• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2028-2030
• /
• 2003

This paper describes the results of reliability prediction analysis of control rod control system, which is being developed as part of KNICS project. The results of reliability prediction indicate MTBF(Mean Time Between Failure) of cards for control rod control system. A purpose of reliability prediction is to evaluate MTBF of cards, identify the design drawbacks of cards, and propose design improvement to a designer to help design the more reliable control rod control system. This reliability prediction analysis used the the part count and part stress method in the basis of MIL-HDBK-217F.

• Journal of Korean Society of Forest Science
• /
• v.95 no.5
• /
• pp.601-604
• /
• 2006

This study compared the accuracy of partial multivariate and vector autoregressive models for lumber demand prediction in Korea. The partial multivariate model has three explanatory variables; own price, construction permit area and dummy. The dummy variable reflected the boom of lumber demand in 1988, and the abrupt decrease in 1998. The VAR model consists of two endogenous variables, lumber demand and construction permit area with one lag. On the other hand, the prediction accuracy was estimated by Root Mean Squared Error. The results showed that the estimation by partial multivariate and vector autoregressive model showed similar explanatory power, and the prediction accuracy was similar in the case of using partial multivariate and vector autoregressive model.

• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.247-275
• /
• 2021

Purpose This study attempted to predict corporate innovation and business performance using ensemble learning. Design/methodology/approach The ensemble techniques uses weak learning to create robust learning, which combines several weak models to derive improved performance. In this study, XGboost, LightGBM, and Catboost were used among ensemble techniques. It was compared and evaluated with traditional machine learning methods. Findings The summary of the research results is as follows. First, the type of innovation is expanding from technical innovation to non-technical areas. Second, it was confirmed that LightGBM performed best for radical innovation prediction, and XGboost performed best for incremental innovation prediction. Third, Catboost performed best for firm performance prediction. Although there was no significant difference in predictive power between ensemble techniques, we found that comparative analysis was necessary to confirm better prediction performance.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.20 no.2
• /
• pp.1-10
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis, a model can be constructed with various machine learning algorithms, including decision tree. And feature importance has been utilized in selecting better input features that can improve performance of data analysis models for several application areas. In this paper, a method of utilizing feature importance calculated from the MDI method and its effects are investigated in the credit card customer churn prediction problem with classification trees. Compared with several random feature selections from case data, a set of input features selected from higher value of feature importance shows higher predictive power. It can be an efficient method for classifying and choosing input features necessary for improving prediction performance. The method organized in this paper can be an alternative to the selection of input features using feature importance in composing and using classification trees, including credit card customer churn prediction.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.4
• /
• pp.491-497
• /
• 2015

In this paper a method of design and Implementation of RFID based control system for reducing standby power consumption at the power outlet is described. The system is composed of a RF controlled power outlet having relay and an active RFID tag communicating with the RF reader module controlling the relay. When the tag carried by human approaches to the RF reader the reader recognizes the tag and switch off the relay based on the RSSI level measurement. A low power packet prediction algorithm has been used to decrease the DC power consumption at both the tag and the RF reader. The result of experiment shows that successful operation of the relay control has been obtained while low power operation of the tag and the reader is achieved using above algorithm. Also setting the distance between the reader and the tag by controlling transmission power of the tag and adjusting the duty cycle of the packet waiting time when the reader is in idle state allows us to reduce DC power consumption at both the reader and the tag.

• Proceedings of the KIPE Conference
• /
• 2016.07a
• /
• pp.423-424
• /
• 2016

Recently, the mass production of Energy storage system (ESS) is actively perform around world. Energy storage system is a technique that stores power to energy storage device to supply energy into grid and load at peak-load. Therefore, the efficient energy management is available by using ESS system. The life of Lithium-ion battery is varied corresponding to the power usage, especially selected depth of discharge (DOD). The lifetime of battery is the one of the most issue of the ESS system because of its stability and reliability. Therefore, lifetime management of battery and power converter of ESS module is required. In this paper, the battery lifetime management method estimating residual power and lifetime of lithium ion battery of ESS system is proposed. Also, total avenue prediction of ESS system is simulated considering the total lifetime of battery.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.20 no.1
• /
• pp.74-82
• /
• 2010

Power flow analysis(PFA) methods have shown many advantages in noise predictions and vibration analysis in medium-to-high frequency ranges. Applying the finite element technique to PFA has produced power flow finite element method(PFFEM) that can be effectively used for analysis of vibration of complicated structures. PFADS(power flow analysis design system) based on PFFEM as the vibration analysis program has been developed for vibration predictions and analysis of coupled structural systems. In this paper, to improve the function of vibro-acoustic coupled analysis in PFADS, the PFFEM has been extended for analysis of the interior noise problems in the vibro-acoustic fully coupled systems. The vibro-acoustic fully coupled PFFEM formulation based on energy coupled relations is extended to structural system model by using appropriate modifications to structural-structural, structural-acoustic and acoustic-acoustic joint matrices. It has been applied to prediction of the interior noise in two room model coupled with panels, and the PFFEM results are compared to those of statistical energy analysis(SEA).

• Transactions of the Korean hydrogen and new energy society
• /
• v.31 no.4
• /
• pp.380-386
• /
• 2020

This paper represents an analysis of the economic impact of firing natural gas/diesel and natural gas/by-product oil mixtures in diesel engine power plants. The objects of analysis is a power plant with electricity generation capacity (300 kW). Using performance data of original diesel engines, the fuel consumption characteristics of the duel fuel engines were simulated. Then, economic assessment was carried out using the performance data and the net present value method. A special focus was given to the evaluation of fuel cost saving when firing natural gas/diesel and natural gas/by-product oil mixtures instead of the pure diesel firing case. Analyses were performed by assuming fuel price changes in the market as well as by using current prices. The analysis results showed that co-firing of natural gas/diesel and natural gas/by-product oil would provide considerable fuel cost saving, leading to meaningful economic benefits.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2004.11a
• /
• pp.25-30
• /
• 2004

This paper gives an assessment criteria and average failure lifetime prediction for power supply of electrodeless fluorescent lamp. The paper present electric appliance safety standard and performance standard for power supply of electrodeless fluorescent lamp. also, It presents the Failure Rate or Mean Time To Failure(MTTF) for power supply of electrodeless fluorescent lamp. We suggest the assessment criteria and improve methods of the reliability on the design basis for the electrodeless fluorescent system.

• 한국신재생에너지학회:학술대회논문집
• /
• 2011.05a
• /
• pp.59.2-59.2
• /
• 2011

Although there are many activities on the construction of wind farm to produce amount of power from the wind, in practice power productions are not as much as its expected capabilities. This is because a lack of both the prediction of wind resources and the aerodynamic analysis on turbines with far wake effects. In far wake region, there are velocity deficits and increases of the turbulence intensity which lead to the power losses of the next turbine and the increases of dynamic loadings which could reduce system's life. The analysis on power losses and the increases of fatigue loadings in the wind farm is needed to prevent these unwanted consequences. Therefore, in this study velocity deficits have been predicted and aerodynamic analysis on turbines in the far wake is carried out from these velocity profiles. Ainslie's eddy viscosity wake model is adopted to determine a wake velocity and aerodynamic analysis on wind turbines is predicted by the numerical methods such as blade element momentum theory(BEMT) and vortex lattice method(VLM). The results show that velocity recovery is more rapid in the wake region with higher turbulence intensity. Since the velocity deficit is larger when the turbine has higher thrust coefficient, there is a huge aerodynamic power loss at the downstream turbine.