• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2006년도 추계학술대회 논문집
• /
• pp.1222-1227
• /
• 2006

These days customers require various things such as multiple train, variable trainset, multiple Auxiliary Power Generator(APG) and so on. Among these, the train with multiple APG is installed with APG in each car. Thus, we control and monitor train installed with multiple APG through the TCMS(Train Control & Monitoring System). The TCMS supervise APG failure status and transmit control data in case of a APG failure or more, so energize or de-energize ESK and LRR. Therefore, we can easily control ESK and LRR which gets hard to control because of multiple APG.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2004년도 춘계학술대회 논문집
• /
• pp.81-85
• /
• 2004

This paper describes the testing facility to demonstrate the performance of the distribution class circuit breakers and switchgears and the testing methods. The field-test evaluation system consists of two parts. One is the distribution system for simulation of the condition on interruption mode of switches which are installed in the system and tested by the AFG(Artificial Fault Generator) and the thunderbolt generator just like in the real field. The other is a laboratory for confirmation or the important characteristics regarding to the insulation, gas, environment durability of equipment. For the fatal failure mode, a FMEA(Failure Modes and Effects Analysis) technique which is a kind of a structural analysis to consider a counter-plan was emploved.

• 대한기계학회논문집A
• /
• 제30권10호
• /
• pp.1255-1260
• /
• 2006

To maintain the structural integrity of steam generator tubes, 40% of wall thickness plugging criterion has been developed. The approach is for the steam generator tube with single crack, so that the interaction effect of multiple cracks can not be considered. Although, recently, several approaches have been proposed to assess the integrity of steam generator tube with two identical cracks whilst actual multiple cracks reveal more complex shape. In this paper, the coalescence pressure of steam generator tube containing multiple cracks of different length is evaluated based on the detailed 3-dimensional (3-D) elastic-plastic finite element (FE) analyses. In terms of the crack shape, two collinear axial through-wall cracks with different length were considered. Furthermore, the resulting FE coalescence pressures are compared with FE coalescence pressures and experimental results for two identical collinear axial through-wall cracks to quantify the effect of crack length ratio on failure behavior of steam generator tube with multiple cracks. Finally, based on 3-D FE results, the coalescence evaluation diagrams were proposed.

• 한국압력기기공학회 논문집
• /
• 제7권3호
• /
• pp.1-7
• /
• 2011

The analysis shows that the vibration is one of the main reasons of turbine failure. Especially, the problems caused by vibration occur right after retrofit of the turbine-generator and restarting the turbine. Through the case study of high vibration caused by after the turbine trip and restart, turbine vibration was identified to be influenced by startup condition. Turbine startup at high casing temperature right after unscheduled turbine trip cause radial expansion in rotor by contraction in axial direction, while casing continues to contract by steam flowing into casing. Consequently, gap between rotor and casing decrease until to metal contact to cause high vibration. Through the case study of high vibration of turbine-generator system after generator retrofit, it was identified that generator replacement could cause high vibration in turbine-generator system if the influence of generator replacement on entire system was not considered properly. To prevent startup delay caused by high vibration, it is important to keep the gaps at the design standard and start the turbine after thermal equilibrium.

• Nuclear Engineering and Technology
• /
• 제55권2호
• /
• 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.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2004년도 요약집 춘계학술발표대회
• /
• pp.156-156
• /
• 2004

• Nuclear Engineering and Technology
• /
• 제51권5호
• /
• pp.1307-1313
• /
• 2019

Recent analysis results with realistic assumptions provide the variability of operator allowable time for the initiation of aggressive cooldown under small break loss of coolant accident or steam generator tube rupture with total failure of high pressure safety injection. We investigated how plant risk may vary depending on the variability of operators' failure probability of timely initiation of aggressive cooldown. Using a probabilistic safety assessment model of a nuclear power plant, we showed that plant risks had a linear relation with the failure probability of aggressive cooldown and could be reduced by up to 10% as aggressive cooldown is more reliably performed. For individual accident management, we found that core damage potential could be gradually reduced by up to 40.49% and 63.84% after a small break loss of coolant accident or a steam generator tube rupture, respectively. Based on the importance of timely initiation of aggressive cooldown by main control room operators within the success criteria, implications for improvement of emergency operating procedures are discussed. We recommend conducting further detailed analyses of aggressive cooldown, commensurate with its importance in reducing risks in nuclear power plants.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 1993년도 제18회 학술대회 초록집
• /
• pp.77-84
• /
• 1993

Systems with journal bearings generally operate in large scale and under severe loading conditions such as steam generator turbines and internal combustion engines, in contrast to the machineries using rolling element bearings. Failure of the bearings in these machineries can result in the system breakdown. To avoid the time consuming repair and considerable economic loss, the detection of incipient failure in journal bearings becomes very important. In this experimental approach, acoustic emission monitoring is employed to the detection of incipient failure caused by intervention of foreign particles most probable in the journal bearing systems. It has been known that the intervention of foreign materials, insufficient lubrication and misassembly etc. are principal factors to cause bearing failure and distress. The experiment was conducted under such designed conditions as inserting alumina particles to the lubrication layer in the simulated journal bearing system. The results showed that acoustic emission could be an effective tool to detect the incipient failure in journal bearings.

• 대한기계학회논문집B
• /
• 제34권9호
• /
• pp.867-873
• /
• 2010

수냉각 발전기 고정자 권선에서의 냉각수 누수 및 흡습에 의한 절연파괴 손상사례가 국내 및 국외에서 자주 발생되고 있다. 이러한 사고는 막대한 경제적 피해뿐만 아니라 전력의 안정적 공급 측면에서 매우 심각한 계통 사고로 연결될 수 있다. 특히 국내 발전기는 15년 이상 운전되어 열화가 진행된 발전기가 50% 이상이며, 계획예방정비 기간 중에 권선에서의 누설 및 흡습 권선이 종종 발견되고 있다. 기존에는 누수 시험 전 과정인 권선 건조 과정을 무시한 채 누수 시험 결과만으로 권선 누설 여부를 진단하였으나 본 논문에서는 누수 시험을 위한 준비 단계인 진공 건조 시의 권선 내부의 진공도 패턴 분석을 통해 권선 누설 및 흡습 여부를 예측진단할 수 있는 방법을 실험적으로 증명하였다.

• 산업경영시스템학회지
• /
• 제43권2호
• /
• pp.33-38
• /
• 2020

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.