• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.241-245
• /
• 1989

A knowledge based expert system is a computer program that emulates the reasoning process of a human expert in a specific problem domain. This paper presents an expert system to diagnose the various faults in power system. The developed expert system is represented considering two points; the possibility of solution and the fast processing speed. As uncertainties exist in the facts and rules which comprise the knowledge base of the expert system, Certainty Factor, which is based on the confirmation theory is used for the inexact reasoning. Also, as the diagnosis problem requires the inductive reasoning process in nature, the solution is imperfect and not unique in general. So the expert system is designed to generate all the possible hypothesis in order of the possibility and also it can explain the propagation procedure of the faults for each solution using the built in backtracking mechanism. In realization of the expert system, the processing speed is greatly dependent upon the problem representation, reasoning scheme and search strategy. So, in this paper the fault diagnosis problem itself is analysed from the view point of Artificial Intelligence and as a result, the expert system has the following basic features. 1) The certainty factor is adopted in the inference engine for inexact reasoning. 2) Problem apace is represented using the problem reduction technique. 3) Bidirectional reasoning scheme is used. 4) Best first search strategy is adopted for rapid processing. The expert system was developed us ing PROLOG language.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.24 no.3
• /
• pp.294-301
• /
• 2015

Oil filters for vehicular parts are used under high and low temperatures as the engine is cooled, and defects can be generated with repeated changes in the operating environment and with changes in the shape, such as very high internal losses for the bolts. Visually checking for defects inside a bolt is impossible. Nondestructive evaluation methods such as eddy current testing (ECT) are recommended as a more effective way to examine inside a bolt and detect surface defects in a short amount of time. In this study, the fit bobbin coil eddy current probe was applied to checking the bolts. The bolt parameters were calculated by using a COMSOL analysis program to obtain parameters for professional interior design and fault diagnosis.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.18 no.6
• /
• pp.50-58
• /
• 2014

This paper is about a short survey on the recent research activities regarding health monitoring and management for liquid rocket engines. For this, we investigate the precedent techniques developed in advanced space-industry countries which are USA, EU, Russia, Japan and China. Particularly, we focus on the technologies applied in China, a recently joined to the advanced space-industry countries in this field. Then we discuss some important points to be considered to apply to the development of the Korea Space Launch Vehicle KSLV-II and other related projects.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.2
• /
• pp.14-22
• /
• 2021

A plan for the development of reliability-based ROK amphibious assault vehicles is proposed. By analyzing the development case of the U.S. EFV, considerations for the successful development of the next-generation Korea Forces amphibious assault vehicle are presented. If the vehicle reliability can be improved to the level of the fourth highest priority electric unit for power units, suspensions, decelerators, and body groups, which have the highest priority among fault frequency items, a system level MTBF of 36.4%↑ can be achieved, and the operational availability can be increased by 3.5%↑. The next-generation amphibious assault vehicles must fulfill certain operating and performance requirements, the underlying systems must be built, and sequencing of the hybrid engine and the modular concept should be considered. Along with big-data- and machine-learning-based failure prediction, machine maintenance based on augmented reality/virtual reality and remote maintenance should be used to improve the ability to maintain combat readiness and reduce lifecycle costs.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.5
• /
• pp.35-46
• /
• 2006

The current Internet Key Exchange protocol(IKE) which has been used for key exchange of security system was pointed out the faults of scalability, speed, efficiency and stability. In this research, we tried to resolve those faults, and implemented the newly designed IKEv2 protocol in the IPsec test bed system. In the trend of network expansion, the current Internet Key Exchange protocol has a limitation of network scalability, so we implemented the new Internet Key Exchange protocol as a recommendation of RFC proposal, so as to resolve the fault of the key exchange complexity and the speed of authentication process. We improved the key exchange speed as a result of simplification of complex key exchange phase, and increased efficiency with using the preexistence state value in negotiation phase.

• Journal of the Korean Society of Safety
• /
• v.36 no.3
• /
• pp.66-73
• /
• 2021

This report documents the results of an at-power internal events Level 1 Probabilistic Safety Assessment (PSA) for a Korea research reactor (KRR). The aim of the study is to determine the accident sequences, construct an internal level 1 PSA model, and estimate the core damage frequency (CDF). The accident quantification is performed using the AIMS-PSA software version 1.2c along with a fault tree reliability evaluation expert (FTREX) quantification engine. The KRR PSA model is quantified using a cut-off value of 1.0E-15/yr to eliminate the non-effective minimal cut sets (MCSs). The final result indicates a point estimate of 4.55E-06/yr for the overall CDF attributable to internal initiating events in the core damage state for the KRR. Loss of Electric Power (LOEP) is the predominant contributor to the total CDF via a single initiating event (3.68E-6/yr), providing 80.9% of the CDF. The second largest contributor is the beam tube loss of coolant accident (LOCA), which accounts for 9.9% (4.49E-07/yr) of the CDF.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.506-515
• /
• 2023

This study is to find a method to learn engine sound after the start-up of a diesel generator installed in nuclear power plant with an unsupervised deep learning algorithm (CNN autoencoder) and a new method to predict the failure of a diesel generator using it. In order to learn the sound of a diesel generator with a deep learning algorithm, sound data recorded before and after the start-up of two diesel generators was used. The sound data of 20 min and 2 h were cut into 7 s, and the split sound was converted into a spectrogram image. 1200 and 7200 spectrogram images were created from sound data of 20 min and 2 h, respectively. Using two different deep learning algorithms (CNN autoencoder and binary classification), it was investigated whether the diesel generator post-start sounds were learned as normal. It was possible to accurately determine the post-start sounds as normal and the pre-start sounds as abnormal. It was also confirmed that the deep learning algorithm could detect the virtual abnormal sounds created by mixing the unusual sounds with the post-start sounds. This study showed that the unsupervised anomaly detection algorithm has a good accuracy increased about 3% with comparing to the binary classification algorithm.

• Journal of the Korean Institute of Gas
• /
• v.23 no.4
• /
• pp.40-45
• /
• 2019

This paper is a purpose to study the failure example for heavy-duty vehicle fire. The first example, the researcher found the engine over-heating phenomenon causing a coolant leakage by the sealing poor of head-gasket because of D-ring part deformation contacting with cylinder liner top-part and cylinder head. He certified a fire breakout by short transferred to surrounding wiring of air-cleaner. The second example, a brake lining by return fault of break operating S cam causing with much wear of a rear 4 wheel brake lining repeatably was worn by friction. In the long run, it became the cause of fire. The third example, the researcher knew the fire cause was came about the short of wire by overload of tilting motor when the driver tilted up the cap to inspect a engine. Therefore, a heavy-duty fire must minimize the fire occurrence by thorough controlling.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.886-887
• /
• 2015

There is a growing interest in and demand for power industry acceleration and energy efficiency due to the increased energy consumption, environmental issues. Electronic power IT convergence industries such as intelligent power system has attract attention as new growth engine industry. A large number of sensors and motors are being installed following unmanned, automated in existing incoming panel management system. Observe the operating conditions and rapid response is essential. Despite the need for immediate action to be taken in the event of various later failed to recognize the emergency power can lead to accidents. In this paper, we propose a new architecture of the implementation of incoming panel monitoring system for power monitoring, fault detection, maintenance and system control using open source hardware platform and Wi-Fi networks.

• Journal of the Korea Society for Simulation
• /
• v.25 no.1
• /
• pp.35-43
• /
• 2016

Increasing the proportion of an embedded system in automotive industry, test methods for evaluation and fault detection of the embedded system have been researched. HILS is a test method that is used in the development and test of complex real-time embedded systems. In this study, we defined the HILS method of the ECU, one of the embedded systems used in automobiles. Our method is to create a test model that can provide a virtual vehicle environment to the ECU on the basis of the actual vehicle data. The test model has reference information that can transmit the sensor signal and CAN Message into the ECU from HILS tester. In this study, the HILS can detect faults of the target ECU.