• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.03a
• /
• pp.1324-1331
• /
• 2008

Recently, landslides have frequently occurred on natural slopes during periods of intense rainfall. With a rapidly increasing population on or near steep terrain in Korea, landslides have become one of the most significant natural hazards. Thus, it is necessary to protect people from landslides and to minimize the damage of houses, roads and other facilities. To accomplish this goal, many landslide prediction methods have been developed in the world. In this study, a simple landslide prediction system that enables people to escape the endangered area is introduced. The system is focused to debris flows which happen frequently during periods of intense rainfall. The system is based on the wireless sensor network (WSN) that is composed of sensor nodes, gateway, and server system. Sensor nodes and gateway are deployed with Microstrain G-Link system. Five wireless sensor nodes and gateway are installed at the man-made slope to detect landslide. It is found that the acceleration data of each sensor node can be obtained via wireless sensor networks. Additionally, thresholds to determine whether the slope will be stable or not are proposed using finite element analysis. It is expected that the landslide prediction system by wireless senor network can provide early warnings when landslides such as debris flow occurs.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.2
• /
• pp.136-148
• /
• 1997

The present study has been carried out to develop a computational procedure for the analysis of the off-design performance in centrifugal compressors with vaneless diffusers by integrating empirical loss models and analytical equations. Losses in centrifugal compressors stem from a number of sources and their exact calculation is not yet possible. This study investigates several modeling schemes and shows that a fairly good prediction can be achieved by a proper selection of the most important flow parameters resulting form a meanline one-dimensional analysis. The performance maps for compressors are calculated and compared with measured performance maps. The off-design performance characteristics in terms of the pressure ratio vs. mass flow produced have generally correct forms. However, no universal means have been found to predict accurately the onset of surge. The prediction method developed through this study can serve as a tool to ensure good matching between parts and it can assist the understanding of the operational characteristics of general purpose centrifugal compressors.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2014.10a
• /
• pp.562-562
• /
• 2014

Assessment of aerodynamic noise is becoming increasingly important for automotive manufacturers. Flow passing a vehicle may indeed lead to high interior noise level and affect cabin comfort. Interior noise results from various mechanisms including aerodynamic fluctuations of the disturbed flow around the side mirror or pillar, hydrodynamic and acoustic loading of the car panels and windows, vibration of these panels and acoustic radiation inside the vehicle. Objective of the present study is to capture these important mechanisms in a simulation model and demonstrate the ability of the combined simulation tools Fluent / Virtual.Lab to provide accurate aerodynamic and interior noise prediction results. Previous study focused on the noise generated by the turbulence around the A-pillar structure of the HSM (Hyundai simplified model). The present study also includes the effect of the side-mirror and rain-gutter structures. Complete modeling process is presented including details on the unsteady CFD simulation and the vibro-acoustic model with absorption materials. Guidelines and best practices for building the simulation model are also discussed.

• Journal of Korean Society on Water Environment
• /
• v.22 no.5
• /
• pp.919-925
• /
• 2006

The regression models for the water temperatures of Ban Byeon Stream and Yong Jeon stream were developed using multi-regression method. It was also investigated that the applicability of the stream temperature prediction to two-dimensional numerical simulation to predict the vertical water temperature in Imha Reservoir. Air temperature and dew point as independent variables were selected to be applicable to cases with the different variation of flow rates. The data division of water temperature using a cutoff flow rate of $20m^3/s$ was found to reduce the prediction error of the stream temperature. The mean absolute percent error of the numerical simulation results of the vertical water temperature in Imha Reservoir using the regression models was 11%, which was only 4.3% lager than the simulation result using the measured stream temperature. Therefore, the regression models of the stream temperatures using multi-regression method applied in this study could be applied to predict the vertical water temperature in Imha Reservoir with a good accuracy.

• IE interfaces
• /
• v.23 no.4
• /
• pp.349-356
• /
• 2010

The role of Intelligent Transportation System (ITS) is to efficiently manipulate the traffic flow and reduce the cost in logistics by using the state of the art technologies which combine telecommunication, sensor, and control technology. Especially, the hardware part of ITS is rapidly adapting to the up-to-date techniques in GPS and telematics to provide essential raw data to the controllers. However, the software part of ITS needs more sophisticated techniques to take care of vast amount of on-line data to be analyzed by the controller for their decision makings. In this paper, the authors develop a traffic congestion prediction model based on several different parameters from the sensory data captured in the Vehicle Detection System (VDS). This model uses the neural network technology in analyzing the traffic flow and predicting the traffic congestion in the designated area. This model also validates the results by analyzing the errors between actual traffic data and prediction program.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.7 no.2
• /
• pp.7-14
• /
• 2003

Computational work using the axisymmetric, compressible, Navier-Stokes Equations is carried out to predict the discharge coefficient of mass flow through a micro-critical nozzle. Several kinds of turbulence models and wall functions are employed to validate the computational predictions. The computed results are compared with the previous experimented ones. The present computations predict the experimental discharge coefficients with a reasonable accuracy. It is found that the standard $\kappa$-$\varepsilon$turbulence model with the standard wall function gives a best prediction of the discharge coefficients. The displacement thickness of the nozzle wall boundary layer is evaluated at the nozzle throat and is well compared to a prediction obtained by an empirical equation. The resulting displacement thickness of the wall boundary layer is about 2% to 0.6% of the diameter of the nozzle throat for the Reynolds numbers of 2000 to 20000.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.34 no.11
• /
• pp.73-79
• /
• 2018

In this study, for the prediction of energy consumption in the ventilator, one of the components of the air conditioning system, the predicted results were analyzed and accurate by the change in the number of neurons and inputs. The input variables of the prediction model for the energy volume of the fan were the supply air flow rate, the exhaust air flow rate, and the output value was the energy consumption of the fan. A predictive model has been developed to study with the Levenbarg-Marquardt algorithm through 8760 sets of one-minute resolution. Comparison of actual energy use and forecast results showed a margin of error of less than 1% in all cases and utilization time of less than 3% with very high predictability. MBE was distributed with a learning period of 1.7% to 2.95% and a service period of 2.26% to 4.48% respectively, and the distribution rate of ${\pm}10%$ indicated by ASHRAE Guidelines 14 was high.8.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.339-352
• /
• 2023

Prediction of the time-related traits of pebble flow inside pebble-bed HTGRs is of great significance for reactor operation and design. In this work, an image-driven approach with the aid of a convolutional neural network (CNN) is proposed to predict the remaining time of initially loaded pebbles and the time interval of paired flow images of the pebble bed. Two types of strategies are put forward: one is adding FC layers to the classic classification CNN models and using regression training, and the other is CNN-based deep expectation (DEX) by regarding the time prediction as a deep classification task followed by softmax expected value refinements. The current dataset is obtained from the discrete element method (DEM) simulations. Results show that the CNN-aided models generally make satisfactory predictions on the remaining time with the determination coefficient larger than 0.99. Among these models, the VGG19+DEX performs the best and its CumScore (proportion of test set with prediction error within 0.5s) can reach 0.939. Besides, the remaining time of additional test sets and new cases can also be well predicted, indicating good generalization ability of the model. In the task of predicting the time interval of image pairs, the VGG19+DEX model has also generated satisfactory results. Particularly, the trained model, with promising generalization ability, has demonstrated great potential in accurately and instantaneously predicting the traits of interest, without the need for additional computational intensive DEM simulations. Nevertheless, the issues of data diversity and model optimization need to be improved to achieve the full potential of the CNN-aided prediction tool.

• Food Science and Preservation
• /
• v.20 no.3
• /
• pp.289-295
• /
• 2013

The capacity of a pressure fan can be designed based on the air flow resistance of containers packed with fruits and vegetables in a pressure cooling system. This study was conducted to develop an air flow resistance model that was dependent on changes in the air flow rate and the method of stacking containers. The air flow resistance of a container packed with uniformly shaped balls was 1.5 times greater than the sum of the air flow resistance of a vacant container and that of a wire net container packed with only balls. In addition, the air flow resistance increased exponentially as the width of the stacks increased; however, the air flow resistance did not increase greatly as the length and height of the stacks increased, which indicates that the air flow resistance is primarily influenced by the width of the stack in the air flow direction. The air flow resistance in two lines of stacking was up to 17% less than that of the width of the stack. It was also possible to determine the air flow resistance using a function of the air flow resistance through a single container and develop a prediction model. A prediction model of air flow resistance that is dependent on the stacking method and the air flow resistance of a single container was developed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.58-64
• /
• 2021

As the number of registered vehicles increases, traffic congestion will worsen worse, which may act as an inhibitory factor for urban social and economic development. Through accurate traffic flow prediction, various AI techniques have been used to prevent traffic congestion. This paper uses the data from a VDS (Vehicle Detection System) as input variables. This study predicted traffic flow in five levels (free flow, somewhat delayed, delayed, somewhat congested, and congested), rather than predicting traffic flow in two levels (free flow and congested). The Catboost model, which is a machine-learning algorithm, was used in this study. This model predicts traffic flow in five levels and compares and analyzes the accuracy of the prediction with other algorithms. In addition, the preprocessed model that went through RandomizedSerachCv and One-Hot Encoding was compared with the naive one. As a result, the Catboost model without any hyper-parameter showed the highest accuracy of 93%. Overall, the Catboost model analyzes and predicts a large number of categorical traffic data better than any other machine learning and deep learning models, and the initial set parameters are optimized for Catboost.