal management system is required, and many automakers are interested in using Brushless DC(BLDC) motors for cooling fans for the overall traction unit's performance and energy saving capability. This paper presents the development status of BLDC motors as major parts of the power-train, i.e. the engine cooling and battery cooling fans of HEVs. A design that uses BLDC motors for the power-train and each battery cooling fan, is successfully implemented through using electro-magnetic analysis, and prototype BLDC motors are examined. As experimental results, the BLDC motors achieved an efficiency of 85% as engine cooling fans and 72% as a battery thermal management fan motor. The electric cogging noise is significantly reduced by changing the skew of the slot pitch angle and optimizing the magnetic shape.

• 정보처리학회논문지D
• /
• 제17D권6호
• /
• pp.383-394
• /
• 2010

최근 플래시 메모리 기반 SSD(Solid State Disks)는 데이터 처리 속도가 빠르고, 외부 충격에 강하며 전력소모가 작다는 우수한 특성과 함께 그 용량의 증가와 가격 하락으로 인하여 차세대 저장 매체로 부각되고 있다. 하지만 SSD는 하드디스크와는 달리 읽기, 쓰기 및 지우기의 단위 및 수행 시간이 다르며 덮어쓰기가 불가능하다는 특징이 있다. 이 때문에 SSD는 기존의 하드디스크 기반 시스템 상에서는 그 동작의 효율성이 떨어지며, 이를 보완하기 위해 플래시 변환 계층이 설계되었다. 본 논문에서는 플래시 변환 계층의 역할 중 하나인 논리 주소 매핑 기법을 개선하여 SSD의 성능을 높일 수 있는 HAMM(Hybrid Address Mapping Method)를 제안한다. HAMM은 기존에 존재하는 슈퍼 블록 매핑 기법과 블록 매핑 기법의 단점을 보완하고 장점을 살릴 수 있도록 설계된 논리 주소 매핑 기법이다. SSD 시뮬레이터를 제작하여 실험하였으며, 실험을 통하여 HAMM은 같은 크기의 쓰기 버퍼 상에서 슈퍼 블록 매핑 기법에 비해 SSD의 저장공간을 효율적으로 사용하는 것으로 나타났으며, 또한 블록 매핑 기법에 비해 매핑 테이블을 구성하는데 적은 양의 메모리를 사용하면서 비슷한 성능을 보이는 것으로 나타났다.

• Nuclear Engineering and Technology
• /
• 제55권9호
• /
• pp.3423-3440
• /
• 2023

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2003년도 춘계전력전자학술대회 논문집(1)
• /
• pp.389-392
• /
• 2003

A use of micro processor having H-com functions is gradually increased, and this paper describes the digital servo controller applied to linear pulse motor The TMS320LF2407, made by TI(Texas Instruments Co.), is used as a arithmetic unit in control circuit, designed f3r motor drive and available for the implement of high performance and miniaturization. Also, it can allow the sufficient debugging and downloading into control board for independent operation. A current control in order to carry out a position control is of a digital current control mode, and its implement confirmed the servo control performance of position control.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 A
• /
• pp.373-375
• /
• 1997

In this paper, we present IGBT VVVF inverters as a 1C1M propulsion system for electric car. These inverters are composed of high power IGBT's and controlled by compact control units. The control unit performs full digital control by using 32bit DSP and microcontroller. By using CAN-bus, high speed network is constructed within four control units. The stack is simplified and optimized by using plate bus and IGBT driver units of hybrid-type.