• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.590-596
• /
• 2020

In the island areas where system connection with the commercial power grid is difficult, it is quite important to find a method to efficiently manage energy produced with independent microgrids. In this paper, a prosumer management system for P2P power transaction was realized through the testing the power meter and the response rate of the collected data for the power produced in the small-scale microgrids in which hybrid models of solar power and wind power were implemented. The power network of the microgrid prosumer was composed of mesh structure and the P2P power transaction was tested through the power meter and DC power transmitter in the off-grid sites which were independently constructed in three places. The measurement values of the power meter showed significant results of voltage (average): 380V + 0.9V, current (average): + 0.01A, power: 1000W (-1W) with an error range within ±1%. Stabilization of the server was also confirmed with the response rate of 0.32 sec. for the main screen, 2.61 sec. for the cumulative power generation, and 0.11 sec for the power transaction through the transmission of 50 data in real time. Therefore, the proposed system was validated as a P2P power transaction system that can be used as an independent network without transmitted by Korea Electric Power Corporation (KEPCO).

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.1
• /
• pp.59-69
• /
• 2021

Recently, large-scale offshore and coastal structures have been constructed owing to the increasing interest in eco-friendly energy development. To achieve this, precise simulations of waves are necessary to ensure the safe operations of marine structures. Several experiments are required in the field to understand the offshore wave; however, in terms of scale, it is difficult to control variables, and the cost is significant. In this study, numerical waves under various wave conditions are produced using a piston-type wavemaker, and the produced wave profiles are verified by comparing with the results from a numerical wave tank (NWT) modeled using the smoothed particle hydrodynamics (SPH) method and theoretical equations. To minimize the effect by the reflected wave, a mass-weighted damping zone is set at the right end of the NWT, and therefore, stable and uniform waves are simulated. The waves are generated using the linear and Stokes wave theories, and it is observed that the numerical wave profiles calculated by the Stokes wave theory yield high accuracy. When the relative depth is smaller than two, the results show good agreement irrespective of the wave steepness. However, when the relative depth and wave steepness are larger than 2 and 0.04, respectively, the errors are negligible if the measurement position is close to the excitation plate. However, the error is 10% or larger if the measurement position is away from the excitation location. Applicable target wave ranges are confirmed through various case studies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.352-361
• /
• 2021

An underwater positioning method that can be applied to structures for underwater construction is being developed at the Korea Institute of Ocean Science and Technology. The method uses an extended Kalman filter (EKF) based on an inertial navigation system for precise and continuous position estimation. The observation matrix was configured to be variable in order to apply asynchronous measured sensor data in the correction step of the EKF. A Doppler velocity logger (DVL) can acquire signals only when attached to the bottom of an underwater structure, and it is difficult to install and recover. Therefore, a complex sensor device for underwater structure attachment was developed without a DVL in consideration of an underwater construction environment, installation location, system operation convenience, etc.. Its performance was verified through a water tank test. The results are the measured underwater position using an ultra-short baseline, the estimated position using only a position vector, and the estimated position using position/velocity vectors. The results were compared and evaluated using the circular error probability (CEP). As a result, the CEP of the USBL alone was 0.02 m, the CEP of the position estimation with only the position vector corrected was 3.76 m, and the CEP of the position estimation with the position and velocity vectors corrected was 0.06 m. Through this research, it was confirmed that stable underwater positioning can be carried out using asynchronous sensors without a DVL.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.5
• /
• pp.126-134
• /
• 2020

In the case of an earthquake, the fluid storage structure generates hydraulic pressure due to the fluctuation of the fluid. At this time, the hydraulic pressure of the fluid changes not only the peaked acceleration of the earthquake but also the sloshing height of the fluid free water surface. Factors influencing this change in load include the shape of the seismic wave, the maximum seismic strength, the size of the fluid storage structure, the width of the structure, and the height of the fluid. In this study, the effect of the ratio between the height of the fluid and the width of the structure was investigated on the fluctuation characteristics of the fluid. 200mm and 140mm of fluid were placed in a water storage tank with a width of 500mm, and a real seismic wave was applied to measure the shape of the fluctuation of the fluid free water surface. The similarity between the experiment and the analysis was verified through the S.P.H(Smoothed Particle Hydrodynamic) technique, one of the numerical analysis techniques. It was confirmed that the free water surface of the fluid showed a similar shape, through comparison of experiment and analysis. And based on this results, SPH technique was applied to analyze the fluctuation shape of the fluid free water surface while varying the ratio between the fluid height and the structure width. An equation to predict the maximum and minimum heights of the fluid free water surface during an earthquake was proposed, and it was confirmed that the error between the maximum and minimum heights of the fluid free water surface predicted by the proposed equation was within a maximum of 3%.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2021

This is a basic study on the development of deep learning-based algorithms to detect smoke before the smoke detector operates in the event of a ship fire, analyze and utilize the detected data, and support fire suppression and evacuation activities by predicting the spread of smoke before it spreads to remote areas. Proposed algorithms were reviewed in accordance with the following procedures. As a first step, smoke images obtained through fire simulation were applied to the YOLO (You Only Look Once) model, which is a deep learning-based object detection algorithm. The mean average precision (mAP) of the trained YOLO model was measured to be 98.71%, and smoke was detected at a processing speed of 9 frames per second (FPS). The second step was to estimate the spread of smoke using the coordinates of the boundary box, from which was utilized to extract the smoke geometry from YOLO. This smoke geometry was then applied to the time series prediction algorithm, long short-term memory (LSTM). As a result, smoke spread data obtained from the coordinates of the boundary box between the estimated fire occurrence and 30 s were entered into the LSTM learning model to predict smoke spread data from 31 s to 90 s in the smoke image of a fast fire obtained from fire simulation. The average square root error between the estimated spread of smoke and its predicted value was 2.74.

• Journal of the Korean Society of Radiology
• /
• v.16 no.3
• /
• pp.295-302
• /
• 2022

Sparse-view computed tomography (CT) imaging technique is able to reduce radiation dose, ensure the uniformity of image characteristics among projections and suppress noise. However, the reconstructed images obtained by the sparse-view CT imaging technique suffer from severe artifacts, resulting in the distortion of image quality and internal structures. In this study, we proposed a convolutional neural network (CNN) with wavelet transformation and residual learning for reducing artifacts in sparse-view CT image, and the performance of the trained model was quantitatively analyzed. The CNN consisted of wavelet transformation, convolutional and inverse wavelet transformation layers, and input and output images were configured as sparse-view CT images and residual images, respectively. For training the CNN, the loss function was calculated by using mean squared error (MSE), and the Adam function was used as an optimizer. Result images were obtained by subtracting the residual images, which were predicted by the trained model, from sparse-view CT images. The quantitative accuracy of the result images were measured in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The results showed that the trained model is able to improve the spatial resolution of the result images as well as reduce artifacts in sparse-view CT images effectively. Also, the trained model increased the PSNR and SSIM by 8.18% and 19.71% in comparison to the imaging model trained without wavelet transformation and residual learning, respectively. Therefore, the imaging model proposed in this study can restore the image quality of sparse-view CT image by reducing artifacts, improving spatial resolution and quantitative accuracy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.502-508
• /
• 2021

Predicting the settlement of soft ground is an important aspect of soft ground design. In this study, a method is proposed that increases the reliability of settlement predictions based on-site investigation data, including piezocone penetration test results, at the Gimhae-Jinyoung district, adjacent area to the Nakdong River. Soils in the area waweres classified using the Robertson Chart (1986, 1990), and theoretical settlement was calculated using the equations proposed by Terzaghi (1925) and Sanglerat (1972). SPSS was used to obtain the correlation between theoretical and measured settlements. Results produced settlement prediction errors for the Terzaghi and Sanglerat methods of 17.28% and 26.96%, respectively. A correction factor calculated by SPSS correlation analysis for the relation between and theoretical and measured settlements is proposed that improves the reliability of settlement prediction in soils of the classification examined.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.4
• /
• pp.17-27
• /
• 2021

Streamflow prediction is a very vital disaster mitigation approach for effective flood management and water resources planning. Lately, torrential rainfall caused by climate change has been reported to have increased globally, thereby causing enormous infrastructural loss, properties and lives. This study evaluates the contribution of rainfall to streamflow prediction in normal and peak rainfall scenarios, typical of the recent flood at Piney Resort in Vernon, Hickman County, Tennessee, United States. Daily streamflow, water level, and rainfall data for 20 years (2000-2019) from two USGS gage stations (03602500 upstream and 03599500 downstream) of the Piney River watershed were obtained, preprocesssed and fitted with Long short term memory (LSTM) model. Tensorflow and Keras machine learning frameworks were used with Python to predict streamflow values with a sequence size of 14 days, to determine whether the model could have predicted the flooding event in August 21, 2021. Model skill analysis showed that LSTM model with full data (water level, streamflow and rainfall) performed better than the Naive Model except some rainfall models, indicating that only rainfall is insufficient for streamflow prediction. The final LSTM model recorded optimal NSE and RMSE values of 0.68 and 13.84 m³/s and predicted peak flow with the lowest prediction error of 11.6%, indicating that the final model could have predicted the flood on August 24, 2021 given a peak rainfall scenario. Adequate knowledge of rainfall patterns will guide hydrologists and disaster prevention managers in designing efficient early warning systems and policies aimed at mitigating flood risks.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.502-517
• /
• 2022

As the use of TBM increases, research has recently increased to to analyze TBM data with machine learning techniques to predict the exchange cycle of disc cutters, and predict the advance rate of TBM. In this study, a regression prediction of disc cutte wear of slurry shield TBM site was made by combining machine learning based on the machine data and the geotechnical data obtained during the excavation. The data were divided into 7:3 for training and testing the prediction of disc cutter wear, and the hyper-parameters are optimized by cross-validated grid-search over a parameter grid. As a result, gradient boosting based on the ensemble model showed good performance with a determination coefficient of 0.852 and a root-mean-square-error of 3.111 and especially excellent results in fit times along with learning performance. Based on the results, it is judged that the suitability of the prediction model using data including mechanical data and geotechnical information is high. In addition, research is needed to increase the diversity of ground conditions and the amount of disc cutter data.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.10 no.4
• /
• pp.435-442
• /
• 2022

In this study, the density of KS L 5110 was compared with that of gas pycnometer and electronic densimeter for efficient density management of cement, blast furnace slag powder and fly ash. Correlation and usability according to the test method were reviewed, and based on the results of the experiment, the availability of alternative test methods was analyzed. As a result of the density test according to test methods, the density of cement, blast furnace slag powder and fly ash tended to decrease in the order of gas pycnometer, KS L 5110 and electronic densimeter. Because the volume range of the sample to be evaluated is different depending on test methods. The coefficient of determination R² was in the range of 0.71 to 0.93, and the correlation according to test methods showed a relatively good correlation. If correction is applied through correlation, it is analyzed that alternative test methods can be used. As a result of the usability review considering the test procedure, measurement time and coefficient of variation, the gas pycnometer had the simplest test procedure and good reliability. In addition, it is expected that the reproducibility between the testers is relatively high because the skill is not greatly required.