• Nuclear Engineering and Technology
• /
• v.56 no.6
• /
• pp.1989-2001
• /
• 2024

Artificial intelligence (AI) techniques are now being considered in the nuclear field, but application faces with the lack of actual plant data. For this reason, most previous studies on AI applications in nuclear power plants (NPPs) have relied on simulators or thermal-hydraulic codes to mimic the plants. However, it remains uncertain whether an AI model trained using a simulator can properly work in an actual NPP. To address this issue, this study suggests the use of metadata, which can give information about parameter trends. Referred to here as robust AI, this concept started with the idea that although the absolute value of a plant parameter differs between a simulator and actual NPP, the parameter trend is identical under the same scenario. Based on the proposed robust AI, this study designs an event diagnosis algorithm to classify abnormal and emergency scenarios in NPPs using prototypical learning. The algorithm was trained using a simulator referencing a Westinghouse 990 MWe reactor and then tested in different environments in Advanced Power Reactor 1400 MWe simulators. The algorithm demonstrated robustness with 100 % diagnostic accuracy (117 out of 117 scenarios). This indicates the potential of the robust AI-based algorithm to be used in actual plants.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.10 no.1
• /
• pp.37-43
• /
• 2014

Nuclear power plants(NPPs) are consisted of power production functions and safety functions preventing leakage of radiation. Operators working in NPPs shall maintain these functions during an operation period through various activities such as improvement & modification, corrective maintenance, preventive maintenance and surveillance test. According to the performance of these work activities, there are configuration changes in NPPs systems. Its changes cause the increase of safety risks(CDF) and plant trip risks. Recently, the importance of risk management is increasing gradually in the operation process of NPPs. Therefore, this paper presents the work management methods using the various risk monitoring systems during power operation and overhaul period. Also this paper suggests the optimum application ways of risk systems for work management.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1997.05a
• /
• pp.611-616
• /
• 1997

The Level 1 probabilistic safety assessment(PSA) for Wolsong(WS) 2/3/4 nuclear power plant(NPPs) in design stage is performed using the methodologies being equivalent to PWR PSA. Accident sequence evaluation program(ASEP) human reliability analysis(HRA) procedure and technique for human error rate prediction(THERP) are used in HRA of WS 2/3/4 NPPs PSA. The purpose of this paper is to introduce the procedure and methodology of HRA in WS 2/3/4 NPPs PSA. Also, this paper describes the interim results of importance analysis for human actions modeled in WS 2/3/4 PSA and the findings and recommendations of administrative control of secondary control area from the view of human factors.

• Corrosion Science and Technology
• /
• v.12 no.3
• /
• pp.142-148
• /
• 2013

Safety is a major concern in Nuclear Power Plants (NPPs). Piping systems in NPPs are very complex and composed of many components such as tees, elbows, expanders and straight pipes. The high pressure and high temperature water flows inside piping components. As high speed water flows inside piping, the pipe wall thinning occurs in various reasons such as FAC (Flow Accelerated Corrosion), LDIE (Liquid Droplet Impingement Erosion) and Flashing. To inspect the wall thinning phenomenon and protect the piping from damages, piping components are checked by UT measurement in every overhaul. During every overhaul, approximately 200~300 components (40,000~60,000 UT data) are examined in NPPs. There are some methods from EPRI for evaluating wear rate of components. However, only few studies have been conducted to find out the raw data reliability for the wear rate evaluation. Securing the reliable raw data is the key factor for a reasonable evaluation. This paper suggests the reliability analysis method for the repeatedly measured data for wear rate evaluation.

• Nuclear Engineering and Technology
• /
• v.36 no.1
• /
• pp.112-120
• /
• 2004

The purpose of this paper is to analyze the piping failure frequency for the main feedwater system in domestic nuclear power plants(NPPs) for the application to an in-service inspection(ISI), leak before break(LBB) concept, aging management program(AMP), and probabilistic safety analysis(PSA). First, a database was developed for piping failure events in domestic NPPs, and 23 domestic piping failure events were collected. Among the 23 events, 12 locations of wall thinning due to flow accelerated corrosion(FAC) were identified in the main feedwater system in 4 domestic WH 3-loop NPPs. Two types of the piping failure frequency such as the damage frequency and rupture frequency were considered in this study. The damage frequency was calculated from both the plant population data and damage(s) including crack, wall thinning, leak, and/or rupture, while the rupture frequency was estimated by using both the well-known Jeffreys method and a new method considering the degradation due to FAC. The results showed that the damage frequencies based on the number of the base metal piping susceptible to FAC ranged from $1.26{\times}10^{-3}/cr.yr\;to\;3.91{\times}10^{-3}/cr.yr$ for the main feedwater system of domestic WH 3-loop NPPs. The rupture frequencies obtained from the Jeffreys method for the main feedwater system were $1.01{\times}10^{-2}/cr.yr\;and\;4.54{\times}10^{-3}/cr.yr$ for the domestic WH 3-loop NPPs and all the other domestic PWR NPPs respectively, while those from the new method considering the degradation were higher than those from the Jeffreys method by about an order of one.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1998.05a
• /
• pp.838-843
• /
• 1998

Risk importance measures are widely wed to rank risk contributors in risk-based applications. Typically, Fussell-Vesely (F-V) importance and risk achievement worth (RAW) are used in the component importance raking for the reliability centered maintenance (RCM) analysis of safety system in nuclear power plants (NPPs). This study was performed as part of feasibility study on RCM for domestic NPPs, which is focused on the component importance ranking approach the maintenance recommendation. The approach of modulizing faulting tree basic events was applied in the simplification process of the PSA model and the validity of the approach was evaluated As a result of the case study, this paper included the importance and the maintenance recommendations for the safety-related equipments associated with safety injection and containment spray in large loss of coolant accident sequences.

• Nuclear Engineering and Technology
• /
• v.46 no.6
• /
• pp.737-752
• /
• 2014

As condition-based maintenance (CBM) has risen as a new trend, there has been an active movement to apply information technology for effective implementation of CBM in power plants. This motivation is widespread in operations and maintenance, including monitoring, diagnosis, prognosis, and decision-making on asset management. Thermal efficiency analysis in nuclear power plants (NPPs) is a longstanding concern being updated with new methodologies in an advanced IT environment. It is also a prominent way to differentiate competitiveness in terms of operations and maintenance costs. Although thermal performance tests implemented using industrial codes and standards can provide officially trustworthy results, they are essentially resource-consuming and maybe even a hind-sighted technique rather than a foresighted one, considering their periodicity. Therefore, if more accurate performance monitoring can be achieved using advanced data analysis techniques, we can expect more optimized operations and maintenance. This paper proposes a framework and describes associated methodologies for in-situ thermal performance analysis, which differs from conventional performance monitoring. The methodologies are effective for monitoring, diagnosis, and prognosis in pursuit of CBM. Our enabling techniques cover the intelligent removal of random and systematic errors, deviation detection between a best condition and a currently measured condition, degradation diagnosis using a structured knowledge base, and prognosis for decision-making about maintenance tasks. We also discuss how our new methods can be incorporated with existing performance tests. We provide guidance and directions for developers and end-users interested in in-situ thermal performance management, particularly in NPPs with large steam turbines.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.4
• /
• pp.71-79
• /
• 2011

This paper proposes a reliability enhancement of industrial real-time Ethernet using master redundancy method for NPPs(Nuclear Power Plants). In this paper, Ethernet Powerlink is investigated for distributed control systems for NPPs considering real-time and reliability performance. The proposed method can reduce a master switch-over time using PReq signal when Ethernet Powerlink master(Managing Node) failure was occurred. Using the OPNET simulation results, the performance enhancement of master switch-over time of Ethernet Powerlink is verified for NPPs.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2058-2060
• /
• 2002

The demand for safety and reliability of Nuclear Power Plants (NPPs) has been constantly increasing and economical operation is also an important issue. Developing and adopting predictive maintenance technology for the major systems or equipment is considered as one way to achieve these goals. This paper suggests the predictive maintenance methodology that can be applied to NPPs and describes a sample application of the Rod Control System (RCS) to verify the effectiveness of the methodology. It is expected that the same methodology can be adopted for other systems of NPPs and general industry fields when its effectiveness is verified.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.493-505
• /
• 2023

Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.