• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2096-2106
• /
• 2023

Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.

• Journal of the Korean Society of Safety
• /
• v.34 no.5
• /
• pp.167-174
• /
• 2019

Compared to a single nuclear power plant (NPP) risk, the commonalities existing in the multiple NPPs attribute the characteristics of the multi-unit risk. If there is no commonality among the multiple NPPs, there will be no dependency among the risks of multiple NPPs. Therefore, understanding the commonality causing multi-unit events is essential to assessing the multi-unit risk, and identifying the characteristics of the multi-unit risk is necessary not only to select the scope and method for the multi-unit risk assessment, but also to analyze the data of the multi-unit events. In order to develop Korea-specific multi-unit risk assessment technology, we analyze the multi-unit commonalities included in the operational experiences of domestic NPPs. We identified 58 cases of multi-unit events through detailed review of domestic nuclear power plant event reports over the past 10 years, and the multi-unit events were classified into six commonalities to identify Korea-specific characteristics of multi-unit events. The identified characteristics can be used to understand and manage domestic multi-unit risks. It can also be used as a basis for modeling multi-unit events for multi-unit risk assessment.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3599-3616
• /
• 2023

After a nuclear power plant (NPP) accident, it would be helpful to predict the movement of the radioactive plume emitted from the NPP as accurately as possible to protect the nearby population. Radioactive plumes are mainly affected by wind direction and speed. Since it is difficult to identify the wind direction and speed immediately after the accident, a good understanding of the historical wind data could save many lives and ensure smoother evacuation procedures. In this study, wind data for the past 10 years are analyzed for the five NPPs in the Republic of Korea (ROK). The analyzed data include wind direction and wind speed from 2012 to 2021. In particular, the characteristics of the wind field blowing from the NPPs to the nearest densely populated regions are examined. Finally, suggestions to improve evacuation plans are made.

• Nuclear Engineering and Technology
• /
• v.45 no.6
• /
• pp.791-794
• /
• 2013

Since the Fukushima accident in 2011, the importance of the electrical systems in nuclear power plants (NPPs) has been emphasized. The result has been that NPP regulators are enhancing their monitoring of loss of offsite power (LOOP) events. Korea Hydro & Nuclear Power Co. (KHNP) is reviewing the status and issues related to LOOPs, and is attempting to establish specific countermeasures to prevent LOOPs, because they can have severe consequences in the complicated maintenance schedule during an outage. A starting point for preventing LOOPs is the control of the loss of voltage (LOV)-initiating components. In order to reflect this in the risk assessment program, an LOV monitor is being developed for use during plant outages.

• Nuclear Engineering and Technology
• /
• v.53 no.6
• /
• pp.2038-2045
• /
• 2021

The main objective of this work is to propose a reliable routine standard operation procedures (SOP) for structural health monitoring and diagnosis of nuclear power plants (NPPs). At present, NPPs have monitoring systems that can be used to obtain the quantitative health record of containment (CTMT) buildings through system identification technology. However, because the measurement signals are often interfered with by noise, the identification results may introduce erroneous conclusions if the measured data is directly adopted. Therefore, this paper recommends the SOP for signal screening and the required identification procedures to identify the dynamic characteristics of the CTMT of NPPs. In the SOP, three recommend methods are proposed including the Recursive Least Squares (RLS), the Observer Kalman Filter Identification/Eigensystem Realization Algorithm (OKID/ERA), and the Frequency Response Function (FRF). The identification results can be verified by comparing the results of different methods. Finally, a preliminary CTMT healthy record can be established based on the limited number of earthquake records. It can be served as the quantitative reference to expedite the restart procedure. If the fundamental frequency of the CTMT drops significantly after the Operating Basis Earthquake and Safe Shutdown Earthquake (OBE/SSE), it means that the restart actions suggested by the regulatory guide should be taken in place immediately.

• Journal of Radiation Protection and Research
• /
• v.34 no.4
• /
• pp.176-183
• /
• 2009

Maintenance on the water chamber of steam generator during outage in nuclear power plants (NPPs) has a likelihood of high radiation exposure to whole body of workers even short time period due to the high radiation exposure rates. In particular, it is expected that hands would receive the highest radiation exposure because of its contact with radiation materials. In this study, characteristic analysis of inhomogeneous radiation fields for contact operations was conducted using thermoluminescent dosimeter (TLD) readouts from the application tests of two-dosimeter algorithm to Korean NPPs in 2004. It is regarded that inhomogeneous radiation fields for contact operations in NPPs are dominated by high energy photons. In addition, field tests for workers who participated in maintenance on the steam generator during outage at Ulchin NPPs in 2009 and pressure tube replacement at Wolsong NPPs in 2009 were conducted to analyze radiation fields and to estimate the extremity dose. As a result, radiation fields were dominated by high energy photons.

• Nuclear Engineering and Technology
• /
• v.41 no.3
• /
• pp.225-236
• /
• 2009

This study has identified human performance research issues associated with the implementation of new technology in nuclear power plants (NPPs). To identify the research issues, current industry developments and trends were evaluated in the areas of reactor technology, instrumentation and control technology, human-system integration technology, and human factors engineering (HFE) methods and tools. The issues were prioritized into four categories based on evaluations provided by 14 independent subject matter experts representing vendors, utilities, research organizations and regulators. Twenty issues were categorized into the top priority category. The study also identifies the priority of each issue and the rationale for those in the top priority category. The top priority issues were then organized into research program areas of: New Concepts of Operation using Multi-agent Teams, Human-system Interface Design, Complexity Issues in Advanced Systems, Operating Experience of New and Modernized Plants, and HFE Methods and Tools. The results can serve as input to the development of a long-term strategy and plan for addressing human performance in these areas to support the safe operation of new NPPs.

• Nuclear Engineering and Technology
• /
• v.55 no.3
• /
• pp.908-918
• /
• 2023

The Saudi National Atomic Energy project aims to adopt peaceful nuclear technologies and be part of the country's energy mix. As emerging nuclear energy, it is essential to understand public concerns and acceptability of nuclear energy, as well as the factors influencing acceptance to develop nuclear energy policy and implement nuclear energy programs. The purpose of this study is to analyze the public attitudes and acceptance of nuclear energy among Saudi Arabian citizens by utilizing protection motivation theory and theory of planned behavior. A total of 1,404 participants answered a questionnaire which was distribute by convenience sampling approach. A Structural Equation Modeling framework was constructed and analyzed to understand public behavior toward building the country's first Nuclear Power Plant (NPP). Before analyzing the data, the model was validated. The research concluded that the benefits of nuclear power plants were essential in determining people's acceptance of NPPs. Surprisingly, the effect of the perceived benefits was found higher than the effect of the perceived risks to the acceptance. Furthermore, the public's participation in this study revealed that the NPPs location has a significant impact on their acceptance. Based on the finding, several policy implementations were suggested. Finally, the study's model results would benefit scholars, government agencies, and the business sector in Saudi Arabia and worldwide.

• Journal of the Korean Society of Safety
• /
• v.30 no.4
• /
• pp.174-180
• /
• 2015

This study developed a Safety Culture Impact Assessment Model (SCIAM) which consists of a safety culture assessment methodology and a safety culture impact quantification methodology. The SCIAM uses safety culture impact index (SCII) to monitor the status of safety culture of the NPPs periodically and it uses relative core damage frequency (RCDF) to present the impact of safety culture on the safety of the NPPs. As a result of applying SCIAM to the reference plant (Kori 3), the standard for the healthy safety culture of the reference plant is suggested. SCIAM might contribute to improve the safety of the NPPs (Nuclear Power Plants) by monitoring the status of safety culture periodically and presenting the standard of healthy safety culture.

• Nuclear Engineering and Technology
• /
• v.55 no.5
• /
• pp.1630-1643
• /
• 2023

The correct situation awareness (SA) of operators is important for managing nuclear power plants (NPPs), particularly in accident-related situations. Among the three levels of SA suggested by Ensley, Level 3 SA (i.e., projection of the future status of the situation) is challenging because of the complexity of NPPs as well as the uncertainty of accidents. Hence, several prediction methods using artificial intelligence techniques have been proposed to assist operators in accident prediction. However, these methods only predict short-term plant status (e.g., the status after a few minutes) and do not provide information regarding the uncertainty associated with the prediction. This paper proposes an algorithm that can predict the multivariate and long-term behavior of plant parameters for 2 h with 120 steps and provide the uncertainty of the prediction. The algorithm applies bidirectional long short-term memory and an attention mechanism, which enable the algorithm to predict the precise long-term trends of the parameters with high prediction accuracy. A conditional variational autoencoder was used to provide uncertainty information about the network prediction. The algorithm was trained, optimized, and validated using a compact nuclear simulator for a Westinghouse 900 MWe NPP.