• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.251-254
• /
• 2022

본 논문은 XGBoost 알고리즘 기반의 침입탐지모델의 성능을 향상하기 위한 스케일링(scaling) 및 특성선택(feature selection) 기법을 제안한다. 머신러닝 모델 개발 중 전처리 단계에서 스케일링 및 특성선택을 수행하면 데이터세트의 조건수가 감소하여 모델의 성능을 향상할 수 있다. 각 과정별로 다양한 기법이 있지만 기존의 연구에서는 이러한 기법들을 적용한 결과를 비교·분석하지 않고 특정 기법을 적용한 결과만을 나열하였고 스케일링 및 특성선택에 대해 최적의 조합은 제시하지 못하였다. 따라서 본 논문에서는 다양한 전처리 기법들의 적용결과를 비교하고 최적의 조합을 제안한다. 또한 기존의 연구들이 특정 데이터세트에만 적용 가능한 전처리 기법을 제안하는데 비해 본 논문은 다양한 데이터세트에 대해 공통적으로 적용 가능한 전처리 기법을 제안함으로써 제안 기법의 범용성과 실세계 적용 가능성을 증명한다.

• Journal of Korean Society for Quality Management
• /
• v.44 no.3
• /
• pp.565-574
• /
• 2016

Purpose: In this study, A reliability assurance model (or reliability program) is proposed to evaluate the reliability of an armed vehicle. The reliability assurance is performed through the reliability-centered activities in the K-000(armed vehicle) of D-Company Methods: By reflecting the current situations of korea defense industry, a reliability assurance model is built up based on the benchmarking results of world leading companies' best practices in same fields. So The reliability growth model is applied the Crow-AMSAA model Results: This research analysis the K-000(armed vehicle) of D-Company using the DT and OT failure data. and application case study by growth model of armed vehicles Conclusion: This research is result of application case study by growth model of armed vehicles.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.2
• /
• pp.218-226
• /
• 2016

In the original design of K2 tank the Vertical Sensor Unit(VSU) was mounted to measure the attitude of the main gun to enhance the hit probability. In this research, as a part of efforts to reduce the cost of K2, it was theoretically simulated and evaluated to use the data from Inertial Navigation System(INS) for the calculation of the gun attitude instead of the direct measurement using VSU. It was found that the negative effect of INS approach is negligible and the elimination of VSU is technically possible and beneficial to the system.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.26 no.5
• /
• pp.343-352
• /
• 2006

In the present paper, the nondestructive test method was suggest to establish the bonding status of a motor case assembly composed of a steel motor case, adiabatic rubber layer and an ablative composite tube with strain data, AE(acoustic emission) signals and UT(ultrasonic test) data. And, finite element analysis was conducted to verify quantitatively the bonding status of motor case assembly under inner pressure loading. The bonding status could be judged whether the bonding status is perfect or contact condition by the data correlation study with AE signals and strain data measured from air pressure test. And, to classify the bonding status of motor case and rubber layer among bonding layers, UT method was also applied. From this study, the bonding status could be classified and detected into fourth types for all bonding layers as follows: (1) initial un-bonding, (2) perfect do-bonding during an air pressure test, (3) partially de-bonding during an air pressure test, and (4) perfect bonding.

• Wind and Structures
• /
• v.32 no.2
• /
• pp.115-126
• /
• 2021

The snow cornice mass on the formation zone had triggered avalanches which led to the loss of human life and property. Snow cornice is formed due to flow separation on the leeward side. Effect of lee slope is more prominent in the formation of snow cornices as compared to the windward slope. The analysis of wind flow pattern has been carried out to evaluate the performance of a jet roof. Computational Fluid Dynamics (CFD) analysis of wind flow over a 2D hill model was carried out using RNG based k-∈ turbulence models available in ANSYS Fluent. Effect of varying leeward hill slope (1:2 to 1:6) on flow separation for the given windward slope was observed and a critical slope of 1:4 was found at which the separation zone ceased to exist. The modification of wind flow over a hill due to the installation of jet roof was simulated. It was observed that jet roof had significantly modified the wind flow pattern around hill ridgeline and ultimately snow cornice formation had mitigated. The results of the wind flow pattern were validated with the wind data collected at the experimental site, Banihal Top (Jammu and Kashmir, India). The wind flow simulation over the hill and mitigation of cornice formation by the jet roof has been explained in the present paper.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.23 no.5
• /
• pp.488-496
• /
• 2003

To establish nondestructive test method for rocket motor assembly with rubber and aerospace composite materials, practicable quality control acoustic emission test method is presented. Structural analysis for motor assembly is performed by ABAQUS code and analysis output result is confirmed by strain gage and AE data. Various specimens were tested and analyzed using strain gage and acoustic emission data. The hit rate of acoustic emission was closely related with case/rubber debonding. This report also describes practicable acoustic emission nondestructive method for evaluating motor case assembly quality assurance in the industrial field.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.4
• /
• pp.76-82
• /
• 2017

The cylinder liner of a diesel engine is commonly made of gray cast iron. However, this cylinder liner can be damaged by the cavitation phenomenon in wet conditions. This cavitation has remained an unsolved problem until now. In this study, the cause of cavitation corrosion due to antifreeze solution was examined using a scanning electron microscope (SEM) and a 3D microscope. The necessary data to prevent the damage caused by cavitation erosion and the corrosion of gray cast iron cylinder liner was obtained. Analysis determined that the gray iron structure consists of an ${\alpha}-matrix$, flake graphite, and steadite. Cavitation erosion was initiated in the coarse flake graphite and propagated into the steadite with pitting. Under repetitive reaction conditions, the ${\alpha}-matrix$ was partially separated from the gray cast iron. This study is expected to be used as the basic data for the prevention of gray cast iron cavitation erosion and corrosion by controlling the graphite and steadite phases.

• Annual Conference of KIPS
• /
• 2005.11a
• /
• pp.175-178
• /
• 2005

국방 M&S에서 사용되는 지형데이터는 각 시뮬레이션의 개발 환경과 개발 요구사항에 따라 서로 다른 형태로 분산저장 되어 각 모델을 통합 하거나, 새로운 모델의 개발 시 많은 시간과 예산을 필요로 하게 된다. 이에 따라 국방부에서는 국방M&S분야의 각종 자료를 표준화 하려는 사업이 진행중이며, 특히 지형 데이터 분야는 모든 M&S모델이 공통적으로 필요로 하는 데이터로서 표준화의 필요성이 매우 높은 분야이다. 본 연구에서는 이러한 지형 데이터를 표준형식으로 저장하고, 네트워크를 통하여 공유할 수 있는 시스템의 구축을 위하여, 환경자료 표현의 국제표준으로 제시된 SEDRIS 기술을 적용 할 것을 제안하고자 한다. SEDRIS는 DRM, EDCS, SRM의 모델을 통하여 합성환경의 다양한 요소를 표현할 수 있으며, API와 STF를 통하여 다른 체계와 자료를 교환 할수 있도록 한 국제 표준화 활동이며, 제정되고 있는 국제표준규격의 이름이다. 또한 SEDRIS는 다양한 환경요소를 표현할 수 있으며 데이터 변환이 빠르고 손실이 적기 때문에 국방 M&S의 지형 data구축 시 발생하는 각 군의 다양한 요구사항을 유연하게 수용할 수 있는 장점이 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.10
• /
• pp.82-88
• /
• 2018

The decoy defensive weapon system is a one-shot system. Reliability is maintained through periodic inspection and high reliability is required to confirm whether or not the functioning is normal after launch. The maintenance cycle of a decoy was set up without target reliability and reliability prediction during the development period. However, the number of operations in the military has been increasing, necessitating the optimization of the maintenance cycle. Reliability is analyzed using the maintenance data of a decoy operated for several decades and the optimal maintenance cycle is suggested. In chapter 2, data collection and classification methods are presented and analysis methodology is briefly introduced. In chapter 3, the data distribution analysis and fitness verification confirmed that applying the Weibull distribution is the most suitable for the maintenance data of the decoy. In chapter 4, we present the analysis result of percentile, survival probability and MTBF and the optimal maintenance cycle was derived from the reliability analysis. Finally, we suggest the application methods for this paper in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.26-35
• /
• 2019

By operating servers, storage, and networking devices, Data centers consume a lot of power such as cooling facilities, air conditioning facilities, and emergency power facilities. In the United States, The power consumed by data centers accounted for 1.8% of total power consumption in 2004. The data center industry has evolved to a large scale, and the number of large hyper scale data centers is expected to grow in the future. However, as a result of examining the server share of the data center, There is a problem where the server is not used effectively such that the average occupancy rate is only about 15% to 20%. To solve this problem, we propose a Virtual Machine Reallocation research using virtual machine migration function. In this paper, we use meta-heuristic for effective virtual machine reallocation. The virtual machine reallocation problem with the goal of maximizing the idle server was designed and solved through experiments. This study aims to reducing the idle rate of data center servers and reducing power consumption simultaneously by solving problems.