• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.1
• /
• pp.43-48
• /
• 2010

The heat sink system for a main board in a network server computer is built on printed circuit board by an anchor structure, mounted by eutectic SnPb solder. The solder creeping is caused by a constant high temperature condition in the computer and it eventually makes fatal failures. The FE model is used to calculate the stress and predict the life of soldered anchor in the computer. In the model, Anand constitutive equation is employed to simulate creep characteristics of solder. The creep test is conducted to verify and calibrate the solder model. A special jig is designed to mitigate the flexure of printed circuit board and to get the creep deformation of solder only in the test. Test results are compared with analysis and calibration is conducted on Anand model's constants. Precise life prediction of soldered anchor in creep condition can be performed by this model.

• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.338-342
• /
• 2015

Recurrent Neural Network (RNN), a machine learning model which can handle time-series data, can possess more varied structures than a feed-forward neural network, since a RNN allows hidden-to-hidden connections. This research focuses on the network structure among hidden neurons, and discusses the information processing capability of RNN. Time-series learning potential and dynamics of RNNs are investigated upon several well-established network structure models. Hidden neuron network structure is found to have significant impact on the performance of a model, and the performance variations are generally correlated with the criticality of the network dynamics. Especially Preferential Attachment Network model showed an interesting behavior. These findings provide clues for performance improvement of the RNN.

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.306-312
• /
• 2008

In a goal-oriented dialogue, speaker's intention can be approximated by a semantic structure that consists of a pair of a speech act and a concept sequence. Therefore, it is very important to correctly identify the semantic structure of an utterance for implementing an intelligent dialogue system. In this paper, we propose a model to efficiently analyze the semantic structures based on an active teaming method. To reduce the burdens of high-level linguistic analysis, the proposed model only uses morphological features and previous semantic structures as input features. To improve the precisions of semantic structure analysis, the proposed model adopts CRFs(Conditional Random Fields), which show high performances in natural language processing, as an underlying statistical model. In the experiments in a schedule arrangement domain, we found that the proposed model shows similar performances(92.4% in speech act analysis and 89.8% in concept sequence analysis) to the previous models although it uses about a third of training data.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.33 no.11
• /
• pp.106-114
• /
• 2005

This study addresses space simulation test results and thermal modelling verification of HAUSAT-2 nanosatellite STM (Structural-Thermal Model). The thermal modelling of the HAUSAT-2 has been modified in accordance with test results. Thermal analysis results were repeatedly compared with test results for modified thermal modelling. It is verified that the analysis results for modified thermal modelling agree well with test results. Some surface heaters were implemented to simulate solar illumination for HAUSAT-2 Thermal Vacuum/Balance Test. A low-cost and effective thermal test methodology, which is applicable to ultra-small satellite system, was proposed and verified by test results in this study.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.6 no.3
• /
• pp.223-230
• /
• 2005

Lately, massive concrete structures are increasingly built. Mass concrete structures are cast in many stages with construction joints. Individually constructed segment exhibit different heat source properpies and time dependent properties. As such construction stages must be incorporated in a heat of hydration analysis model to truly reflect a real construction process. Thermal stress analysis is conducted to find the way of controlling the thermal crack of pier footing mat in this paper. The footing mat model fur the analysis is $12m\times14m$ area and 3m height. This study show the process of construction stage and analyzes the results for a foundation structure constructed in 2 stage pours.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.8 no.2
• /
• pp.19-25
• /
• 2004

The linear analysis for the balance of linear momentum of a structure is relatively easy to perform, but the error becomes large when the structure experiences large deformation. Therefore, the material and geometric nonlinearity need to be considered for the precise calculations in that case. The plastic flow of a ductile steel-like metal mainly transforms its dissipated mechanical energy into heat, which transfers under the first and second law of thermodynamics. This heat increases the temperature of the material and the strength of the material decreases accordingly, which affects mechanical behavior of the given structure. This paper presents a finite-strain thermo-elasto-plastic steel model. This model can handle large deformation and thermal load simultaneously, which is common during earthquake periods. Two 3-dimensional finite element analyses verify this formulation.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.20 no.5
• /
• pp.653-660
• /
• 2007

Since the temperature of asphalt for deck plate of steel bridge during paying procedure is relatively high as $240^{\circ}C\;to\;260^{\circ}C$, the temperature of deck plate of bridge rises mere than $100^{\circ}C$ and excessive displacement and stress could occur. In order to avoid undesirable failure of base plate and determine the optimal pavement pattern, a thorough thermal analysis is needed. General structural model which is made of beam and plate element should be modified for transient heat transfer analysis; asphalt pavement material and convection effect on surface of structure need to be added. A new technique with the Equivalent Heat Source (EHS) for numerical thermal analysis for steel bridge under thermal load of Guss asphalt pavement is proposed. Since plate/beam elements which were generally used for structural analysis for bridge cannot explain convection effect easily on plate/beam surface, EHS which is determined based on calculated temperature with convection effect is used. To verify the EHS proposed in this study, numerical analyses with plate elements are performed and the results are compared with estimated temperatures. EHS might be used for other thermal analyses of steel bridge such as welding residual stress analysis and bridge fire analysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.458-461
• /
• 2021

유동인구 예측은 상권의 특성에 따른 점포의 입지 선정 및 고객 맞춤형 마케팅 등 민간 분야에서부터 교통망 등 사회 간접 자본 설계를 위한 공공 분야에 이르기까지 다양한 목적으로 연구되어 왔으며, 최근에는 Covid-19 의 확산에 따라 그 중요도가 더욱 높아지고 있다. 보다 정교한 예측을 위해서는 전체적인 유동 인구 뿐만 아니라 특성 별로 세분화된 하위 그룹에 대해서도 정확한 예측이 요구되나, 기존의 예측 모델들은 이러한 데이터의 계층 구조를 고려하지 않았다. 본 연구에서는 세분화된 하위 그룹 별 유동인구의 예측 정확도를 높이기 위해 전체 유동인구의 패턴을 동시에 활용하는 Global-Local 구조 기반의 Deep Learning 유동인구 분석 모델을 제안한다. 실험 결과 단일 시계열 데이터만을 사용하는 경우 대비 5.4%~52.6%의 예측 오류 감소 효과가 있음을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.37-40
• /
• 2024

본 연구에서는 웨어러블 디바이스로부터 수집된 다변량 반려동물 행동 데이터를 처리하기 위해, GCN(Graph Convolutional Network)과 GRU(Gated Recurrent Unit)를 결합한 모델을 제안한다. 제안된 모델은 시계열 내부 구조를 활용하여 그래프 구조로 변환하고, DTW(Dynamic Time Warping) 유사도 분석을 통해 노드 간의 시간적 유사도를 기반으로 엣지를 생성한다. 실험결과로 DTW 기반 엣지 생성 방식이 유클리드 거리 및 선형 방식에 비해 더 높은 성능을 나타냈다. 본 연구는 반려동물의 행동을 정확히 분류하기 위한 효과적인 방법론을 제공한다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.2
• /
• pp.156-164
• /
• 2016

Qualification model(QM) of main payloads including concentrating photovoltaic system using fresnel lens, heating wire cutting type shockless holding and release mechanism, and MEMS-based solid propellant thruster have been developed for the STEP Cube Lab.(Cube Laboratory for Space Technology Experimental Project), which is a pico-class satellite for verification of core space technologies. In this study, we have verified structural safety and functionality of the developed payloads under a qualification temperature range through the QM thermal vacuum test. Additionally, a reliability of thermal model of the payloads has been confirmed by performing a thermal correlation based on the thermal balance test results.