• 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.

• Nuclear Engineering and Technology
• /
• v.50 no.3
• /
• pp.319-326
• /
• 2018

Since the Fukushima Daiichi nuclear disaster, concern and worry about multiunit accidents have been increasing. Korea has a higher urgency to evaluate its site risk because its number of nuclear power plants (NPPs) and population density are higher than those in other countries. Since the 1980s, technical documents have been published on multiunit probabilistic safety assessment (PSA), but the Fukushima accident accelerated research on multiunit PSA. It is therefore necessary to summarize the present situation and draw implications for further research. This article reviews journal and conference papers on multiunit or site risk evaluation published between 2011 and 2016. The contents of the reviewed literature are classified as research status, initiators, and methodologies representing dependencies, and the insights and conclusions are consolidated. As of 2017, the regulatory authority and nuclear power utility have launched a full-scale project to assess multiunit risk in Korea. This article provides comprehensive reference materials on the necessary enabling technology for subsequent studies of multiunit or site risk assessment.

• Journal of Radiation Protection and Research
• /
• v.28 no.3
• /
• pp.189-197
• /
• 2003

The Level 3 PSA being termed accident consequence analysis is defined to assess effects on health and environment caused by radioisotopes released from severe accidents of nuclear power plants. In this study consequence analysis on health effects depending on release characteristics of radioisotopes has been peformed using the 3 MACCS code in severe accidents. The results of this study may contribute to identifying the relative importance of various parameters occurred in consequence analysis as well as to assessing risk reduction accident management strategies. Especially three parameters for the purpose of consequence analysis, such as the release height, the heat content, and the duration time, are used to analyze the variation of early fatalities and latent cancer fatalities. Also, in this study risk assessment using the concept, 'products of uncertainty and consequences', has been performed using consequence of MACCS and frequency on source term category 19 scenarios from IPE (Individual Plant Examination) analysis.

• Nuclear Engineering and Technology
• /
• v.55 no.3
• /
• pp.1167-1180
• /
• 2023

Due to the tightened regulatory environment since the Fukushima accident, the capacity factor of Korean nuclear power plants has been declining since 2011. To overcome this circumstance, a shift from 18-month to 24-month cycle operation is being considered in Korea. Therefore, in this study, loading patterns(LPs) for 24-month cycle operation of the Korean standard nuclear power plant(OPR-1000) are suggested and economic evaluations are performed. A single-zone LP with 89 fresh fuels was evaluated to be optimal for 24-month operation of OPR-1000 in terms of economic gain. The 24-month operation of OPR-1000 with this LP gives a profit of 7.073 million dollars per year compared to 18-month operation.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.9 no.4
• /
• pp.231-236
• /
• 2011

When the Fukushima nuclear power plant accident occurred in March of 2011, a hydrogen explosion in the reactor building at the 4th unit of Fukushima plants led to a big surprise because the full core of the unit 4 reactor had been moved and stored underwater at the spent nuclear fuel storage pool for periodic maintenance. It was because the possible criticality in the fuel storage pool by coolant loss may yield more severe situation than the similar accident happened inside the reactor vessel. Fortunately, it was assured to be evitable to an anxious situation by a look of water filled in the storage pool later. In the paper, the safety state of the spent fuel storage pool and rack structures of the domestic nuclear plants would be roughly reviewed and compared with the Fukushima plant case by engineering viewpoint of potential severe accidents.

• Journal of Fisheries and Marine Sciences Education
• /
• v.29 no.3
• /
• pp.920-931
• /
• 2017

Since the export of Korean-type APR 1400 in 2009 to the UAE, Korea has been achieved management performance, quality inspections, training, nuclear fuel exports for the nuclear power plant. Despite this apparent growth, there are lacking of the research on the marine transportation of radioactive waste. And the terrible accident at the Japan nuclear power plant in 2011 has caused another reconsideration such as emergency response training and plan, reinforcement of safety regulation. According to the Korean government aims to rebuild the appropriate regulation, training, education that is necessary in order to ensure the safety of marine transportation of radioactive waste. Therefore, this study analyzed the various problems identified by the team of experts for the radioactive waste and marine field, the investigation of relevant legal basis, the need for emergency response training for the person in charge of radioactive waste and suggested the simulation-based interactive curriculum during the process of safety verification related to the marine transport of mid- and low-level radioactive waste generated at the Yeon-ggwang nuclear power(Hanbit) plant in 2015.

• Nuclear Engineering and Technology
• /
• v.23 no.3
• /
• pp.285-298
• /
• 1991

An example application of the fuzzy set theory is first made to a simple portion of a given accident progression event tree with typical qualitative fuzzy input data, and thereby computational algorithms suitable for application of the fuzzy set theory to the accident progression event tree analysis are identified and illustrated with example applications. Then the procedure used in the simple example is extended to extremely complex accident progression event trees with a number of phenomenological uncertainty issues, i.e., a typical plant damage state‘SEC’of the Zion Nuclear Power Plant risk assessment. The results show that the fuzzy averages of the fuzzy outcomes are very close to the mean values obtained by current methods. The main purpose of this paper is to provide a formal procedure for application of the fuzzy set theory to accident progression event trees with imprecise and qualitative branch probabilities and/or with a number of phenomenological uncertainty issues.

• Journal of the Korean Society of Systems Engineering
• /
• v.11 no.1
• /
• pp.1-7
• /
• 2015

The purpose of this paper is to present the results of reengineering of the YGN 3&4 (Yonggwang Nuclear Power Plant, Units 3&4) SDS (Safety Depressurization System) retrofit design and to make recommendations for the improvement in design and design procedure implementing the Systems Engineering (SE) process. YGN 3&4 is a basic model for OPR1000 (the Korean standard 1000 MWe plant). The basic model, herein, represents the reference plant for the OPR1000 development. In the middle of the YGN 3&4 construction, the Korean Nuclear Regulatory Body requested a retrofit of this plant with a means to rapidly depressurize the plant in conformance with a severe accident mitigation requirement. For the reengineering of the SDS in YGN 3&4, V-model and functional and physical architectures have been developed. A SE decision making method has been used for the selection of SDS valves. Finally, recommendations have been made to improve OPR1000 design for the improved operation and enhanced safety.

• Journal of Korean Institute of Industrial Engineers
• /
• v.16 no.2
• /
• pp.135-147
• /
• 1990

A nuclear power plant can be viewed as a large complex man-machine system where high system reliability is obtained by ensuring that sub-systems are designed to operate at a very high level of performance. The chance of severe accident involving at least partial core-melt is very low but once it happens the consequence is very catastrophic. The prediction of risk in low probability, high-risk incidents must be examined in the contest of general engineering knowledge and operational experience. Engineering knowledge forms part of the prior information that must be quantified and then updated by statistical evidence gathered from operational experience. Recently, Bayesian procedures have been used to estimate rate of accident and to predict future risks. The Bayesian procedure has advantages in that it efficiently incorporates experts opinions and, if properly applied, it adaptively updates the model parameters such as the rate or probability of accidents. But at the same time it has the disadvantages of computational complexity. The predictive distribution for the time to next incident can not always be expected to end up with a nice closed form even with conjugate priors. Thus we often encounter a numerical integration problem with high dimensions to obtain a predictive distribution, which is practically unsolvable for a model that involves many parameters. In order to circumvent this difficulty, we propose a method of approximation that essentially breaks down a problem involving many integrations into several repetitive steps so that each step involves only a small number of integrations.

• Nuclear Engineering and Technology
• /
• v.53 no.8
• /
• pp.2534-2546
• /
• 2021

Nuclear emergency preparedness and response is an essential part to ensure the safety of nuclear power plant (NPP). Key support technologies of nuclear emergency decision-making usually consist of accident diagnosis, source term estimation, accident consequence assessment, and protective action recommendation. Source term estimation is almost the most difficult part among them. For example, bad communication, incomplete information, as well as complicated accident scenario make it hard to determine the reactor status and estimate the source term timely in the Fukushima accident. Subsequently, it leads to the hard decision on how to take appropriate emergency response actions. Hence, this paper aims to develop a method for rapid source term estimation to support nuclear emergency decision making in pressurized water reactor NPP. The method aims to make our knowledge on NPP provide better support nuclear emergency. Firstly, this paper studies how to build a Bayesian network model for the NPP based on professional knowledge and engineering knowledge. This paper presents a method transforming the PRA model (event trees and fault trees) into a corresponding Bayesian network model. To solve the problem that some physical phenomena which are modeled as pivotal events in level 2 PRA, cannot find sensors associated directly with their occurrence, a weighted assignment approach based on expert assessment is proposed in this paper. Secondly, the monitoring data of NPP are provided to the Bayesian network model, the real-time status of pivotal events and initiating events can be determined based on the junction tree algorithm. Thirdly, since PRA knowledge can link the accident sequences to the possible release categories, the proposed method is capable to find the most likely release category for the candidate accidents scenarios, namely the source term. The probabilities of possible accident sequences and the source term are calculated. Finally, the prototype software is checked against several sets of accident scenario data which are generated by the simulator of AP1000-NPP, including large loss of coolant accident, loss of main feedwater, main steam line break, and steam generator tube rupture. The results show that the proposed method for rapid source term estimation under nuclear emergency decision making is promising.