• Journal of the Korean Society of Systems Engineering
• /
• v.19 no.2
• /
• 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
• /
• v.11 no.4
• /
• 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.

• Korean Institute of Interior Design Journal
• /
• v.21 no.1
• /
• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.5
• /
• pp.3139-3145
• /
• 2014

This paper describes the design of a size-reduced ring hybrid coupler for microwave band using an artificial dielectric substrate(ADS). ADS structure adopts the second substrate on which has lots of the metalized via-holes. The effective capacitance and effective dielectric constant per unit length of ADS increases compared to the normal substrate due to the via-holes. This enables the physical length of microstrip transmission line to be reduced by adopting ADS instead of the normal substrate. In order to present an example of size-reduction of microwave wireless circuit by ADS, a size-reduced 3GHz ring hybrid coupler is designed, fabricated and measured in this work. The designed coupler has the smaller size from the normal one by 65% due to the ADS, while no critical degradation from ideal performances is observed. The measured power division ratio at two output ports are -3.05dB and -3.135dB, respectively. In addition, the phase differences are 3o for in-phase division and 176o for out of phase split. The measured performances are so similar to ideal ones, and prove the design of size-reduced ring hybrid coupler using ADS is successful.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.6
• /
• pp.2588-2595
• /
• 2013

In a traditional hydraulic elevator, elevator car is descended by down control valve, and the oil hydraulic energy must be lost during the descending stroke. In this paper, the performance characteristics of the hybrid type energy saving unit, is used to save the hydraulic energy which is lost during the descending stroke, for a hydraulic elevator are studied. The energy can be reused as the auxiliary power. The results show that the performance characteristics, such as the pressure, flow rate, output current and voltage, efficiency, and the energy recovery rate of the unit are stable and good as the energy recovery rate is 54%, and the energy saving unit is useful to reuse the saved energy during the descending stroke of elevator car. Also, it was confirmed that the energy saving unit can be deployed on a commercial scale.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.2
• /
• 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.

• The KIPS Transactions:PartD
• /
• v.17D no.6
• /
• pp.383-394
• /
• 2010

Flash memory based SSDs are currently being considered as a promising candidate for replacing hard disks due to several superior features such as shorter access time, lower power consumption and better shock resistance. However, SSDs have different characteristics from hard disk such as difference of unit and time for read, write and erase operation and impossibility for over-writing. Because of these reasons, SSDs have disadvantages on hard disk based systems, so FTL(Flash Translation Layer) is designed to increase SSDs' efficiency. In this paper, we propose an advanced logical address mapping method for increasing SSDs' performance, which is named HAMM(Hybrid Address Mapping Method). HAMM addresses drawbacks of previous block-mapping method and super-block-mapping method and takes advantages of them. We experimented our method on our own SSDs simulator. In the experiments, we confirmed that HAMM uses storage area more efficiently than super-block-mapping method, given the same buffer size. In addition, HAMM used smaller memory than block-mapping method to construct mapping table, demonstrating almost same performance.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• 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.

• Proceedings of the KIPE Conference
• /
• 2003.07a
• /
• 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.

• Proceedings of the KIEE Conference
• /
• 1997.07a
• /
• 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.