• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.3
• /
• pp.59-64
• /
• 2018

In general, tracked combat vehicles require excellent output performance of a power unit system to drive on special terrains and in extreme environmental conditions. However, high temperature and pressure are readily applied to the coolant hose in the power unit of the vehicles during high-speed driving under extreme road and weather conditions. These driving conditions can cause the separation phenomenon of the coolant hose in the power unit and consequentially engine overheating during driving. Therefore, a newly designed decompression device for the coolant hose has been proposed and manufactured to solve these problems in the present study. To validate of the newly proposed decompression device, the input and output pressures were measured under the before- and after-improvement conditions using experimental methods for different engine RPMs. In addition, the pre-heater temperature was measured under both conditions. From the experimental results, we expect that the current investigation can help to improve the driving performance of tracked combat vehicles.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.4
• /
• pp.1-9
• /
• 2012

The NCF control algorithm for an active suspension system was proposed and investigated. The NCF algorithm using spring dynamic variation force and suspension relative velocity was applied to the 1/4 vehicle model and numerical analysis was performed. Vehicle's performances such as vehicle displacement, vehicle acceleration, suspension deflection, tire deflection and absorbed power were calculated and compared with those of the passive, semi-active and LQR active suspension system that use full state feedback. Numerical results show that the proposed NCF active suspension system has superior performance compared with the passive and semi-active suspension system and has very similar performance compared with the LQR active suspension system. So the proposed NCF algorithm is considered as a highly practical algorithm because it requires only one displacement sensor in a 1/4 vehicle model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.805-825
• /
• 2017

Correlation Filter-based Trackers (CFTs) gained popularity recently for their effectiveness and efficiency. To deal with the size changes of the target which may degenerate the tracking performance, scale estimation has been introduced in existing CFTs. However, the variations of the aspect ratio were usually neglected, which also influence the size of the target. In this paper, Size Aware Correlation Filter Trackers (SACFTs) are proposed to deal with this problem. The SACFTs not only determine the translation and scale variations, but also take the aspect ratio changes into consideration, thus a better estimation of the size of the target can be realized, which improves the overall tracking performance. And competing results can be achieved compared with state-of-the-art methods according to the experiments conducted on two large scale datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.12
• /
• pp.5765-5781
• /
• 2018

Extreme learning machine (ELM) is emerging as a powerful machine learning method in a variety of application scenarios due to its promising advantages of high accuracy, fast learning speed and easy of implementation. However, how to select the optimal hidden layer of ELM is still an open question in the ELM community. Basically, the number of hidden layer nodes is a sensitive hyperparameter that significantly affects the performance of ELM. To address this challenging problem, we propose to adopt multiple kernel learning (MKL) to design a multi-hidden-layer-kernel ELM (MHLK-ELM). Specifically, we first integrate kernel functions with random feature mapping of ELM to design a hidden-layer-kernel ELM (HLK-ELM), which serves as the base of MHLK-ELM. Then, we utilize the MKL method to propose two versions of MHLK-ELMs, called sparse and non-sparse MHLK-ELMs. Both two types of MHLK-ELMs can effectively find out the optimal linear combination of multiple HLK-ELMs for different classification and regression problems. Experimental results on seven data sets, among which three data sets are relevant to classification and four ones are relevant to regression, demonstrate that the proposed MHLK-ELM achieves superior performance compared with conventional ELM and basic HLK-ELM.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.3
• /
• pp.281-292
• /
• 2021

With the development of deep learning technology, researchers and technicians keep attempting to apply deep learning in various industrial and academic fields, including the defense. Most of these attempts assume that the data are balanced. In reality, since lots of the data are imbalanced, the classifier is not properly built and the model's performance can be low. Therefore, this study proposes cost-sensitive learning as a solution to the imbalance data problem of image classification in the defense field. In the proposed model, cost-sensitive learning is a method of giving a high weight on the cost function of a minority class. The results of cost-sensitive based model shows the test F1-score is higher when cost-sensitive learning is applied than general learning's through 160 experiments using submarine/non-submarine dataset and warship/non-warship dataset. Furthermore, statistical tests are conducted and the results are shown significantly.

• Journal of Korean Society for Quality Management
• /
• v.46 no.3
• /
• pp.411-424
• /
• 2018

Purpose: The purpose of this study is to improve submarine TACM launcher system safety device performance. Methods: In this study, EPLD(Electrically Programmable Logic Device) control and time sharing method to the safety device actuator motor and discrete signal processor in launch control panel were used to resolve unusual performance of safety system. Results: The result of this study are as follows; First, sporadic stopping of safety device actuator motor due to insufficient In-Rush current was resolved. Second, repeat of safety device condition as lock & release due to chattering for motor activating was resolved. Third, simultaneous release function for safety device actuator was available. Conclusion: The unusual performance of function for submarine TACM launcher system was overcame by applying EPLD control and time sharing method. The suggestions were proved by performance test in the pressure chamber. The results of this study enhanced survivability of ${\bigcirc}{\bigcirc}{\bigcirc}$ class submarine from enemy torpedo.

• 한국벤처창업학회:학술대회논문집
• /
• 2009.08a
• /
• pp.5-24
• /
• 2009

This study is the result of meta evaluation for the self evaluation of defense R&D programs in Korea. The overall meta evaluation result of defense R&D programs gained 74.3 points out of 100, so it was evaluated as 'Good'. But it demonstrated that further improvement for overall system of defense R&D programs evaluation is required. And especially, it demonstrated that more alternatives are necessary in order to improve the utilizations and the feedbacks of evaluation results. The evaluation context component gained 80.2 points out of 100, so it was evaluated as 'Very Good'. The evaluation input component gained 73.1 points out of 100, so it was evaluated as 'Good'. The evaluation process component gained 74.8 points out of 100, so it was evaluated as 'Good'. From the analysis, it is attempted to identify possible problems and to find out the ways of improvements related to the self evaluation system of defense R&D Programs.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.2_2
• /
• pp.225-232
• /
• 2020

In this paper, we introduce the results of investigating and overhauling bearing drawings in the defense field, and propose an effective bearing drawing management system. We identify the features and performance items that must be regulated in the bearing drawing. After reviewing the validity of the bearing drawings, we classify the incorrect drawings by factor. To achieve greater effect, standardized formats are needed to incorporate into the drawing in the early stage. We propose the introduction of a bearing drawing management system so that the developing bearing technology can be applied quickly to the defense sector. As other elementary parts of the machine have similar problems, we think this study will help develop improvement plans.

• Current Optics and Photonics
• /
• v.3 no.5
• /
• pp.429-437
• /
• 2019

Temperature adaptability is an important metric for evaluating the performance of an optical system. The temperature characteristics of the optical system are closely related to the material and shape of its lens. In this paper, we establish a mathematical model relating the temperature characteristics to the shape and material of the lens. Then a novel assembly structure that can solve the lens constraint and positioning problem is proposed. From those basics, the correctness of the theoretical model and the effectiveness of the assembly structure are verified through simulated analysis of the imaging quality of the optical system, whose operating temperature range is $-60{\sim}100^{\circ}C$.

• Archives of Metallurgy and Materials
• /
• v.65 no.3
• /
• pp.1011-1014
• /
• 2020

Ice formed on radome surfaces causes communication disruption due to radio-frequency interference (RFI), which reveals the importance of de-icing systems for radomes. As a radome de-icing application, in this work, carbon nanotube (CNT) thin films were fabricated using a spray-coating method, and influence of process parameters on RF transmittance and electrothermal properties was investigated. With the increase of spraying time, sheet resistance of the fabricated film decreases, which results in a decrease of the RF transmittance and improvement of the heating performance. Also, the de-icing capability of the fabricated CNT film was evaluated at -20℃, and efficient removal of ice under cold conditions was demonstrated.