• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.1-6
• /
• 2019

The objective of this study was to investigate performance characteristics of thermal management system(TMS) in a fuel cell electric vehicle with 100kW Fuel Cell(FC) system. In order to build up analytic modelling for TMS, each component was installed and tested under various operating conditions, such as water pump, radiator, 3-Way valve, COD heater, and FC stack etc. and as the results of them, correlations reflecting component's characteristics with flow rate, air velocity were developed. Developed analytic modelling was carried out under various operating conditions on the road. To verify modelling's accuracy, after prediction for optimum coolant flow rate was fulfilled under certain operating conditions, such as FC system, water pump speed, opening of 3-way valve, and pipe resistance, analytic and experimental values were compared and good agreement was shown. In order to predict cold-start operating performance for analytic modelling, coolant temperature variation was analyzed with $-20^{\circ}C$ ambient temperature and duration was predicted to rise in optimum temperature for FC. Because there is appropriate temperature difference between inlet and outlet of FC stack to operate FC system properly, related analysis was performed with respect to power consumption for TMS and heat rejection rate and performance map was depicted along with FC operating conditions.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.4
• /
• pp.11-19
• /
• 2006

For the last decade, the hi-directional testing method has been advantageous over the conventional pile load testing method in many aspects. However, because the hi-directional test uses a loading mechanism entirely different from that of the conventional pile load testing method, many investigators and practicing engineers have been concerned that the hi-directional test would give inaccurate results, especially about the pile head settlement behavior. Therefore, a hi-directional load test and the conventional top-down load test were executed on 1.5 m diameter cast-in-situ concrete piles at the same time and site. Strain gauges were placed on the piles. The two tests gave similar load transfer curves at various depth of piles. However, the top-down equivalent curve constructed from the hi-directional load test results predicted the pile head settlement under the pile design load to be about one half of that predicted by the conventional top-down load test. To improve the prediction accuracy of the top-down equivalent curve, a simple method that accounts for the pile compression is proposed. It was also shown that the strain gauge measurement data from the hi-directional load test could reproduce almost the same top-down curve.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• Journal of Digital Convergence
• /
• v.15 no.11
• /
• pp.245-250
• /
• 2017

Flash floods is defined as the flooding of intense rainfall over a relatively small area that flows through river and valley rapidly in short time with no advance warning. So that it can cause damage property and casuality. This study is to establish the flash-flood warning system using 38 accident data, reported from the National Disaster Information Center and Land Surface Model(TOPLATS) between 2009 and 2012. Three variables were used in the Land Surface Model: precipitation, soil moisture, and surface runoff. The three variables of 6 hours preceding flash flood were reduced to 3 factors through factor analysis. Decision tree, random forest, Naive Bayes, Support Vector Machine, and logistic regression model are considered as big data methods. The prediction performance was evaluated by comparison of Accuracy, Kappa, TP Rate, FP Rate and F-Measure. The best method was suggested based on reproducibility evaluation at the each points of flash flood occurrence and predicted count versus actual count using 4 years data.

• International Journal of Highway Engineering
• /
• v.9 no.1 s.31
• /
• pp.1-15
• /
• 2007

The objective of this paper is the establishment of finite element analysis frame work for pavement research. Finite element analysis results simulating various loading experiments are verified with sensor measurements obtained from the KHC Test Road. The accuracy of the finite element analysis can be supported by these efforts so that it helps spread out the finite element analysis to pavement research and design processes. The finite element model used in this research is the full 3D nonlinear model including concrete slab, lean concrete base, subbase, shoulder, dowel, and tie-bar. In order to accomplish the accurate verification, the loading condition and the pavement temperature distribution are exactly simulated with field measured data. The curling behavior and the strain distribution are compared with measured responses from the loading tests with a truck and the FWD. Strain and curling predictions from the concrete slab are matched well with measured responses but the strain prediction from the lean concrete base is not matched with measured response. In addition, the magnitude of permanent curling is evaluated with the finite element analysis.

• Journal of Korea Water Resources Association
• /
• v.43 no.9
• /
• pp.823-833
• /
• 2010

Open-channel flows with submerged vegetation show two distinct flow structures in the vegetation and upper layers. That is, the flow in the vegetation layer is featured by relatively uniform mean velocity with suppressed turbulence from shear, while the flow in the upper layer is akin to that in the plain open-channel. Due to this dual characteristics, the flow has drawn many hydraulic engineers' attentions. This study compares layer-averaged models for flows with submerged vegetation. The models are, in general, classified into two-layer and three-layer models. The two-layer model divides the flow depth into vegetation and upper layers, while the three-layer model further divides the vegetation layer into inner and outer vegetation layers depending on the influence of the bottom roughness. This study compares the two-layer model and the three layer-model. It is found that the two-layer model predicts better the average value of the velocity and the prediction by the three-layer model is sensitive to Reynolds shear stress. In the three-layer model, the mean flow in the inner vegetation layer does not affect the flow seriously, which motivates the proposal of the modified two-layer model. The two-layer model, capable of predicting non-uniform mean velocity, is based on the Reynolds stress which is linear and of power form in the upper and vegetation layers, respectively. Application results reveal that the modified two-layer model predicts the mean velocity at an accuracy similar to the two- and three-layer models, but it predicts poorly in the case of very low vegetation density.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.6
• /
• pp.623-641
• /
• 2020

About 5 km length of tunnels were constructed by mechanized tunnelling method using closed type shield TBM. In order to avoid construction delay problems for ensuring timely electricity transmission, it is necessary to increase the prediction accuracy of the excavation process involving machines according to rock mass types. This is important to corroborate the project duration and optimum operation for various considerations involved in the machine. So, full-scale tunnelling tests were performed for developing the advance rate model to be appropriately used for 3.6 m diameter shield TBM. About 100 test cases were established and performed using various operational parameters such as thrust force and rotational speed of cuttterhead in representative uniaxial compressive strengths. Accordingly, relationships between normal force and penetration depth and, between UCS and torque were suggested which consider UCS and thrust force conditions according to weathered, soft, hard rocks. Capacity analysis of cutterhead was performed and optimum operational conditions were also suggested based on the developed model. Based on this study, it can be expected that the project construction duration can be reduced and users can benefit from the provision of earlier service.

• Economic and Environmental Geology
• /
• v.50 no.3
• /
• pp.239-250
• /
• 2017

Physically based landslide susceptibility analysis has been recognized as an effective analysis method because it can consider the mechanism of landslide occurrence. The physically based analysis used the slope geometry and geotechnical properties of slope materials as input. However, when the physically based approach is adopted in regional scale area, the uncertainties were involved in the analysis procedure due to spatial variation and complex geological conditions, which causes inaccurate analysis results. Therefore, probabilistic method have been used to quantify these uncertainties. However, the uncertainties caused by lack of information are not dealt with the probabilistic analysis. Therefore, fuzzy set theory was adopted in this study because the fuzzy set theory is more effective to deal with uncertainties caused by lack of information. In addition, the vertex method and Monte Carlo simulation are coupled with the fuzzy approach. The proposed approach was used to evaluate the landslide susceptibility for a regional study area. In order to compare the analysis results of the proposed approach, Monte Carlo simulation as the probabilistic analysis and the deterministic analysis are used to analyze the landslide susceptibility for same study area. We found that Fuzzy Monte Carlo simulation showed the better prediction accuracy than the probabilistic analysis and the deterministic analysis.

• Ecology and Resilient Infrastructure
• /
• v.10 no.4
• /
• pp.116-124
• /
• 2023

As the flood damage on small streams increase due to the increase in frequency of extreme climate events, the need to measure hydraulic data of them has increased for disaster risk management. National Disaster Management Institute, Ministry of Interior and Safety develops CADMT, a CCTV-based automatic discharge measurement technology, and operates pilot small streams to verify its performance and develop disaster risk management technology. The research selects two small streams such as the Neungmac and the Jungsunpil streams to develop the Nomograph by using the 4-Parameter Logistic method using only the observed rainfall data from the Automatic Weather System operated by the Korea Meteorological Agency closest to the small streams and discharge data collected by using the CADMT. To evaluate developed Nomograph, the research forecasts floods discharges in each small stream and compares the result with the observed discharges. As a result of the evaluations, the forecasted value is found to represent the observed value well, so if more accurate observed data are collected and the Nomograph based on it is developed in the future, the high-accuracy flood prediction and warning will be possible.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.2
• /
• pp.86-102
• /
• 2012

For predictive flooded area susceptibility mapping, this study applied and verified probability model and the frequency ratio using a geographic information system (GIS) and frequency raio. Flooded areas were identified in the study area of field surveys, For predictive flooded area susceptibility mapping, this study applied and verified probability model and the frequency ratio using a geographic information system (GIS) and frequency raio. Flooded areas were identified in the study area of field surveys, and maps of the topography, geology, landcover and green infrastructure were constructed for a spatial database. The factors that influence flooded areas occurrence, such as slope gradient, slope, aspect and curvature of topography and distance from darinage, were calculated from the topographic database. Lithology and distance from fault were extracted and calculated from the geology database. The frequency ratio coefficient is overlaid for flooded areas susceptibility mapping as each factor's ratings. Then the flooded areas susceptibility map was verified and compared using the existing flooded areas. As the verification results, the frequency ratio model showed 82% in prediction accuracy. The method can be used to reduce hazards associated with flooded areas and to plan land use.