• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.10
• /
• pp.1469-1478
• /
• 2015

In this paper, The methodology of Type-2 fuzzy set-based Radial Basis Function Neural Network(T2RBFNN) is proposed for Sewage Treatment Process and the simulator is developed for application to the real-world sewage treatment plant by using the proposed model. The proposed model has robust characteristic than conventional RBFNN. architecture of network consist of three layers such as input layer, hidden layer and output layer of RBFNN, and Type-2 fuzzy set is applied to receptive field in contrast with conventional radial basis function. In addition, the connection weights of the proposed model are defined as linear polynomial function, and then are learned through Back-Propagation(BP). Type reduction is carried out by using Karnik and Mendel(KM) algorithm between hidden layer and output layer. Sewage treatment data obtained from real-world sewage treatment plant is employed to evaluate performance of the proposed model, and their results are analyzed as well as compared with those of conventional RBFNN.

• Nuclear Engineering and Technology
• /
• v.52 no.1
• /
• pp.78-86
• /
• 2020

The operation and monitoring (OM) interface is the digital medium between nuclear power system and operators. The cognitive load of OM interface has an important effect on the operation errors made by operator during OM task between operator and computer. The cognitive load model of OM interface is constructed for analysing the composition and influencing factors of OM interface cognitive load. And to study the coping strategies and methods for cognitive load of nuclear power system. An experiment method based on eye movement is proposed to measure the cognitive load of OM interface. Experiment case is carried out with 20 subjects and typical OM interface of a nuclear power system simulator. The OM interface is optimized based on the experiment results. And the results comparison between the original OM interface and the optimized OM interface shows that the cognitive load model and proposed method is valuable contributions in reducing the cognitive load and improving the interaction efficiency of OM tasks.

• Journal of the military operations research society of Korea
• /
• v.33 no.1
• /
• pp.59-74
• /
• 2007

Computer simulation models are in general quite complex and time-consuming to run, and therefore, a simpler meta-model is usually constructed for further analysis. In this paper, JANUS, a war-game simulator, is used to describe a certain tank combat situation. Then, second-order response surface and artificial neural network meta-models are developed using the data from eight different experimental designs. Relative performances of the developed meta-models are compared in terms of the mean squared error of prediction. Computational results indicate that, for the given problem, the second-order response surface meta-model generally performs better than the neural network, and the orthogonal array-based Latin hypercube design(LHD) or LHD using maximin distance criterion may be recommended.

• Journal of the Korean Society of Radiology
• /
• v.1 no.3
• /
• pp.11-16
• /
• 2007

In this study, the potential of a newly developed simulation toolkit, GATE for the simulation of electronic portal imaging devices (EPID) in radiation therapy was evaluated by characterizing the performance of the metal plate/phosphor screen detector for EPID. We compared the performances of the GATE simulator against MCNP4B code and experimental data obtained with the EPID system in order to validate its use for radiation therapy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.3
• /
• pp.555-562
• /
• 2007

In order to display Bayer input stream received from CMOS image sensor to the display device, image signal processing must be performed. That is, the hardware performing the image signal processing for Bayer data is called ISP(Image Signal Processor). We can see real image through ISP processing. ISP executes functionalities for gamma correction, interpolation, color space conversion, image effect, image scale, AWB, AE and AF. In this paper, we obtained the optimum algorithm through software verification of ISP module for CMOS camera image sensor and described using VHDL and verified in ModelSim6.0a simulator. Also we downloaded into Xilinx XCV-1000e for the designed ISP module and completed the board level verification using PCI interface.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.11a
• /
• pp.43-50
• /
• 2003

시뮬레이션의 궁극적인 목표인 분산 시뮬레이션은 Virtual Simulation과 Constructive Simulation 이외에 Live Simulation이 동시에 참여하여 동일한 환경 내에서 상호작용 하는 것을 추구하고 있다. 따라서 서로 다른 목적과 기술로 제작된 시뮬레이션은 통합된 환경 내에서 사실적으로 상호작용 해야만 할 것이다. 통합 환경(Synthetic Environment)은 시각적 영상을 표현하기 위한 Visual Database 이상의 의미를 내포하고 있다. 상호운용성(Interoperability)은 타 Model 및 Simulation에서 부터 제공되는 기능을 사용하거나 기능을 제공할 수 있는 유용성(Availability)을 뜻하기 때문에 표준화된 통합 환경의 사용 및 교환을 요구한다. 1980년대 중반, 미 국방성은 Image Generator 제작 회사마다 독자적인 데이터베이스 포맷을 사용함으로 인해 시뮬레이터 데이터베이스의 중복성이 야기되고 있다는 것을 지적하고 통합 환경 데이터 교환 문제를 해결하기 위한 최초의 관련 연구를 수행하였다. Virtual Simulation에서 막대한 비용이 소모되는 시뮬레이터 데이터베이스의 제작 및 유지 보수에 들어가는 이중적인 비용 절감에 대한 관심은 최근 SEDRIS에 이르러 표준 교환에 대한 명세의 필요성이 보다 구체화되어 지구상에 존재하는 각종 주변 환경을 기술하기 위한 통합 환경표현 및 교환의 표준화가 진행되고 있다. 국내에서는 문화콘텐츠진흥원, 한국게임산업개발원, 한국전자통신연구원, 국방과학연구소, 서울대, 아주대, 세종대 등을 중심으로 연구가 진행 중이며, 그중 세종대학교는 SEDRIS 데이터로 사용될 원본 데이터의 충실도와 신뢰도를 향상시킬 수 있는 방법을 연구하고 있다. SEDRIS는 그 응용가능성이 무궁무진하여 향후 인공적인 가상환경을 대표하는 용어로 사용될 것이며, 공개된 표준을 통한 소스 데이터의 공유로 상호운용성을 위한 초석을 제공하여 궁극적으로는 비용 절감 효과가 있을 것으로 전망된다.

• Journal of the Society of Naval Architects of Korea
• /
• v.42 no.5 s.143
• /
• pp.516-527
• /
• 2005

It has been estimated that up to $80\%$ of all marine accidents have human elements as a cause. Out of these, human elements of crew fatigue is one of the main causes of marine accident. Crew fatigue involves sleep, schedule, workload, off-time, alcohol, health and stress. With a ship handling simulator, the effect of alcohol on ship operational performance is studied for each 0.05 and 0.08 $\%$ blood alcohol concentrations(BAC). The main effect of alcohol was found that ship operational performance was significantly impaired by alcohol compared to that in the non-alcohol condition. The results of this research can be used as basic data to minimize marine accidents.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.4
• /
• pp.40-45
• /
• 2019

The smart factory has developed with the help of several technologies such as automation, artificial intelligence, big data, smart sensors and communication protocols. The Internet of things(IOT) among communication protocols has become the key factor for the seamless integration of various manufacturing equipment. Therefore, it is important that the IOT cooperate with the standards of communication protocols proposed by the SEMI in the semiconductor industry. In this paper, we suggest a novel reference model of the communication protocols for semiconductor equipment by introducing an IOT service layer. With the IOT service layer, we can use the functions and the additional services provided by the IOT standards that give the inter-operability between factory machines and host computers. We implement the standard of the communication protocols for semiconductor equipment with the IOT service layer by using ns3 simulator. It concludes that it is necessary to provide the platform for the IOT service layer to deploy efficiently the proposed reference model of the communication protocols.

• Nuclear Engineering and Technology
• /
• v.37 no.1
• /
• pp.79-90
• /
• 2005

In this paper are reviewed the current status of nuclear fuel management and reactor operational aid tools. In addition, we indicate deficiencies in current capabilities and what future research is judged warranted. For the nuclear fuel management review the focus is on light water reactors and the utilization of stochastic optimization methods applied to the lattice, fuel bundle, core loading pattern, and for BWRs the control rod pattern/core flow design decision making problems. Significant progress in addressing separately each of these design problems on a single cycle basis is noted; however, the outstanding challenge of addressing the integrated design problem over multiple cycles under conditions of uncertainty remains to be addressed. For the reactor operational aid tools review the focus is on core simulators, used to both process core instrumentation signals and as an operator aid to predict future core behaviors under various operational strategies. After briefly reviewing the current status of capabilities, a more in depth review of adaptive core simulation capabilities, where core simulator input data are adjusted within their known uncertainties to improved agreement between prediction and measurement, is presented. This is done in support of the belief that further development of adaptive core simulation capabilities is required to further significantly advance the utility of core simulators in support of reactor operational aid tools.

• Nuclear Engineering and Technology
• /
• v.52 no.12
• /
• pp.2709-2716
• /
• 2020

Compositions of large nuclear cores (e.g. boiling water reactors) are highly heterogeneous in terms of fuel composition, control rod insertions and flow regimes. For this reason, they usually lack high order of symmetry (e.g. 1/4, 1/8) making it difficult to estimate their neutronic parameters for large spaces of possible loading patterns. A detailed hyperparameter optimization technique (a combination of manual and Gaussian process search) is used to train and optimize deep neural networks for the prediction of three neutronic parameters for the Ringhals-1 BWR unit: power peaking factors (PPF), control rod bank level, and cycle length. Simulation data is generated based on half-symmetry using PARCS core simulator by shuffling a total of 196 assemblies. The results demonstrate a promising performance by the deep networks as acceptable mean absolute error values are found for the global maximum PPF (~0.2) and for the radially and axially averaged PPF (~0.05). The mean difference between targets and predictions for the control rod level is about 5% insertion depth. Lastly, cycle length labels are predicted with 82% accuracy. The results also demonstrate that 10,000 samples are adequate to capture about 80% of the high-dimensional space, with minor improvements found for larger number of samples. The promising findings of this work prove the ability of deep neural networks to resolve high dimensionality issues of large cores in the nuclear area.