This study investigates improvement of torsional strength of special wrench for K-series self-propelled howitzer power-pack maintenance. In order to maintain the power-pack, special wrench is one of the essential tools for assembling/disassemblimg the engine and transmission. However, failures(plastic deformation, fracture phenomenon and etc.) have been frequently reported even though special wrench was used within recommended standard torque range. Therefore, in this study, finite element analysis using ABAQUS was performed and modification of design parameters have been proposed. Prototypes based on the proposed parameters were manufactured and torsional experiment(torque about 130 % of recommend maximum torque) validated the newly proposed design parameters. Special wrench based on this study is applied to mass production and currently used for the maintenance.

An optical mirror assembly is an opto-mechanically coupled system as the optical and mechanical behaviors interact. In the assembly, a flexure mount attached to an optical mirror should be flexible in the radial direction, but rigid for the remaining degrees of freedom for supporting the mirror rigidly and suppressing the wavefront error of the optical mirror. This work presents an optimal design of the flexure mount using topology optimization with thermal stress constraint. By simplifying the optical mirror assembly into finite shell elements, topology optimization model was built for efficient design and good machinability. The stress at the boundary between the optical mirror and the mount together with the first natural frequency were applied as constraints for the optimization problem, while the objective function was set to minimize the strain energy. As a result, we obtained the optimal design of the flexure mount yielding the improved wavefront error, proper rigidity, and machinability.

The analysis of foreign aircraft appearing suddenly in air defense identification zones requires a lot of cost and time. This study aims to develop a pre-trained model that can identify neighboring military aircraft based on aircraft photographs available on the web and present a model that can determine which aircraft corresponds to based on aerial photographs taken by allies. The advantages of this model are to reduce the cost and time required for model classification by proposing a pre-trained model and to improve the performance of the classifier by data augmentation of edge-detected images, cropping, flipping and so on.

In this study, the high-temperature dielectric constant of Si₃N₄ ceramics, a representative non-oxide-based radome material, was evaluated and the cause of the dielectric constant change was analyzed in relation to the oxidation behavior. The dielectric constant of Si₃N₄ ceramics was 7.79 at room temperature, and it linearly increased as the temperature increased, showing 8.42 at 1,000 ℃. As results of analyzing the microstructure and phase for the Si₃N₄ ceramics before and after heat-treatment, it was confirmed that oxidation did not occur at all or occurred only on the surface at a very insignificant level below 1,000 ℃. Based on this, it is concluded that the increase in the dielectric constant according to the temperature increase of Si₃N₄ ceramics is irrelevant to the oxidation behavior and is only due to the activation of charge polarization.

In this paper, we propose a formation control algorithm for multi-USVs according to COLREGs. First, we applied the Dynamic Window Approach algorithm that can reflect the kinematic characteristics for the path movement of USVs. Then, we propose a virtual structure-based virtual leader-follower method that applies the advantages of leader-follower and virtual structure methods among conventional formation control algorithms for stability. Next, we proposed a collision avoidance algorithm according to all COLREGs when encountering an opposing ship by adding COLREGs situational conditions to the virtual leader, and finally confirmed the feasibility of the proposed method through simulation.

In this study, analysis of dynamic characteristics and flight vibration was performed to unmanned aerial vehicles. The analysis model was supplemented by performing a dynamic characteristic test and a random vibration test using manufactured dummy aerial vehicle. For the dynamic characteristic test, a bungee cable was used to implement the free end boundary condition. Prior to the flight vibration test using a multiple electric shaker, a random vibration test was performed to predict the excitation force during the actual flight vibration test. It was judged that the actual test could be predicted more accurately by supplementing the analysis model from the test results. In addition, it was possible to determine the feasibility of the test by predicting the excitation force of the flight vibration test.

Semantic segmentation in autonomous driving for unstructured environments is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures. Current off-road datasets exhibit difficulties like class imbalance and understanding of varying environmental topography. To overcome these issues, we propose a deep learning framework for semantic segmentation that involves a pooled class semantic segmentation with five classes. The evaluation of the framework is carried out on two off-road driving datasets, RUGD and TAS500. The results show that our proposed method achieves high accuracy and real-time performance.

Military training is an essential item for the fundamental problem of war. However, there has always been a problem that many resources are consumed, causing spatial and environmental pollution. The concepts of defense modeling and simulation and CGF(Computer Generated Force) using computer technology began to appear to improve this problem. The Naval Operations, Resources Analysis Model(NORAM) developed by the Republic of Korea Navy is also a DEVS(Discrete Event Simulation)-based naval virtual force analysis model. The current NORAM is a battle experiment conducted by an operator, and parameter values such as maneuver and armament operation for individual objects for each situation are evaluated. In spite of our research conducted evolutionary, supervised, reinforcement learning, in this paper, we introduce our design of a scenario creation model based on evolutionary learning using genetic algorithms. For verification, the NORAM is loaded with our model to analyze wartime engagements. Human-level tactical scenario creation capability is secured by automatically generating enemy tactical scenarios for human-designed Blue Army tactical scenarios.

This paper describes the design of the avionics architecture for military unmanned aerial vehicles considering the airworthiness requirements for the first time. This design considers the redundancy in the system data bus and the power system and the data link system to meet the system safety requirements of the airworthiness requirements of military UAVs. This avionics architecture design has been verified through the system integration test and the flight test after manufacturing the UAV.

Since the concept of Manned-UnManned Teaming(MUM-T) and Unmanned Aircraft System(UAS) can efficiently respond to rapidly changing battle space, many studies are being conducted as key components of the mosaic warfare environment. In this paper, we propose a rule-based AI engagement model based on Basic Fighter Maneuver(BFM) capable of Within-Visual-Range(WVR) air-to-air combat and a simulation environment in which human pilots can participate. In order to develop a rule-based AI engagement model that can pilot a fighter with a 6-DOF dynamics model, tactical manuals and human pilot experience were configured as knowledge specifications and modeled as a behavior tree structure. Based on this, we improved the shortcomings of existing air combat models. The proposed model not only showed a 100 % winning rate in engagement with human pilots, but also visualized decision-making processes such as tactical situations and maneuvering behaviors in real time. We expect that the results of this research will serve as a basis for development of various AI-based engagement models and simulators for human pilot training and embedded software test platform for fighter.