• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.115-123
• /
• 2021

Through machine learning-based load prediction, it is possible to prevent excessive power generation or unnecessary economic investment by estimating the appropriate amount of facility investment in consideration of the load that will increase in the future or providing basic data for policy establishment to distribute the maximum load. However, in order to secure the reliability of the developed load prediction model in the field, the performance comparison verification between the distribution line load prediction models must be preceded, but a comparative performance verification system between the distribution line load prediction models has not yet been established. As a result, it is not possible to accurately determine the performance excellence of the load prediction model because it is not possible to easily determine the likelihood between the load prediction models. In this paper, we developed a reliability verification system for load prediction models including a method of comparing and verifying the performance reliability between machine learning-based load prediction models that were not previously considered, verification process, and verification result visualization methods. Through the developed load prediction model reliability verification system, the objectivity of the load prediction model performance verification can be improved, and the field application utilization of an excellent load prediction model can be increased.

• KEPCO Journal on Electric Power and Energy
• /
• v.1 no.1
• /
• pp.61-65
• /
• 2015

For effective distribution planning and operation, we need a reliable estimation of operation capacity. But it is difficult to ensure reliability due to the low accuracy of section load data, which is used as a basis in estimating the operation capacity. This paper discusses how to improve the accuracy of section load data by analyzing the existing method of estimating the section load, using statistical techniques to adjust the acquired data, and using the section load estimation algorithm to estimate the section load based on the adjusted data.

• Proceedings of the KIEE Conference
• /
• 2006.07a
• /
• pp.464-465
• /
• 2006

RCM(Reliability-centered Maintenance)은 유지 보수하고자 하는 기기에 대하여 시스템의 신뢰도와 안정성 및 경제적 측면을 고려하여 적용 가능하고 효율적인 유지보수 기법을 논리적으로 선택하는 기법이다. RCM은 이미 항고우주산업이나 원자력발전산업과 같은 곳에 적용되어 사용되고 있으며 전력설비 분야에도 도입되고 있다. 본 논문에서는 이러한 RCM 기법을 적응하여 개발 중인 당사의 전력설비관리 시스템에 대하여 그 구성 및 기능 등의 시스템 설계에 대하여 논하고자 한다.

• Proceedings of the KIEE Conference
• /
• 2006.11a
• /
• pp.132-134
• /
• 2006

최근 도입되고 있는 RCM(Reliability-centered Maintenance)은 전력 설비의 특성과 운용 환경에 따른 신뢰성 분석을 통해 설비의 목표 신뢰도를 유지하기 위한 가장 효율적이고 경제적인 유지보수 방법을 결정 하는 방법론이다. 본 논문에서는 전력 설비의 감시, 분석 및 진단 데이터를 데이터베이스로 구축하고 RCM 기법을 바탕으로 유지보수 방법을 제시하는 전력설비관리 시스템의 구성과 기능을 기술한다.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.543-545
• /
• 1995

The purpose of this paper is to determine the proper reliability criteria used in generation expansion planning of electric utilities. In this paper, we tried to combine long-term generation expansion planning and short-term weekly maintenance scheduling program package. We set two scenarios in which the O&M technology of power plants will be improved or not in the future. We performed LOLP sensitivity analysis for each scenario to determine the optimum reliability criteria in the power system operation aspects.

• International Journal of Railway
• /
• v.5 no.1
• /
• pp.1-9
• /
• 2012

Reliability means that a product maintains its initial quality and performance at a certain period of time (time, distance, cycle etc) under given condition without failure. The given conditions include both environmental condition and operating condition. Environmental condition means a common natural environment such as temperature, humidity, vibration, and working condition means an artificial environment such as voltage, current load, place for installment, and hours of use, which occurs during the life of the product. In the field of railway vehicles, it is mandatory to use a part with the proved reliability as the extension of the life of vehicle become highly necessary. But the reliable assessment method for the reliability of the part is insufficient. If the reliability of the railway vehicle parts could be assessed by using the field data, the reliability of the entire system could also be evaluated reliably. In this study, life span of micro-switch for master controller is analyzed and prediction is performed based on its field data given by an operator considering the special circumstances of railway vehicles such as the operation of a large number of trains on the same line.

• Proceedings of the KIEE Conference
• /
• 2006.07a
• /
• pp.29-31
• /
• 2006

The most crucial requirement of a power system is o supply quality electric energy to customers without interrution. This problem is directly related to reliability of power system. Reliability assessment of power system has been an important topic for the past several decades. This paper deals with reliability assessment of a 154kV power substation n KEPCO. In his paper, exponential distribution is used to calculate reliablity index. The failure rate data that are utilited for reliablity index based on the realistic system. Also, FTA(Fault Tree Analysis) is used to compute substation reliablity

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.2
• /
• pp.301-307
• /
• 2021

After the spread of the data collection devices such as smart meters, energy data is increasingly collected in a variety of ways, and its importance continues to grow. However, due to technical or practical limitations, errors such as missing or outliers in the data occur during data collection process. Especially in the case of customer-related data, billing problems may occur, so energy companies are conducting various research to process such data. In addition, efforts are being made to create added value from data, which makes it difficult to provide such services unless reliability of data is guaranteed. In order to solve these challenges, this research analyzes prior research related to bad data processing specifically in the energy field, and propose new missing value processing methods to improve the reliability and field utilization of energy data.

• KEPCO Journal on Electric Power and Energy
• /
• v.3 no.2
• /
• pp.107-111
• /
• 2017

The reliability on high cycle fatigue damage mechanism for new blades manufactured by reverse-engineering is demonstrated by success-run test. Turbine blades always experience various dynamic loads in turbine operation, as well as being in resonance condition and forced by fluid-induced vibrations mostly during run-up/down, which may accumulate high cycle damage to the blades. The accidents caused by blade failure especially incur not only a lot of troubles to the machinery but also huge financial losses. Therefore it is necessary to verify the reliability of blades in advance for the safe use. The success run test for the reliability demonstration is designed and performed for the new blades using the technique known as resonant high cycle fatigue testing.

• Journal of Applied Reliability
• /
• v.10 no.4
• /
• pp.279-297
• /
• 2010

AQS(Air Quality Control System) is the important part of a car air conditioning system. This device intercepts automatically the influx of harmful waste gas. In this paper reliability assessment criteria for AQS are established in terms of quality certification test and lifetime test. The former quality certification test comprises general performance test and environmental test. Items which pass the test undergo lifetime test which guarantees the extent of mean lifetime with certain confidence.