Reinforcement learning (RL) is successfully applied to various engineering fields. RL is generally used for structural control cases to develop the control algorithms. On the other hand, a machine learning (ML) is adopted in various research to make automated structural design model for reinforced concrete (RC) beam members. In this case, ML models are developed to produce results that are as similar to those of training data as possible. The ML model developed in this way is difficult to produce better results than the training data. However, in reinforcement learning, an agent learns to make decisions by interacting with an environment. Therefore, the RL agent can find better design solution than the training data. In the structural design process (environment), the action of RL agent represent design variables of RC beam. Because the number of design variables of RC beam section is many, multi-agent DQN (Deep Q-Network) was used in this study to effectively find the optimal design solution. Among various versions of DQN, Double Q-Learning (DDQN) that not only improves accuracy in estimating the action-values but also improves the policy learned was used in this study. American Concrete Institute (318) was selected as the design codes for optimal structural design of RC beam and it was used to train the RL model without any hand-labeled dataset. Six agents of DDQN provides actions for beam with, beam depth, bottom rebar size, number of bottom rebar, top rebar size, and shear stirrup size, respectively. Six agents of DDQN were trained for 5,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases that is not used for training. Based on this study, it can be seen that the multi-agent RL algorithm can provide successfully structural design results of doubly reinforced beam.

The 3T irregular shape structure is used for designing wind loads in high-rise buildings. Among them, the Tapered shape is a shape with a cross-section that changes throughout the entire floor. Recently, various advanced Tapered shapes have been applied, such as having a cross-section that varies only in part of the height or combining different shapes. In this study, an analysis model was selected by applying three types of Tapered part locations(Bottom, Middle, Top) and angles as design variables. Equivalent static seismic loads and historical earthquake records were applied to compare and analyze the seismic response of the Tapered models with regular-shaped models. As a result of the analysis, positioning the partial taper in the middle shows the lowest seismic response. Additionally, a larger taper angle decreased the story drift ratio, top-story displacement, shear wall shear force, and column bending moment, while increasing absolute acceleration and column axial force.

The rapid expansion of bridge and tunnel infrastructure has resulted in a growing incidence of wind-induced traffic accidents occurring at bridge approaches and tunnel portals. These accidents not only inflict direct damage on vehicles but also lead to substantial social and economic losses, stemming from roadway infrastructure repair and maintenance costs, as well as elevated logistics expenses due to traffic delays and congestion. In this study, a theoretical expression for the lateral displacement of vehicles as a function of wind speed was derived. Subsequently, lateral displacement and lateral wind force were analyzed and compared across vehicle types, considering both straight and curved roadway sections. An analysis of prevailing wind directions at each site revealed that, for passenger cars, the maximum lateral force and displacement on straight sections occurred at a wind incidence angle of 45°, whereas on curved sections with a pier curvature of 90°, the critical wind direction ranged from 0° to 120°. These results demonstrate that vehicle stability can be significantly compromised during high-speed travel under crosswind conditions. Based on departure trajectories of vehicles under varying wind speeds, a risk-assessment scale for wind-induced accidents was developed. In addition, design guidelines were proposed for the strategic placement of windbreak barriers to enhance driving safety under strong wind conditions.

Automated structural design methods for reinforced concrete (RC) beam members have been widely studied with various techniques to date. Recently, artificial intelligence has been actively applied to various engineering fields. In this study, machine learning (ML) is adopted to make automated structural design model for RC beam members. Among various machine learning methods, a supervised learning was selected. When a supervised learning is applied to development of ML-based prediction model, datasets for training and test are required. Therefore, the datasets for rectangular and t-shaped RC beams was constructed by commercial structural design software of MIDAS. Five supervised learning algorithms, such as Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), Artificial Neural Networks (ANN), eXtreme Gradient Boosting (XGBoost) were used to develop the automated structural design model. Design moment (Mu), design shear force (Vu), beam length, uniform load (wu) were used for inputs of structural design model. Width and height of the designed section, diameter of top and bottom bars, number of top and bottom bars, diameter of stirrup bar were selected for outputs of structural design model. Performance evaluation of the developed structural design models was conducted using metrics sush as root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R2). This study presented that random forest provides the best structural design results for both rectangular and t-shaped RC beams.

In this study, static and dynamic analyses were conducted on three atypical building models to evaluate the displacement response reduction performance based on the outrigger system installation location in a atypical building that incorporated both tapered and twisted shapes. Three 60-story models were developed with a fixed 3-degree taper and twist angles of 1, 2, and 3 degrees per story. Outrigger systems were installed at 10-story intervals and additionally between the 20th and 40th floor at 1-story intervals. The results indicated that, although there were variations depending on the seismic loads, the displacement response reduction performance was generally most effective when the outriggers were installed in the upper stories (41st to 60th floors) of the analytical models.

Performance-Based Seismic Design (PBSD) is an approach that evaluates how structures will perform under different levels of seismic activity. It focuses on ensuring that buildings not only withstand earthquakes but also meet specific performance objectives, such as minimizing damage or maintaining functionality after the event. Unlike traditional methods, PBSD allows for more tailored, cost-effective designs by considering varying degrees of acceptable damage based on the structure's importance and use. PBSD was introduced in Korea in 2016 to replace elastic design, which is inevitable to over-design to cope with all variables such as earthquakes and winds. When PBSD is applied to the structural design new building, One of the challenges of PBSD is the complexity involved in creating accurate inelastic analysis models. The process requires significant time and effort to analyze the results, as it involves detailed simulations of how structures will behave under seismic stress. Additionally, organizing and interpreting the analysis data to meet performance objectives can be labor-intensive and technically demanding. In order to solve this problem, a post-processor program was developed in this study. A post-processor was developed based on Excel program using Visual Basic for Applications(VBA). Because analysis outputs of Perform-3D, that is a commercial software for structural analysis and design, are very complicated, generation of tables and graphs for report is significant time and effort consuming task. When the developed post-processor is used to make the seismic design report, the required task time is significantly reduced.

The diagrid structural system has a braced frame that simultaneously resists lateral and vertical loads, and is being applied to many atypical high-rise buildings for aesthetic effects. In this study, a 60-story structure with twisted degrees of 0° to 180° was selected to determine seismic response control performance of twisted high-rise structures whether the diagrid system was applied and according to the reduction of braced frame material quantity. For this purpose, ‘Nor’ model without the diagrid system and the ‘DS’ model with the diagrid system, which was modeled by reducing braced frame member section to 700~400, were modeled. As a result, the 'DS' model showed an seismic response control effect in all Twisted models even when the quantity was reduced, and especially, the Twisted shape model was found to have an superior response control effect compared to the regular structure. In addition, the ‘600DS’ analysis model, which matched the ‘Nor’ model by 99.0% in quantity, showed an increase in seismic response control performance as the rotation angle increased.

This study is to deal with the cause analysis and improvement ideas for breakage to hydraulic pipes mounted on self-propelled howitzers. Hydraulic piping is one of the core components of a hydraulic system. This is because in the case of devices that use hydraulic pressure as a power source, hydraulic oil is supplied through hydraulic piping to operate. Compared to the main hydraulic assembly, its importance is low, so there are not many studies or failure analysis cases on it. However, contrary to this, cases of hydraulic pipe failure account for a significant proportion of the total number of failures, requiring in-depth technical review. In this study, we aim to analyze the causes of failures in hydraulic pipes of self-propelled guns operated by the military and propose improvement measures. It is expected that this study will aid as a reference for problem solving when similar failures occur in the future.

High-rise buildings are equipped with TMD (Tuned Mass Damper), a vibration control device that ensure the stability and usability of the building. In this study, the seismic response control performance was evaluated by selecting the design variables of the TMD based on the installation location of the twisted irregular building. To this end, we selected analysis models of 60, 80, and 100 floors with a twist angle of 1 degree per floor, and performed time history analysis by applying historical seismic loads and resonant harmonic loads. The total mass ratio of TMDs was set to 1.0%, and the distributed installation locations of TMDs were selected through mode analysis. The analysis results showed that the top-floor displacement responses of all analysis models increased, but the maximum story drift ratio decreased. In order to secure the seismic response control performance by distributed installation of TMDs in twisted irregular buildings, it is judged that the mass ratio distribution of TMDs will act as a key variable.

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.

This study identifies the possibility of alignment discrepancies during mortar firing when using inactive fuzes, which make it impossible to visually observe impact points. To address this issue, we studied a quality assurance method for Sight Alignment after firing. To establish a baseline, we analyzed the pre-firing Sight Alignment and the impact group status during firing for 00 mortars and 000 shells. Based on this analysis, we derived the alignment position information range after firing for 36 mortars, distinguishing between 68% and 95% confidence interval. Finally, considering data characteristics, inspection time requirements, and non-conforming data, we selected the Sight Alignment range after firing based on the 95% confidence interval. This study is expected to contribute to the development of quality assurance methods for munitions by serving as an example of quality assurance in the mass production stage of mortars.

This study is to deal with a failure phenomenon that occurred during a vibration test on an Inertial Navigation System mounted on a self-propelled howitzer. Vibration occurs naturally due to the operation characteristics of self-propelled howitzers, The study describes a case of failure that occurred during the durability verification process. It explains the function and configuration of the INS(Inertial Navigation System) and describe how the failure occurred through understanding the phenomenon. Based on the occurrence phenomenon, an in-depth cause analysis was conducted and fundamental improvement measures were presented to prevent recurrence. It is expected that this study will aid as a reference for problem solving when similar failures occur in the future.

현대 건설산업 분야에서 철근콘크리트는 반영구적인 재료로 인식되어 가장 많이 사용되고 있다. 하지만 콘크리트의 노후화 및 수분 용해 현상 등으로 생긴 균열을 통해 강재의 부식이 발생하게 된다. 이러한 부식은 철근콘크리트의 거동과 구조물의 내구성을 저하시키기 때문에 근본적인 원인인 강재를 대체할 필요가 있다. 최근 건설산업에서 복합재료는 높은 강도, 낮은 중량, 부식에 대한 우 려가 없어 주목받고 있는 재료이다. 복합재료는 섬유와 기지재료로 사용되는 수지에 따라 재료의 특성이 달라지게 되며 이중 탄소섬유 를 활용한 복합재료 CFRP은 복합재료 중 가장 뛰어난 성능을 보여준다. 따라서 본 연구에서는 뛰어난 성능을 보여주는 CFRP와 경제 성을 고려하여 탄소섬유와 유리섬유를 혼합한 CFRP Hybrid를 사용하여 강재의 대체품으로 사용가능성을 확인하고자 한다. 재료의 특 성을 비교하기 위하여 ASTM 규정에 따라 인장시험과 압축시험을 수행하고 반복하중에 대한 저항을 확인하기 위하여 인장반복시험과 압축반복시험을 수행한다. 이때 측정된 응력, 영구변형 등을 그래프로 도식화하고 강재와 비교분석을 진행하였다.

In this paper, the cause of mortar baseplate breakage was analyzed by diving into cross-section, material, process, and design aspects. As a result of observing the fracture surface and non-fracture suface using optical equipment, it was possible to confirm changes in the shape of disconnected line and metal surface at a specific area. In addition, a number of linear defects due to overlap were found. Flow analysis was performed using the Deform program to verify changes during the production process. According to the result, a drop test was performed on each of the lap detection baseplate, undetection baseplate, and removed product to verify the presumptive cause of the rupture of the poplite.

Advancements in technology for large aircraft have led to the development of new materials for aviation. Traditional alloy-based components in aircraft, once prevalent, are now being replaced by composite materials that offer superior performance in terms of strength and operational limits. Notably, propellers have evolved from wood to composite materials, finding application in contemporary small aircraft. In this context, there is a need for research on the composite propellers of the 3-blade "W Company," based on the widely used Rotax 914 engine in South Korea. This study aims to investigate the changes in noise and thrust corresponding to variations in propeller blade angles and engine RPM, with the goal of selecting the optimal propeller pitch angle. Particularly, the "W Company's" propellers are durable and cost-effective, widely adopted in domestic aircraft. The research seeks to propose an effective method to minimize noise while maintaining the necessary thrust, contributing to the smooth operation of aircraft and promoting coexistence with local communities.

PURPOSES : The aim of this study is to develop a road fog information system based on the geostationary meteorological satellite (GK2A) for road weather services on highways. METHODS : Three threshold values sensitive to fog intensity in the GK2A fog algorithm were optimized using multi-class receiver operating characteristic analysis to produce road fog information depending on day and night. The developed a GK2A road fog algorithm that can detect three levels of road fog based on the visibility distance criteria (1km, 500m, and 200m). Furthermore, the GK2A road fog product was not only substituted with visibility objective analysis data in unknown and cloud-covered areas of satellite data, but also integrated with visibility distance data obtained from visibility gauges and CCTV image analysis to improve the accuracy of road fog information. RESULTS : The developed road fog algorithm based on meteorological satellite data provides real-time road fog information categorized into three levels (attention, caution, and danger) based on the visibility distance, with a spatial resolution of 1km × 1km and temporal resolution of 5 minutes. The road fog algorithm successfully detected road fog in five out of seven fog-related traffic accidents reported by Korean media outlets from 2020 to 2022, resulting in a detection success rate of 71.4%. The Korea Meteorological Administration is currently in the process of installing additional visibility gauges on 26 highways until 2025, and the next high-resolution meteorological satellite (GK5) is planned to be launched in 2031. We look forward to significantly improving the accuracy of the road fog hazard information service in the near future. CONCLUSIONS : The road fog information test service was initiated on the middle inner highway on July 27, 2023, and this service is accessible to all T-map and Kakao-map users through car navigation systems free of charge. After 2025, all drivers on the 26 Korean highways will have access to real-time road fog information services through their navigation systems.

Machine learning is widely applied to various engineering fields. In structural engineering area, machine learning is generally used to predict structural responses of building structures. The aging deterioration of reinforced concrete structure affects its structural behavior. Therefore, the aging deterioration of R.C. structure should be consider to exactly predict seismic responses of the structure. In this study, the machine learning based seismic response prediction model was developed. To this end, four machine learning algorithms were employed and prediction performance of each algorithm was compared. A 3-story coupled shear wall structure was selected as an example structure for numerical simulation. Artificial ground motions were generated based on domestic site characteristics. Elastic modulus, damping ratio and density were changed to considering concrete degradation due to chloride penetration and carbonation, etc. Various intensity measures 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 and extreme gradient boosting algorithms present good prediction performance.

Since atypical high-rise buildings are vulnerable to gravity loads and seismic loads, various structural systems must be applied to ensure the stability of the structure. In this study, the authors selected a 60-story twisted-shaped structure among atypical high-rise structures as an analytical model to investigate its structural behavior concerning the outrigger system. The structural analyses were performed varying the number of installed layers and the arrangement of the outrigger system, as well as the placement of the mega column, as design variables. The analysis revealed that the most effective position for the outrigger was 0.455H from the top layer, consistent with previous studies. Additionally, connecting outriggers and mega columns significantly reduced the displacement response of the model. From an economic standpoint, it is deemed efficient to connect and install outriggers and mega columns at the structure's ends.