• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2019.11a
• /
• pp.60-61
• /
• 2019

Concrete carbonation is one of the factors that reduce the durability of concrete. In modern times, due to industrialization, the carbon dioxide concentration in the atmosphere is increasing, and the impact of carbonation is increasing. So, it is important to understand the carbonation resistance according to the concrete compounding to secure the concrete durability life. In this study, we want to predict the concrete carbonation velocity coefficient, which is an indicator of the carbonation resistance of concrete, through the deep learning algorithm, and to find the activation function suitable for the prediction of carbonation rate coefficient as a process to determine the learning accuracy through the deep learning algorithm. In the scope of this study, using the ReLU function showed better accuracy than using other activation functions.

• Journal of the Korean Geosynthetics Society
• /
• v.15 no.2
• /
• pp.1-12
• /
• 2016

In this study, laboratory mixture design test and field test were performed to evaluate applicability of eco-friendly binder material (CMD-SOIL) using desulfurized dust in deep cement mixing method (DCM). As a result of laboratory mixture design test, the uniaxial compressive strength of CMD-SOIL was up to 1.136 times bigger than slag cement by changing the water content, mixing rate, and W/B. Also, it had shown the strength up to 1.222 times bigger in shell content and up to 1.363 times in mixing of floating soil. As a result of field test, field strength/laboratory design criterion strength ratio (${\lambda}$) is shown 0.77. And this result was similar to earlier studies. From this result, CMD-SOIL can show the same efficiency compared with existing binder.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.247-253
• /
• 2004

As a large scale port development in coastal waters proceeds step by step and populations in the vicinity of port are getting increased, the issue on "how to dispose the treated municipal water and wastewater in harbor" brings peoples′ concern. The submarine outfall system discharges the primary or secondary treated effluent at the coastline or in deep water, or between these two. The effluent, which has a density similar to that of fresh water, rises to the sea surface forming plume or jet, together with entraining the surrounding sea water and becomes very dilute. We intended in this paper to investigate the impact on dilution of effluent and the behavior of flume under the conditions of the seasonal and spatial temperature variations, which have not been noticeable in designing effective marine outfall system. To predict and analyze the behaviour and dilution characteristics of plume not just with the effluent temperature, but also with the seasonal variation of temperature of surround water and tidal changes, CORMIX(Cornell Mixing Zone Expert System)-GI have been applied. The results should be used with caution in evaluation the mixing zone characteristics of discharged water. We hope to help for the effective operation of outfall system, probable outfall design, protection of water quality, and warm water discharges from a power plant, etc.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.506-515
• /
• 2023

This study is to find a method to learn engine sound after the start-up of a diesel generator installed in nuclear power plant with an unsupervised deep learning algorithm (CNN autoencoder) and a new method to predict the failure of a diesel generator using it. In order to learn the sound of a diesel generator with a deep learning algorithm, sound data recorded before and after the start-up of two diesel generators was used. The sound data of 20 min and 2 h were cut into 7 s, and the split sound was converted into a spectrogram image. 1200 and 7200 spectrogram images were created from sound data of 20 min and 2 h, respectively. Using two different deep learning algorithms (CNN autoencoder and binary classification), it was investigated whether the diesel generator post-start sounds were learned as normal. It was possible to accurately determine the post-start sounds as normal and the pre-start sounds as abnormal. It was also confirmed that the deep learning algorithm could detect the virtual abnormal sounds created by mixing the unusual sounds with the post-start sounds. This study showed that the unsupervised anomaly detection algorithm has a good accuracy increased about 3% with comparing to the binary classification algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.475-482
• /
• 2018

In this paper, we present a study on data augmentation methods for DNN (Deep Neural Network)-based audio tagging. In this system, an audio signal is converted into a mel-spectrogram and used as an input to the DNN for audio tagging. To cope with the problem associated with a small number of training data, we augment the training samples using time stretching, pitch shifting, dynamic range compression, and block mixing. In this paper, we derive optimal parameters and combinations for the augmentation methods through audio tagging simulations.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.260-267
• /
• 2021

In this paper, we intend to use a new mixed model of YoloV5 and DeepSort. For fire detection, we want to increase the accuracy by automatically extracting the characteristics of the flame in the image from the training data and using it. In addition, the high false alarm rate, which is a problem of fire detection, is to be solved by using this new mixed model. To confirm the results of this paper, we tested indoors and outdoors, respectively. Looking at the indoor test results, the accuracy of YoloV5 was 75% at 253Frame and 77% at 527Frame, and the YoloV5+DeepSort model showed the same accuracy at 75% at 253 frames and 77% at 527 frames. However, it was confirmed that the smoke and fire detection errors that appeared in YoloV5 disappeared. In addition, as a result of outdoor testing, the YoloV5 model had an accuracy of 75% in detecting fire, but an error in detecting a human face as smoke appeared. However, as a result of applying the YoloV5+DeepSort model, it appeared the same as YoloV5 with an accuracy of 75%, but it was confirmed that the false positive phenomenon disappeared.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.320-324
• /
• 2023

As urbanization accelerates and facilities that use energy increase, human life and property damage due to fire is increasing. Therefore, a fire monitoring system capable of quickly detecting a fire is required to reduce economic loss and human damage caused by a fire. In this study, we aim to develop an improved artificial intelligence model that can increase the accuracy of low fire alarms by mixing DeepSORT, which has strengths in object tracking, with the YOLOv5s model. In order to develop a fire detection model that is faster and more accurate than the existing artificial intelligence model, DeepSORT, a technology that complements and extends SORT as one of the most widely used frameworks for object tracking and YOLOv5s model, was selected and a mixed model was used and compared with the YOLOv5s model. As the final research result of this paper, the accuracy of YOLOv5s model was 96.3% and the number of frames per second was 30, and the YOLOv5s_DeepSORT mixed model was 0.9% higher in accuracy than YOLOv5s with an accuracy of 97.2% and number of frames per second: 30.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2004.05a
• /
• pp.178-182
• /
• 2004

To establish the design criteria for construction of the rubble mound on improved ground, two kinds of analyses for the soil deformation behavior and the slope stability were performed on various cases for rubble mounds, soft grounds and back fills with application of the finite element method and the Bishop simplified method. The horizontal displacements and settlements at the crest of rubble mounds were analyzed as a function of the safety factor of embankments. The analyzed result shows that the soil movement increases considerably when the safety factor of rubble mounds is lower than 1.3.

• Journal of Ocean Engineering and Technology
• /
• v.15 no.1
• /
• pp.73-78
• /
• 2001

Soundness evaluation of a structure being constructed under the sea is usually difficult. In this study, a cross-hole sonic logging(CSL) which have been used for non-destructive test of concrete piles is adopted for the integrity test and monitoring of DCM(deep cement mixing) treated soils. Chemical and physical characteristics of raw ground materials are analysed to delineate ground environmental effects on the strength of DCM treated soils. In order to convert cross-hole sonic logging data into compressive strength, correlations between compressive strengths and wave velocities of core samples have been obtained. It is found that there is little effect of ground environment on the strength of the DCM treated soils, and the density distribution of core samples and cross-hole logging data show that a defective zone may exist in the DCM treated soils. With the time lapse, however, the defective zone has been cured and consequently, compressive strength of the DCM treated soils increases and satisfies the design parameter. From this study it can be concluded that the cross-hole sonic logging can be used for the integrity test as well as monitoring the curing stage of the structures, successfully.

• Journal of the Korean Geosynthetics Society
• /
• v.20 no.4
• /
• pp.19-32
• /
• 2021

In this study, evaluation and consideration of domestic/overseas design, construction, and quality control performed by the authors on the deep cement mixing method were performed, and improvements for the development of the DCM method were suggested in the future. As a result of this study, it was found that the cross-sectional area correction for strength is required during the laboratory test of mix proportion, and caution is required because the extrapolation method may lead to different results from the actual one. Applicable design methods should be selected in consideration of both the improvement ratio and the type of improvement during design, and it was confirmed that the allowable compressive strength to which the safety factor was applied refers to the standard value for stability review and not the design parameters. In the case of the stress concentration ratio, rather than applying a conventional value, it was possible to perform economical design by calculating the experimental and theoretical stress concentration ratio reflecting the design conditions. In the case where pre-boring is expected during construction, if the increased water content is not large compared to the original, there were cases where a major problem did not occur even if the result that did not consider the increase in water content was used. In addition, it was confirmed that when the ratio of the top treatment length to the improved length is high, a small amount of design cement contents per unit length can be injected during construction. In the case of quality control, it was evaluated that D/4~2D/4 for single-axis and D/4 point for multi-axis were optimal for coring of grouting mixtures. As an item for quality control, it is judged that the standard that considers the TCR along with the unconfined compressive strength of grouting mixtures is more suitable for the domestic situation.