• Journal of Korean Association for Spatial Structures
• /
• v.23 no.3
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.33-36
• /
• 2021

In this paper, we propose a new method for improving compression efficiency of immersive video using reinforcement learning. Immersive video means a video that a user can directly experience, such as 3DOF+ videos and Point Cloud videos. It has a vast amount of information due to their characteristics. Therefore, lots of compression methods for immersive video are being studied, and generally, a method, which projects an 3D image into 2D image, is used. However, in this process, a region where information does not exist is created, and it can decrease the compression efficiency. To solve this problem, we propose the reinforcement learning-based filling method with considering the characteristics of images. Experimental results show that the performance is better than the conventional padding method.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.160-161
• /
• 2023

Currently, the ship's passage planning relies on the navigator officer's knowledge and empirical methods. However, as ship autonomous navigation technology has recently developed, automation technology for passage planning has been studied in various ways. In this study, we intend to generate an optimal route for a ship based on Q-learning, one of the reinforcement learning techniques. Reinforcement learning is applied in a way that trains experiences for various situations and makes optimal decisions based on them.

• Journal of the Korea Safety Management & Science
• /
• v.25 no.4
• /
• pp.131-140
• /
• 2023

This paper proposes an algorithm for the Unrelated Parallel Machine Scheduling Problem(UPMSP) without setup times, aiming to minimize total tardiness. As an NP-hard problem, the UPMSP is hard to get an optimal solution. Consequently, practical scenarios are solved by relying on operator's experiences or simple heuristic approaches. The proposed algorithm has adapted two methods: a policy network method, based on Transformer to compute the correlation between individual jobs and machines, and another method to train the network with a reinforcement learning algorithm based on the REINFORCE with Baseline algorithm. The proposed algorithm was evaluated on randomly generated problems and the results were compared with those obtained using CPLEX, as well as three scheduling algorithms. This paper confirms that the proposed algorithm outperforms the comparison algorithms, as evidenced by the test results.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.107-113
• /
• 2024

Scheduling of semiconductor test facilities has been crucial since effective scheduling contributes to the profits of semiconductor enterprises and enhances the quality of semiconductor products. This study aims to solve the scheduling problems for the wafer burn-in test facilities of the semiconductor back-end process by utilizing simulation and deep reinforcement learning-based methods. To solve the scheduling problem considered in this study. we propose novel state, action, and reward designs based on the Markov decision process. Furthermore, a neural network is trained by employing the recent RL-based method, named proximal policy optimization. Experimental results showed that the proposed method outperformed traditional heuristic-based scheduling techniques, achieving a higher due date compliance rate of jobs in terms of total job completion time.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.214-224
• /
• 2024

Sonobuoys are disposable devices that utilize sound waves for information gathering, detecting engine noises, and capturing various acoustic characteristics. They play a crucial role in accurately detecting underwater targets, making them effective detection systems in anti-submarine warfare. Existing sonobuoy deployment methods in multistatic systems often rely on fixed patterns or heuristic-based rules, lacking efficiency in terms of the number of sonobuoys deployed and operational time due to the unpredictable mobility of the underwater targets. Thus, this paper proposes an optimal sonobuoy placement strategy for Unmanned Aerial Vehicles (UAVs) to overcome the limitations of conventional sonobuoy deployment methods. The proposed approach utilizes reinforcement learning in a simulation-based experimental environment that considers the movements of the underwater targets. The Unity ML-Agents framework is employed, and the Proximal Policy Optimization (PPO) algorithm is utilized for UAV learning in a virtual operational environment with real-time interactions. The reward function is designed to consider the number of sonobuoys deployed and the cost associated with sound sources and receivers, enabling effective learning. The proposed reinforcement learning-based deployment strategy compared to the conventional sonobuoy deployment methods in the same experimental environment demonstrates superior performance in terms of detection success rate, deployed sonobuoy count, and operational time.

• Journal of the Korean Geotechnical Society
• /
• v.21 no.1
• /
• pp.29-41
• /
• 2005

The small harbors and fishing ports in Korea have less economic efficiency if the previous construction method of breakwater would be utilized due to bad ground conditions in spite of low design waves. Therefore, it is necessary to develop a new type breakwater economically applicable to the cases with low design wave. In this study, a soldier pile type breakwater, which is found to be economic and can be easily constructed on the ground without any need of treatment of the ground, was newly introduced. The effects of embedded depth, reinforcement methods as well as pile types including saw type and flat type on the lateral behavior of the proposed breakwaters installed in loose sandy soils were investigated from model test. The test results revealed that the lateral resistance increases by increasing the embedded depth and by adopting the reinforcement techniques such as raker and anchor. Furthermore, it was also verified that the saw type breakwater shows better geotechnical performance than the flat type breakwater.

• Tunnel and Underground Space
• /
• v.17 no.4
• /
• pp.255-265
• /
• 2007

As the mechanism and effect range of subsidence are altered according to the various conditions (the ground condition, the earth pressure, the geometric condition of underground cavity and the structure load), the analysis and prediction of subsidence in abandoned mining area are very difficult. Also, as the geological characteristics and the mining methods are differed in each mines, the application of the pre-existing reinforcements without improvement has a lot of difficulties and limits. In this study, the various underground investigation such as long-depth core drilling, seismic tomography and BIPS (borehole image processing system) were performed, the distribution of underground cavity and coal seam and rock relaxation condition were analyzed. And we predicted the type of subsidence and estimated the subsidence by theories of mining subsidence. With these results, we analyzed the mechanism of subsidence occurrence in the research object area. Finally, we improved existing methods which were applied to the abandoned mining area and also we established the rational reinforcement for the ground and structure foundation against each subsidence cause.

• Journal of the Korean Society for Railway
• /
• v.13 no.3
• /
• pp.298-303
• /
• 2010

The transition zone of the railway is the section which roadbed stiffness is suddenly varied like as tunnel-earthwork, bridge-earthwork and concrete track-ballasted track. There are about 450 tunnel-bridge transition sections on Kyungbu high-speed railway line. It is very important to pay careful attention to construction of these transition zones, in order to secure the train running safety. So, we developed a finite element model of the moving wheel loading to simulate the behavior of bridge-earthwork transitions in this paper. The most distinctive characteristics of the model proposed is to simulate the real wheel behavior on rail. And the main analysis object is to evaluate and compare the deformation characteristics of the transition zone according to the reinforcement methods and length of transition zone which is adopted to high-speed railway. Based on the analysis results, we assessed the effect of the reinforcements on the transition zone of high-speed railway.

• Journal of the Korean Society for Railway
• /
• v.12 no.2
• /
• pp.276-284
• /
• 2009

Recently pile-supported embankments have emerged as an optimum method when the rapid construction and strict deformation of structures are required on soft soils. Especially geosynthetic-reinforced and pile-supported (GRPS) embankments are used worldwide as they can provide economic and effective solutions. However the load transfer mechanism in GRPS embankments is very complex, and not yet fully understood. Particularly the purpose and effect of geosynthetic inclusion are ambiguous and considered as an auxiliary measure assisting the arching effect of piles. Numerical parametric study using 3D finite element method has been conducted to investigate the effect of geosynthetic reinforcement on the load transfer mechanism of GRPS embankments. Numerical results suggested that as more stiffer geosynthetic is included, arching effect decreases considerably and the load concentration to the piles mostly caused by tension effect of geosynthetic. This finding is contradictory to the common understanding that geosynthetic inclusion only enhance the efficiency of load transfer. Consequently the design parameters determined from the numerical analyses are compared with those of three existing design methods. The problems of the existing methods are discussed.