• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3620-3630
• /
• 2022

The diagnosis of abnormalities in a nuclear power plant is essential to maintain power plant safety. When an abnormal event occurs, the operator diagnoses the event and selects the appropriate abnormal operating procedures and sub-procedures to implement the necessary measures. To support this, abnormality diagnosis systems using data-driven methods such as artificial neural networks and convolutional neural networks have been developed. However, data-driven models cannot always guarantee an accurate diagnosis because they cannot simulate all possible abnormal events. Therefore, abnormality diagnosis systems should be able to detect their own potential misdiagnosis. This paper proposes a rulebased diagnostic validation algorithm using a previously developed two-stage diagnosis model in abnormal situations. We analyzed the diagnostic results of the sub-procedure stage when the first diagnostic results were inaccurate and derived a rule to filter the inconsistent sub-procedure diagnostic results, which may be inaccurate diagnoses. In a case study, two abnormality diagnosis models were built using gated recurrent units and long short-term memory cells, and consistency checks on the diagnostic results from both models were performed to detect any inconsistencies. Based on this, a re-diagnosis was performed to select the label of the second-best value in the first diagnosis, after which the diagnosis accuracy increased. That is, the model proposed in this study made it possible to detect diagnostic failures by the developed consistency check of the sub-procedure diagnostic results. The consistency check process has the advantage that the operator can review the results and increase the diagnosis success rate by performing additional re-diagnoses. The developed model is expected to have increased applicability as an operator support system in terms of selecting the appropriate AOPs and sub-procedures with re-diagnosis, thereby further increasing abnormal event diagnostic accuracy.

• 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 Advanced Marine Engineering and Technology
• /
• v.30 no.2
• /
• pp.247-252
• /
• 2006

Almost ship monitoring systems are event driven alarm system which warn only when the measurement value is over or under set point. These kinds of system cannot warn until signal is growing to abnormal state that the signal is over or under the set point. therefore cannot play a role for preventive maintenance system. This paper proposes fault diagnosis method which is able to diagnose and forecast the fault from present operating condition by analyzing monitored signals with present ship monitoring system without any additional sensors. By analyzing the data with high correlation coefficient(CC), correlation level of interactive data can be defined. Knowledge base of abnormal detection can be built by referring level of CC(Fault Detection CC. FDCC) to detect abnormal data among monitored data from monitoring system and knowledge base of diagnosis built by referring CC among interactive data for related machine each other to diagnose fault part.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2005.06a
• /
• pp.281-286
• /
• 2005

Almost ship monitoring systems are event driven alarm system which warn only when the measurement value is over or under set point. These kinds of system cannot warn while signal is growing to abnormal state until the signal is over or under the set point and cannot play a role for preventive maintenance system. This paper proposes fault diagnosis method which is able to diagnose and forecast the fault from present operating condition by analyzing monitored signals with present ship monitoring system without additional sensors. By analyzing this data having high correlation coefficient(CC), correlation level of interactive data can be understood. Knowledge base of abnormal detection can be built by referring level of CC(Fault Detection CC, FDCC) to detect abnormal data among monitored data from monitoring system and knowledge base of diagnosis built by referring CC among interactive data for related machine each other to diagnose fault part.

• Nuclear Engineering and Technology
• /
• v.52 no.9
• /
• pp.2009-2016
• /
• 2020

A nuclear power plant is a large complex system with tens of thousands of components. To ensure plant safety, the early and accurate diagnosis of abnormal situations is an important factor. To prevent misdiagnosis, operating procedures provide the anticipated symptoms of abnormal situations. While the more severe emergency situations total less than ten cases and can be diagnosed by dozens of key plant parameters, abnormal situations on the other hand include hundreds of cases and a multitude of parameters that should be considered for diagnosis. The tasks required of operators to select the appropriate operating procedure by monitoring large amounts of information within a limited amount of time can burden operators. This paper aims to develop a system that can, in a short time and with high accuracy, select the appropriate operating procedure and sub-procedure in an abnormal situation. Correspondingly, the proposed model has two levels of prediction to determine the procedure level and the detailed cause of an event. Simulations were conducted to evaluate the developed model, with results demonstrating high levels of performance. The model is expected to reduce the workload of operators in abnormal situations by providing the appropriate procedure to ultimately improve plant safety.

• Korean Journal of Computational Design and Engineering
• /
• v.17 no.2
• /
• pp.97-110
• /
• 2012

High performance sensors and modern data logging technology with real-time telemetry facilitate system fault diagnosis in a very precise manner. Fault detection, isolation and identification in fault diagnosis systems are typical steps to analyze the root cause of failures. This systematic failure analysis provides not only useful clues to rectify the abnormal behaviors of a system, but also key information to redesign the current system for retrofit. The main barriers to effective failure analysis are: (i) the gathered data (event) logs are too large in general, and further (ii) they usually contain noise and redundant data that make precise analysis difficult. This paper therefore applies suitable pre-processing techniques to data reduction and feature extraction, and then converts the reduced data log into a new format of event sequence information. Finally the event sequence information is decoded to investigate the correlation between specific event patterns and various system faults. The efficiency of the developed pre-filtering procedure is examined with a terminal box data log of a marine diesel engine.

• Journal of Power System Engineering
• /
• v.17 no.4
• /
• pp.17-22
• /
• 2013

Diesel generator of nuclear power plant has a role for supply of emergency electric power to protect reactor core system in event of loss of off-site power supply. Therefore diesel generator should be tested periodically to verify the function that can supply specified frequency and voltage at design power level within limited time. For this purpose, appropriate maintenances in case that abnormal conditions were found are required in allowed time. In this paper, results of development of engine condition diagnosis technology and study on power plant of its technology for diesel generator are described.

• 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.

• Journal of the Korean Society of Safety
• /
• v.27 no.1
• /
• pp.7-13
• /
• 2012

This paper describes the diagnosis techniques using UV images taken in the field under energized condition of power equipments in order to figure out and analyze the abnormal states on the terminals of power equipments. To classify the features of the terminals, the counted No. of the corona generated at the terminals is defined. According to the result detected, the No. of corona detected on the power equipments installed inside a building is less than that installed outside a building, and it strongly depends on the environment and installed condition. Thus, the environmental condition needs enhanced, and stable operation by the periodic inspection under energized condition of the power equipments is required. Especially, the event counting technique using UV camera is useful for the power equipments apart more than 20 m to apply, and there can be an error due to the features of the sensing techniques when the distance between the user and the objects is close less than 15 m. Therefore, the experimental result shows that event counting technique is employed in the case of the distance more than 15 m. The electrical safety can be ensured by using the UV detection technique and the criteria.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.30 no.9
• /
• pp.596-601
• /
• 2017

The advancement and diversification of urban functions has caused an increasing need to improve the reliability of power supplies. The diversification of urban areas causes social disruptions by paralyzing urban functions during power outages. A large power outage occurs in the event of an accident, owing to the subduction of distribution lines. Therefore, in recent years, for the sake of the environment and safety, the safety diagnosis of electric power facilities has become an important issue. In this system, because thermal information changes rapidly during unattended monitoring owing to heat concentration phenomenon due to abnormal load or deterioration, studies have been conducted on the development of a device that can notify the manager at all times.