• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.22-30
• /
• 2022

In order to prevent chemical accidents caused by human error, a chemical accident prevention and response training program using advanced technology was developed. After designing a virtual process based on the previously built pilot plant, chemical accident response contents were developed. A part of the pilot facility was remodeled for content realization and a remote control function was given. In addition, a DCS program that can control facilities in a virtual environment was developed, and chemical process operator training (OTS) that can finally respond to virtual chemical accidents was developed in conjunction with AR. Through this, trainees can build driving skills by directly operating the device, and by responding to virtual chemical accidents, they can develop emergency response capabilities. If the next-generation OTS like this study is widely distributed in the chemical industry, it is expected to greatly contribute to the prevention of chemical accidents caused by human error.

• Nuclear Engineering and Technology
• /
• v.53 no.10
• /
• pp.3275-3285
• /
• 2021

A Nuclear Power Plant (NPP) is a complex dynamic system-of-systems with highly nonlinear behaviors. In order to control the plant operation under both normal and abnormal conditions, the different systems in NPPs (e.g., the reactor core components, primary and secondary coolant systems) are usually monitored continuously, resulting in very large amounts of data. This situation makes it possible to integrate relevant qualitative and quantitative knowledge with artificial intelligence techniques to provide faster and more accurate behavior predictions, leading to more rapid decisions, based on actual NPP operation data. Data-driven models (DDM) rely on artificial intelligence to learn autonomously based on patterns in data, and they represent alternatives to physics-based models that typically require significant computational resources and might not fully represent the actual operation conditions of an NPP. In this study, a feed-forward backpropagation artificial neural network (ANN) model was trained to simulate the interaction between the reactor core and the primary and secondary coolant systems in a pressurized water reactor. The transients used for model training included perturbations in reactivity, steam valve coefficient, reactor core inlet temperature, and steam generator inlet temperature. Uncertainties of the plant physical parameters and operating conditions were also incorporated in these transients. Eight training functions were adopted during the training stage to develop the most efficient network. The developed ANN model predictions were subsequently tested successfully considering different new transients. Overall, through prompt prediction of NPP behavior under different transients, the study aims at demonstrating the potential of artificial intelligence to empower rapid emergency response planning and risk mitigation strategies.

• Journal of the Korean Society of Industry Convergence
• /
• v.14 no.4
• /
• pp.157-165
• /
• 2011

The study figures out the alternatives of training BIM design experts which is the biggest obstacle in training manpower of professional BIM designer, the largest problem when the plant introduce BIM design about the change in Construction Environment by Equipment Based BIM Design in reality of design followed by equipment based BIM design, education institution plan. BIM is the system which is built to make these information be used easier and technique which enables design construction and maintenance in 3-dimensional virtual space by designing buildings in 3-dimensional space, and by data-basing the generated information of every life-cycle information. As the essential contents of the study, educational institutions with the public authority should invest the opening of educational programs, recruit of experts and development of textbooks from a long-term perspective. And also, the role of public institution is important above all for the development of construction industry.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.243-247
• /
• 1992

This paper describes a neural network based control scheme with MRAC. The system consists of two neural network; one is for identifier and the other is for controller. Identification is firstly performed to learn the behavior of the nonlinear plant. Neural net controller is next trained by backpropagating the error at the output of plant through the identifier. Also the training method used in this paper repeatedly updates weights of neural network to track the reference model.

• Journal of the Korean Society of Safety
• /
• v.29 no.6
• /
• pp.172-178
• /
• 2014

In terms of an accident management, the cases causing severe core damage need to be analyzed and arranged systematically for an easy access to the results since the Three Mile Island (TMI) accident. The objectives of this paper are to explain how to identify the plant response and cope with its vulnerabilities using the probabilistic safety assessment (PSA) quantified results and severe accident database SARDB(Severe Accident Risk Data Bank) based on sequences analysis results. Although PSA has been performed for the Korean Standard Power Plants (KSNPs), and that it considered the necessary sequences for an assessment of the containment integrity. The developed Database (DB) system includes a graphical display for a plant and equipment status, previous research results by a knowledge-based technique, and the expected plant behaviour. The plant model used in this paper is oriented to the cases of loss of coolant accident (LOCA) is be used as a training simulator for a severe accident management.

• Nuclear Engineering and Technology
• /
• v.56 no.2
• /
• pp.558-567
• /
• 2024

Diagnostic support systems are being researched to assist operators in identifying and responding to abnormal events in a nuclear power plant. Most studies to date have considered single abnormal events only, for which it is relatively straightforward to obtain data to train the deep learning model of the diagnostic support system. However, cases in which multiple abnormal events occur must also be considered, for which obtaining training data becomes difficult due to the large number of combinations of possible abnormal events. This study proposes an approach to maintain diagnostic performance for multiple abnormal events by training a deep learning model with data on single abnormal events only. The proposed approach is applied to an existing algorithm that can perform feature selection and multi-label classification. We choose an extremely randomized trees classifier to select dedicated monitoring parameters for target abnormal events. In diagnosing each event occurrence independently, two-channel convolutional neural networks are employed as sub-models. The algorithm was tested in a case study with various scenarios, including single and multiple abnormal events. Results demonstrated that the proposed approach maintained diagnostic performance for 15 single abnormal events and significantly improved performance for 105 multiple abnormal events compared to the base model.

• Journal of the Korea Society for Simulation
• /
• v.6 no.1
• /
• pp.85-96
• /
• 1997

Designing and constructing a proper simulator for real power plants requires extensive research in human engineering and computer science and integration of different fields of technologies such as system analysis, operational knowledge for nuclear plant, etc. A full scope replica type simulator for nuclear power plant is developed. The simulator has the same feature and operational functions as one in the main control room (MCR) of a reference power plant. The simulator provides the necessary training to recover or reduce damages from accidents that usually are unpredictable. This paper describes the configurations and characteristics for the simulator that is developed for Younggwang Nuclear Power Plant #3,4 which is the basic model of the Korean Nuclear Power Plant. The paper also describes technical aspects of Auto Code Generator that is used for developing the simulator. The successful development of the simulator will contribute to improve safety in operation of nuclear power plants.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.1
• /
• pp.42-53
• /
• 1996

The paper presents a speed control system of vector controlled induct- ion motor using neural networks. The main feature of proposed speed control system is a Neural Network Controller(NNC) which supplies torque current to induction motor and Neural Network Emulator(NNE) which captures the forward dynamics of induction motor. A back propagation training algorithm is employed to train the NNE and NNC. In order to determine the NNC output error, plant(induction motor) output error can be back propagated through the NNE. The NNC and NNE for speed control of vector controlled induction motor is carried out by TMS320C30 DSP and IGBT current regulated PWM inverter. Through computer simulation and experimental results, it is verified that proposed speed control system is robust to the load variation. (author). refs., figs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.571-573
• /
• 2015

본 연구에서는 플랜트 운영 중 발생할 수 있는 다양한 인적에러를 최소화하고, 예측하기 힘든 사고 발생 시 운전자의 대응과 사고피해 확산을 방지할 수 있는 플랜트 안전훈련 시스템의 설계 방안과 이를 구현하는 플랫폼에 관한 연구를 소개한다. 제안하는 플랫폼은 기존에 활용 중인 플랜트 운영자 훈련 시스템(OTS : Operator Training System)과 비교하여, 관제실 운영자와 현장 조업자가 동시에 상호 유기적인 훈련을 가능케 하는 안전훈련 시스템 개발을 목표로 하며, 추후 서브 시스템의 구현과 통합과정을 통해 본 훈련 시스템 플랫폼의 실용성을 검증할 계획이다.

• Proceedings of the KIPE Conference
• /
• 2000.07a
• /
• pp.249-252
• /
• 2000

원자력 교육원 #2(KNPEC-2) 시뮬레이터는 1980년도 중반에 웨스팅하우스에 의해 공급되어 계속 사용되어 오다가 현재 성능개선 연구가 진행 중이다. 이번 성능개선을 통해 기존의 컴퓨터 시스템(Gould MPX)와 소프트웨어의 전면 교체가 이루어지고 있으며 최적 계산 코드를 이용한 실시간 열수력 모델 (ARTS; Advanced Real-Time Thermal-Hydraulics Simulation) 개발 , 2-Group 3D 실시간 노심모델(REMARK ; REal Time Multigroup Advanced Reactor Kinetics)를 이용한 노심 주기개선 (Cycle Update) 가상현실 기술 등을 이용한 컴퓨터 교육지원 시스템(CATS: Computer Assister Training System)등 새로운 시도가 이루어지고 있으며 본 논문은 이러한 새로운 시도가 이루어지고 있으며 본 논문은 이러한 새로운 시도들 및 그 결과에 대해 기술하고 있다. 기준발전소(Reference Plant)인 영광 1호기 12주기의 노심모델로 주기개선(Cycle Update)을 위한 REMARK의 입력자료 생성을 위해 핵설계 전산체계인 APA(ALPHA-PHOENIX-ANC) 시스템의 출력으로부터 자동으로 REMARK 입력데이타를 생성하기 위한 GUI툴 개발하였다. 또 이를 이용하여 개발된 노심모델은 최적계산코드(RETRAn 3D) 의 열수력 해법을 이용하여 개발된 NSSS 열수력코드(ARTS) 와 결합(Integration) 되어 안정 및 과도 상태 시험에 사용되었으며 원자로 냉각재 펌프 정지등의 몇 가지 과도 시험 계산결과 기존 해석 결과와 잘 일치하였다 중앙제어실(MCR; Main Control Room)내의 운전원 행동만 훈련하도록 되어있는 기존시뮬레이터의 한계를 극복하기 위해 가상현실 (VR) 저작도구를 이용한 발전소 현장 내부를 표현하는 가상발전소 (Virtual Plant) 발전소 현장에 소재하여 기존 시뮬레이터의 모의한계 밖에 있던 패널을 표현한 가상판넬(Virtual Panel)등과 강의실에서 발전소 모의 훈련을 가능케 하기 위해 가상현실 기술을 이용한 컴퓨터 지원 교육훈력 시스템(CATS ; Computer Assister Training System)을 개발 중이며 일부 개발부분을 소개하였다.