• Journal of the Korean Society of Propulsion Engineers
• /
• v.14 no.3
• /
• pp.52-60
• /
• 2010

Combustion stability tests of 30 $ton_f$-class LRE thrust chamber with double swirl coaxial injector were carried out in domestic ground combustion test facility by means of artificial perturbation method. In these tests, thrust chambers with varying design factors like recess number of injector, baffle length, types of film cooling and chamber diameter were used and test results showed that these design factors are closely related with high frequency combustion stability. By using the oscillation decrement instead of the decay time in the combustion stability analysis of artificially perturbed LRE thrust chamber, it was confirmed that increment of damping factor results in the improvement of high frequency combustion stability of LRE thrust chamber.

• Journal of the Korean Geosynthetics Society
• /
• v.10 no.4
• /
• pp.81-92
• /
• 2011

In order to understand evaluation of the seismic stability of a fill dam, we made chambers of 1:100, 1:70, and 1:50 (the ratio of the miniature), considering the law of similarity based on drawings of three representative cross sections. And we measured an increase in acceleration, excess pore water pressure, and vertical/horizontal displacement after applying Hachinohe wave (long period), Ofunato wave (short period), and artificial wave, complying with the domestic standards, in order to evaluate the stability and interaction between the ground, the structure, and fluids based on the measurements. As a result, we could observe that displacement of the target cross section was relatively small compared to the allowed level of 30 cm, ensuring proper stability for an earthquake. Regarding the acceleration measurements, the increase rate was 20% for Hachinohe wave and Ofunato wave but 30% for the artificial wave. With respect to the excess pore water pressure, it was lower than 1 (which is the permissible ratio for liquefaction) ensuring proper stability as well.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.16 no.6
• /
• pp.93-107
• /
• 2013

Construction of an artificial wetland for the growth of Sphagnum palustre with emergent macrophytes (Phragmites australis, Typha angustifolia, and Zizania latifolia) was firstly tried and the growth of those plant components according to various environmental combinations has been monitored for three years. Above-ground dry weight of Z. latifolia ($1,500g/m^2$) was higher than T. angustifolia ($900g/m^2$) and P. australis ($500g/m^2$) under most environmental conditions. In overall, planted emergent macrophytes seemed to prefer polishing sand without moss peat as a substrate and relatively deep water-depth condition (20cm) rather than shallow water-depth (5cm). Despite of high calcium content in inflow water (> 15ppm) into the constructed wetland, S. palustre populations have survived in most experimental plots during the monitoring period. Substrate layer including moss peat with high surface-area might play a role as an ion-filter. After three years, relatively thicker litter-layer in Z. latifolia plots due to vigorous growth appeared to heavily depress S. palustre by physical compressing and complete shading processes. Most of all, for the continuous growth of S. palustre, physio-chemical characteristics of water and substrate must be carefully managed. In addition, companion emergent species should be also cautiously selected not to depress S. palustre by much litter production. We suggest P. australis and T. angustifolia as companion species rather than Z. latifolia.

• Journal of the Korean Geotechnical Society
• /
• v.18 no.3
• /
• pp.113-125
• /
• 2002

Although there are several empirical and semi-empirical formulae available for predicting ground surface settlement, most of them do not simultaneously take into consideration all the relevant factors, resulting in inaccurate predictions. In this study, an artificial neural network (ANN) is incorporated with 113 of monitored field results to predict surface settlement for a tunnel site with prescribed conditions. To achieve this, a format for a database of monitored field data is first proposed and then used for sorting out a variety of monitored data sets available in Korea Institute of Construction Technology. An optimal neural network model is suggested through preliminary parametric studies and introduces a concept of RSE (Yang and Zhang, 1997) in sensitivity analysis for various major factors affecting the surface settlement in tunnelling. It is seen in some examples that the RSE rationally enables to recognize the most significant factors of all the contributing factors. Two verification examples are undertaken with the trained ANN using the database created in this study. It is shown from the examples that the ANN has adequately recognized the characteristics of the monitored data sets retaining a generality fur further prediction.

• Journal of the Korean Geotechnical Society
• /
• v.32 no.11
• /
• pp.31-42
• /
• 2016

Usually the seismic stability analysis of slope uses the pseudostatic analysis considering the inertial force by the earthquake as a static load. Geostructures such as slope include the uncertainty of soil properties. Therefore, it is necessary to consider probabilistic method for stability analysis. In this study, the probabilistic stability analysis of slope considering the uncertainty of soil properties has been performed. The fragility curve that represents the probability of exceeding limit state of slope as a function of the ground motion has been established. The Monte Carlo Simulation (MCS) has been implemented to perform the probabilistic stability analysis of slope with pseudostatic analysis. A procedure to develop the fragility curve by the pseudostatic horizontal acceleration has been presented by calculating the probability of failure based on the Artificial Neural Network (ANN) based response surface technique that reduces the required time of MCS. The results showed that the proposed method can get the fragility curve that is similar to the direct MCS-based fragility curve, and can be efficiently used to reduce the analysis time.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 1999.10a
• /
• pp.52-57
• /
• 1999

Korea Earthquake Monitoring System(KEMS) in the Korea Institute of Geology Mining and Materials(KIGAM) as detected more than 1000 events since the end of 1998. But not all events are interpreted as earthquakes because many events are concentrated on daytime. It strongly implies that in addition to earthquake these events include artificial effects such as industrial blasting. Before the determination of eathquake charactertistics in the korean peninsula it is necessary to discriminate the detected events as earthquakes or artificial events. For the discriminant study KIGAM and SMU(Southern Methodist University) installed a triangular four-element 1-km aperture seismo-acoustic array at Chul-Won area northeast of Seoul Korea. Each array element includes a GS-13 seismometer in the bottom of borehole and a Validyne DP250-14 microbarometer sensor mounted inside of the borehole 1,2 meter deep connected to a 11 arm radial array of 10m porous soaker hoses. This array introduce the use of 2.4-GHz radios for inter-array self-contained solar-charged power system and GPS time-keeping system. A 24-bit digital data acquisition system performs 40 SPS in the infrasound and seismometer data. Velocity and direction of wind and temperature are also measured at hub site and included to the data stresam. This seismo-acoustic array will be used to identify and locate associated with industrial blasting and these identified and located events will be applied to form a ground truth database useful to assist the other development of discriminant studies.

• The korean journal of orthodontics
• /
• v.51 no.2
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• Journal of Biomedical Engineering Research
• /
• v.44 no.3
• /
• pp.211-217
• /
• 2023

Recently, many studies have introduced artificial intelligence systems in the surgical process to reduce the incidence and mortality of complications in patients. Bleeding is a major cause of operative mortality and complications. However, there have been few studies conducted on detecting bleeding in surgical videos. To advance the development of deep learning models for detecting intraoperative hemorrhage, three models have been trained and compared; such as, YOLOv5, RetinaNet50, and RetinaNet101. We collected 1,016 bleeding images extracted from five surgical videos. The ground truths were labeled based on agreement from two specialists. To train and evaluate models, we divided the datasets into training data, validation data, and test data. For training, 812 images (80%) were selected from the dataset. Another 102 images (10%) were used for evaluation and the remaining 102 images (10%) were used as the evaluation data. The three main metrics used to evaluate performance are precision, recall, and false positive per image (FPPI). Based on the evaluation metrics, RetinaNet101 achieved the best detection results out of the three models (Precision rate of 0.99±0.01, Recall rate of 0.93±0.02, and FPPI of 0.01±0.01). The information on the bleeding detected in surgical videos can be quickly transmitted to the operating room, improving patient outcomes.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.601-609
• /
• 2023

In this paper, we propose an artificial intelligence-based high-speed fault diagnosis method using an FPGA in the event of a ground fault in a DC system. When applying artificial intelligence algorithms to fault diagnosis, a substantial amount of computation and real-time data processing are required. By employing an FPGA with AI-based high-speed fault diagnosis, the DC breaker can operate more rapidly, thereby reducing the breaking capacity of the DC breaker. therefore, in this paper, an intelligent high-speed diagnosis algorithm was implemented by collecting fault data through fault simulation of a DC system using Matlab/Simulink. Subsequently, the proposed intelligent high-speed fault diagnosis algorithm was applied to the FPGA, and performance verification was conducted.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.3
• /
• pp.43-51
• /
• 2024

Dynamic responses of nuclear power plant structure subjected to earthquake loads should be carefully investigated for safety. Because nuclear power plant structure are usually constructed by material of reinforced concrete, the aging deterioration of R.C. have no small effect on structural behavior of nuclear power plant structure. Therefore, aging deterioration of R.C. nuclear power plant structure should be considered for exact prediction of seismic responses of the structure. In this study, a machine learning model for seismic response prediction of nuclear power plant structure was developed by considering aging deterioration. The OPR-1000 was selected as an example structure for numerical simulation. The OPR-1000 was originally designated as the Korean Standard Nuclear Power Plant (KSNP), and was re-designated as the OPR-1000 in 2005 for foreign sales. 500 artificial ground motions were generated based on site characteristics of Korea. Elastic modulus, damping ratio, poisson's ratio and density were selected to consider material property variation due to aging deterioration. Six machine learning algorithms such as, Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Artificial Neural Networks (ANN), eXtreme Gradient Boosting (XGBoost), were used t o construct seispic response prediction model. 13 intensity measures and 4 material properties were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks present good prediction performance considering aging deterioration.