• Journal of IKEEE
• /
• v.26 no.1
• /
• pp.62-66
• /
• 2022

Recently, there have been many research efforts based on data-based deep learning technologies to deal with the interference problem between heterogeneous wireless communication devices in unlicensed frequency bands. However, existing approaches are commonly based on the use of complex neural network models, which require high computational power, limiting their efficiency in resource-constrained network interfaces and Internet of Things (IoT) devices. In this study, we address the problem of classifying heterogeneous wireless technologies including Wi-Fi and ZigBee in unlicensed spectrum bands. We focus on a data-driven approach that employs a supervised-learning method that uses received signal strength indicator (RSSI) data to train Deep Convolutional Neural Networks (CNNs). We propose a simple measurement methodology for collecting RSSI training data which preserves temporal and spectral properties of the target signal. Real experimental results using an open-source 2.4 GHz wireless development platform Ubertooth show that the proposed sampling method maintains the same accuracy with only a 10% level of sampling data for the same neural network architecture.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4093-4099
• /
• 2014

In this study, the thermal-structural behavior of the combustor assembly of 200 kW micro gas turbine system was performed. The typical combustor assembly consists of a Liner, Inner & Outer Case, Burner and Nozzle ring, etc. There are some gaps and friction elements between the components to compensate for the different thermal expansions of various components. Therefore, the developed finite element model includes nonlinear elements. The boundary support conditions of the combustor assembly significantly affect the stress distribution due to the high temperature gradient. This paper deals with parametric studies to quantitatively determine the effects of the variation of the support conditions on the stress distribution and deformation of various components of combustor assembly. These results may be useful for the design of the combustor assembly.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.18 no.5
• /
• pp.95-100
• /
• 2014

In hypersonic aircraft, increase of aerodynamic heat and engine heat leads heat loads in airframe. It could lead structural change of aircraft's component and malfunctioning. Endothermic fuels are liquid hydrocarbon fuels which are able to absorb the heat load by undergoing endothermic reactions. In this study, exo-tetrahydrodicyclopentadiene was selected as a model endothermic fuel and experiments on endothermic properties were investigated with pore structure controlled zeolite catalyst using metal deposition. We secured the catalyst that had better endothermic performance than commercial catalyst. The object of this study is inspect catalyst properties which have effect on heat absorption improvement. Synthetic catalyst could be applied to system that use exo-THDCP as endothermic fuel instead of other commercial catalyst.

• Tribology and Lubricants
• /
• v.40 no.1
• /
• pp.17-23
• /
• 2024

This study analyzes the thermal effects on the performance of an air foil thrust bearing (AFTB) using COMSOL Multiphysics to approximate actual bearing behavior under real conditions. An AFTB is a sliding-thrust bearing that uses air as a lubricant to support the axial load. The AFTB consists of top and bump foils and supports the rotating disk through the hydrodynamic pressure generated by the wedge effect from the inclined surface of the top foil and the elastic deformation of the bump foils, similar to a spring. The use of air as a lubricant has some advantages such as low friction loss and less heat generation, enabling air bearings to be widely used in high-speed rotating systems. However, even in AFTB, the effects of energy loss due to viscosity at high speeds, interface frictional heat, and thermal deformation of the foil caused by temperature increase cannot be ignored. Foil deformation derived from the thermal effect influences the minimum decay in film thickness and enhances the film pressure. For these reasons, performance analyses of isothermal AFTBs have shown few discrepancies with real bearing behavior. To account for this phenomenon, a thermal-fluid-structure analysis is conducted to describe the combined mechanics. Results show that the load capacity under the thermal effect is slightly higher than that obtained from isothermal analysis. In addition, the push and pull effects on the top foil and bump foil-free edges can be simulated. The differences between the isothermal and thermal behaviors are discussed.

• Journal of Korea Water Resources Association
• /
• v.55 no.7
• /
• pp.495-504
• /
• 2022

With the recent development of artificial intelligence, a Long Short-Term Memory (LSTM) model that is efficient with time-series analysis is being used to increase the accuracy of predicting the inflow of dams. In this study, we predict the inflow of the Soyang River dam, using the LSTM model with the Sequence-to-Sequence (LSTM-s2s) and attention mechanism (LSTM-s2s with attention) that can further improve the LSTM performance. Hourly inflow, temperature, and precipitation data from 2013 to 2020 were used to train the model, and validate and test for evaluating the performance of the models. As a result, the LSTM-s2s with attention showed better performance than the LSTM-s2s in general as well as in predicting a peak value. Both models captured the inflow pattern during the peaks but detailed hourly variability is limitedly simulated. We conclude that the proposed LSTM-s2s with attention can improve inflow forecasting despite its limits in hourly prediction.

• Geophysics and Geophysical Exploration
• /
• v.23 no.4
• /
• pp.230-242
• /
• 2020

We performed a magnetotelluric (MT) survey to delineate the geological structures below the depth of 20 km in the Gyeongju area where an earthquake with a magnitude of 5.8 occurred in September 2016. The measured MT data were severely distorted by electrical noise caused by subways, power lines, factories, houses, and farmlands, and by vehicle noise from passing trains and large trucks. Using machine-learning methods, we classified the MT time series data obtained near the railway and highway into two groups according to the inclusion of traffic noise. We applied three schemes, stochastic gradient descent, support vector machine, and random forest, to the time series data for the highspeed train noise. We formulated three datasets, Hx, Hy, and Hx & Hy, for the time series data of the large truck noise and applied the random forest method to each dataset. To evaluate the effect of removing the traffic noise, we compared the time series data, amplitude spectra, and apparent resistivity curves before and after removing the traffic noise from the time series data. We also examined the frequency range affected by traffic noise and whether artifact noise occurred during the traffic noise removal process as a result of the residual difference.

• Journal of Korea Water Resources Association
• /
• v.54 no.5
• /
• pp.301-309
• /
• 2021

In this study, we tried to improve the performance of the existing U-net-based deep learning rainfall prediction model, which can weaken the meaning of time series order. For this, ConvLSTM2D U-Net structure model considering temporal consistency of data was applied, and we evaluated accuracy of the ConvLSTM2D U-Net model using a RainNet model and an extrapolation-based advection model. In addition, we tried to improve the uncertainty in the model training process by performing learning not only with a single model but also with 10 ensemble models. The trained neural network rainfall prediction model was optimized to generate 10-minute advance prediction data using four consecutive data of the past 30 minutes from the present. The results of deep learning rainfall prediction models are difficult to identify schematically distinct differences, but with ConvLSTM2D U-Net, the magnitude of the prediction error is the smallest and the location of rainfall is relatively accurate. In particular, the ensemble ConvLSTM2D U-Net showed high CSI, low MAE, and a narrow error range, and predicted rainfall more accurately and stable prediction performance than other models. However, the prediction performance for a specific point was very low compared to the prediction performance for the entire area, and the deep learning rainfall prediction model also had limitations. Through this study, it was confirmed that the ConvLSTM2D U-Net neural network structure to account for the change of time could increase the prediction accuracy, but there is still a limitation of the convolution deep neural network model due to spatial smoothing in the strong rainfall region or detailed rainfall prediction.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.18 no.2
• /
• pp.10-15
• /
• 2014

For hypersonic aircraft, increase of flight speeds causes heat loads that are from aerodynamic heat and engine heat. The heat loads could lead structural change of aircraft's component and malfunctioning. Endothermic fuels are liquid hydrocarbon fuels which are able to absorb the heat loads by undergoing endothermic reactions, such as thermal and catalytic cracking. In this study, methylcyclohexane was selected as a model endothermic fuel and experiments on endothermic properties were implemented. To improve heat of endothermic reaction, we applied zeolites and confirmed that HZSM-5 was the best catalyst for the catalytic performance. The objective is to investigate catalytic effects for heat sink improvement. The catalyst could be applied to system that use kerosene fuel as endothermic fuel.

• Journal of the Korea Society for Simulation
• /
• v.22 no.4
• /
• pp.93-98
• /
• 2013

In this paper, the proposed shallow trench isolation structures for high threshold voltage for very large scale and ultra high voltage integrated circuits MOSFET were simulated. Physically based models of hot-carrier stress and dielectric enhanced field of thermal damage have been incorporated into a TCAD tool with the aim of investigating the electrical degradation in integrated devices over an extended range of stress biases and ambient temperatures. As a simulation results, shallow trench structure were intended to be electric functions of passive, as device dimensions shrink, the electrical characteristics influence of proposed STI structures on the transistor applications become stronger the potential difference electric field and saturation threshold voltage.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2011.04a
• /
• pp.357-361
• /
• 2011

본 논문에서는 확률적 불확실성을 포함한 손상 장에서 강성저감 효과를 추정하는 방법을 제안하였다. 실제 교량 구조물에 분포된 손상 장은 매우 불확실하며 손상의 위치와 형상 또한 정확히 알 수 없는 경우가 많다. 그러나 대부분의 손상 추정 문제는 균열이나 손상의 위치와 형상을 기지의 주어진 정보로 가정하고 손상을 추정한다. 제안 기법에서는 이러한 손상의 위치와 형태가 본질적으로 불확실하다는 가정 하에 이 불확실성을 수정 가우스 강성 저감 분포 함수를 도입하여 기술한다. 교량에 국부적으로 발생된 손상은 교량의 요소강성의 저감 분포로 변환되어 손상이 발생한 전체 시스템의 강성을 표현하고 이를 통해 손상이 발생한 시스템의 전체 응답을 해석할 수 있게 된다. 수정 가우스 강성 저감 분포 함수는 손상 분포의 개략적 중심을 표현하는 평균 변수와 강성 저감의 비국소적 분포 특성을 묘사하는 표준편차 변수, 손상 중심의 손상 정도를 표현하는 강성저감 변수로 구성된다. 본 논문에서는 손상 장에서 손상의 위치나 형태에 대한 확률적 불확실성을 기술하는 수정 가우스 강성 저감 분포 함수를 포함한 유한요소모델을 정식화하여 제시한다. 또한 단일 또는 복합 균열로 인해 교량 구조물에 국부적인 손상이 야기된 경우에 대한 수치 예제를 통하여 균열 등에 대한 정보가 불확실하더라도 수정 가우스 강성 저감 분포 함수를 통해 강성 저감 효과가 분석될 수 있음을 확인하였다.