• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.175-181
• /
• 2021

This paper analyzes the artificial intelligence-based approach for short-term energy consumption prediction. In this paper, we employ the reinforcement learning algorithms to improve the limitation of the supervised learning algorithms which usually utilize to the short-term energy consumption prediction technologies. The supervised learning algorithm-based approaches have high complexity because the approaches require contextual information as well as energy consumption data for sufficient performance. We propose a deep reinforcement learning algorithm based on multi-agent to predict energy consumption only with energy consumption data for improving the complexity of data and learning models. The proposed scheme is simulated using public energy consumption data and confirmed the performance. The proposed scheme can predict a similar value to the actual value except for the outlier data.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.112-118
• /
• 2023

As technology advances, the need for enhanced preparedness against cyber-attacks becomes an increasingly critical problem. Therefore, it is imperative to consider various circumstances and to prepare for cyber-attack strategic technology. This paper proposes a method to solve network security problems by applying reinforcement learning to cyber-security. In general, traditional static cyber-security methods have difficulty effectively responding to modern dynamic attack patterns. To address this, we implement cyber-attack scenarios such as 'Tiny Alpha' and 'Small Alpha' and evaluate the performance of various reinforcement learning methods using Network Attack Simulator, which is a cyber-attack simulation environment based on the gymnasium (formerly Open AI gym) interface. In addition, we experimented with different RL algorithms such as value-based methods (Q-Learning, Deep-Q-Network, and Double Deep-Q-Network) and policy-based methods (Actor-Critic). As a result, we observed that value-based methods with discrete action spaces consistently outperformed policy-based methods with continuous action spaces, demonstrating a performance difference ranging from a minimum of 20.9% to a maximum of 53.2%. This result shows that the scheme not only suggests opportunities for enhancing cybersecurity strategies, but also indicates potential applications in cyber-security education and system validation across a large number of domains such as military, government, and corporate sectors.

• Journal of Korea Port Economic Association
• /
• v.20 no.1
• /
• pp.153-172
• /
• 2004

With swelling of Chinese Economic scale, the competitive environment is swinging over the north-east Asia countries, Korea, Japan, China, and Taiwan. As the result of this circumstance, each countries in this area has been reformed their industries. According to the expanding in ocean logistic. The trends of competition on Hub port is looking forward much more severe year after year to preoccupy in logistics competitive within this Area. On the other hand, considering competitive environment & swelling of Chinese Economic scale, the structural reforms are imperative in korea. Korea have to convert the traditional sects into new high added value sects. In these trends, provincial government also should look for the plan for reinforcement of Regional competitiveness. The focus of this study is to look for the reinforcement methods on regional competitiveness of Gyeongnam Provincial Government. First, competitive industries in Gyeongnam, and second, Masan Free Trade Zone will be surveyed from data. Finally, the effects of New Hub port developing in Pusan-Jinhae will be discussed.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2002.05a
• /
• pp.361-366
• /
• 2002

The deterioration of concrete structure due to corrosion of the reinforcement has created big financial losses on the overall industries. The volume expansion of the corrosion products causes internal pressure to concrete wall around reinforcing bar. If the maximum principal stress induced by internal pressure exceeds the tensile strength of the concrete at any point of time, a crack forms at any point of material. Therefore, in terms of life assessment of concrete structure, it is very important to predict the amount of corrosion products which induces initial concrete cracking. With this objective, this paper proposes the critical amount of corrosion products at interface between reinforcement and concrete using finite element analysis. If an actual survey of corrosion rates could be made, the model might supply information for condition assessment of existing concrete structure. As the mechanical properties of corrosion product and instantaneous geometry of corroded steel are considered in the analysis, the value obtained will be more realistic.

• Earthquakes and Structures
• /
• v.9 no.4
• /
• pp.851-873
• /
• 2015

A methodology for estimation of statistical properties (viz. mean and standard deviation) of the expected seismic damage to reinforced concrete framed structures subject to corrosion of reinforcement, over a specified reference time (typically the service life of the structure) is proposed in this paper. The damage to the structure under the earthquake loading is characterised by the damage index, determined using the modified Park and Ang damage model. The reduction in area, yield strength and strain at ultimate of steel reinforcement, and the reduction in compressive strength of cover concrete due to corrosion are taken into account in the estimation of damage. The proposed methodology is illustrated through an example problem. From the results obtained, it is noted that there is an increase of about 70% in the mean value of expected seismic damage to the reinforced concrete frame considered over a reference time of 30 years when effect of corrosion is taken into consideration. This indicates that there is a need to consider the effect of corrosion of reinforcement on the estimation of expected seismic damage.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1999.04a
• /
• pp.653-658
• /
• 1999

Bond between reinforcing bars and the surrounding concrete is supposed to safely transfer load in the design process of reinforced concrete structures. Bond failure of reinforcing bars generally take place by splitting of concrete cover as bond force between concrete and reinforcing bars exceeds the resistance by the confinement of the concrete cover and transverse reinforcement. Confinement, concrete cover and transverse reinforcement, on bond are the key factor of current provision to determine development length of reinforcing bars to concrete. In this study, previous available data are analyzed with respect to the current provisions for development and splice of reinforcement. From this study, the new provision for the design are proposed, which will be efficient and effective with some specific limit value.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2004.04a
• /
• pp.219-222
• /
• 2004

The effects of short fiber and particle hybrid reinforcement on fatigue crack propagation behaviors in aluminum matrix composites have been investigated. Single and hybrid reinforced 6061 aluminum containing same 20 $Al_2O_3\;volume\%$ with four different constituent ratios of short fibers and particles were prepared by squeeze casting method and tested to check the near-threshold and stable crack growth behavior. The fatigue threshold of the composites increased with portion of particle contents and showed the improved crack resistance especially in low stress intensity range. Addition of particle instead of short fiber also increased fracture toughness due to increase of inter-reinforcement distance. These increase in both fatigue threshold and fracture toughness eventually affected the fatigue crack growth behavior such that the crack growth curve shift low to high stress intensity factor value. Overall experimental results were shown that particle reinforcement was enhanced the fatigue crack resistance over the whole stress intensity factor range.

• Geomechanics and Engineering
• /
• v.35 no.5
• /
• pp.555-570
• /
• 2023

In the current study, a series of experimental and analytical evaluations were performed to introduce the horizontal pseudo static coefficient (kh) as a function of the wall configuration and the reinforcement type for analyzing reinforced soil walls. For this purpose, eight shaking table tests were performed on reduced-scale models of integrated and two-tiered walls reinforced by metal strip and geogrid to determine the distribution of dynamic lateral pressure in the walls. Then, the physical models were analyzed using Mononobe-Okabe method to estimate the value of kh required to establish the dynamic lateral pressures similar to those observed in shaking table tests. Based on the results, the horizontal pseudo static coefficient and the position of resultant lateral force (R) were introduced as a function of the horizontal peak ground acceleration (HPGA), the wall configuration, the reinforcement type as well as maximum wall displacement.

• KCI Concrete Journal
• /
• v.11 no.3
• /
• pp.5-17
• /
• 1999

In recent years. the concept of the modified compression field theory (MCFT) was develped and applied to the analysis of reinforced concrete beams subjected to shear, moment, and axial load. Although too complex for regular use in the shear design or beams. the procedure has value in its ability to provide a rational method of anlysis and design for reinforced concrete members. The objective of this paper is to review the MCFT and apply it for the prediction of the response and shear strength of reinforced concrete beams A Parametric analysis was Performed on a reinforced T-section concrete beam to evaluate and compare the effects of concrete strength. longitudinal reinforcement ratio shear reinforcement ratio, and shear span to depth ratio in two different approaches the MCFT and the ACI code. The analytical study showed that the concrete contribution to shear strength by the MCFT was higher than the one by the ACI code in beams without stirrups, while it was lower with stirrups. On the other hand. shear reinforcement contribution predicted by the MCFT was much higher than the one by the ACI code. This is because the inclination angle of shear crack is much smaller than 45$^{\circ}$assumed in the ACI code.

• Structural Engineering and Mechanics
• /
• v.78 no.5
• /
• pp.623-635
• /
• 2021

Previous studies have suggested the maximum experimental story shear force of beam-column joint frame does not reach its theoretical value due to beam-column joint failure when the column-to-beam moment capacity ratio was close to 1.0. It was also pointed out that under a certain amount of axial force, an axial collapse and a sudden decrease of lateral load-carrying capacity may occur at the joint. Although increasing joint transverse reinforcement could improve the lateral load-carrying capacity and axial load-carrying capacity of beam-column joint frame, the conditions considering varying axial force were still not well investigated. For this purpose, 7 full-scale specimens with no-axial force and 14 half-scale specimens with varying axial force are designed and subjected to static loading tests. Comparing the experimental results of the two types of specimens, it has indicated that introducing the varying axial force leads to a reduction of the required joint transverse reinforcement ratio which can avoid the beam-column joint failure. For specimens with varying axial force, to prevent beam-column joint failure and axial collapse, the lower limit of joint transverse reinforcement ratio is acquired when given a column-to-beam moment capacity ratio.