• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.11
• /
• pp.4726-4731
• /
• 2011

This paper proposed the algorithm to select optimal grinding condition for plunge grinding in the batch production unit. In order to apply to the proposed algorithm, the state variable for plunge grinding process was defined and the optimal grinding condition for each cycle in batch production was decided by genetic algorithm. Based on the optimized grinding condition in each cycle, the optimal grinding condition for whole batch production was selected by dynamic programming. The proposed algorithm was evaluated by computer simulation.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2020.11a
• /
• pp.68-69
• /
• 2020

해상에서는 선박의 안전한 항해를 위해 각종 항로 표지가 이용되는데, 과학 기술이 발전함에 따라 환경적 요소 등의 이유로 항로표지를 설지 할 수 없는 지역에서는 가상항로 표지를 필요로 하고 있다. 선행연구에서는 가상항로 표지의 최적 배치를 위해 선박 항해의 물리적 항해 제한 및 항해 장애물요소, 선박 교통 위험도 등을 격자 단위로 파악하였다. 이에 본 연구는 격자별로 나눈 해역의 위험도 지수를 통합하여 통합 위험도 평가 지수를 개발하고자 한다. 이에 요소별 가중치를 설정하고, 레이어를 통합한 뒤 위험도를 산정하여 통계데이터 기반 위험도를 평가하였다. 요소별 가중치 설정을 위해 위험도 레이어 통합 가중치를 설정하였으며, 실제 해역에 적용하여 위험도를 평가하였다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.41-48
• /
• 2007

In this paper, we propose an optimal placement of sensor nodes with 2.4GHz wireless channel characteristics. The proposed method determines optimal transmission range based on log-normal path loss model, and optimal number of sensor nodes calculating the density of sensor nodes. For the lossless data transmission, we search the optimal locations with self-organizing feature maps(SOM) using transmission range, and number of sensor nodes. We demonstrate that optimal transmission range is 20m, and optimal number of sensor nodes is 8. We performed simulations on the searching for optimal locations and confirmed the link condition of sensor nodes.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.3
• /
• pp.42-48
• /
• 2002

Placement is an important step in the physical design of VLSI circuits. It is the problem of placing a set of circuit modules on a chip to optimize the circuit performance. The most popular algorithms for placement include the cluster growth, simulated annealing and integer linear programming. In this paper we propose a genetic algorithm searching solution space for the placement problem, and then compare it with simulated annealing by analyzing the results of each implementation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.79-80
• /
• 2023

동기식 분산 딥러닝 기법은 그래디언트 계산 작업을 다수의 워커가 나누어 병렬 처리함으로써 모델 학습 과정을 효율적으로 단축시킨다. 배치 사이즈는 이터레이션 단위로 처리하는 데이터 개수를 의미하며, 학습 속도 및 학습 모델의 품질에 영향을 미치는 중요한 요소이다. 멀티 GPU 환경에서 작동하는 분산 학습의 경우, 가용 GPU 메모리 용량이 커짐에 따라 선택 가능한 배치 사이즈의 상한이 증가한다. 하지만 배치 사이즈가 학습 속도 및 학습 모델 품질에 미치는 영향은 GPU 활용률, 총 에포크 수, 모델 파라미터 개수 등 다양한 변수에 영향을 받으므로 최적값을 찾기 쉽지 않다. 본 연구는 동기식 분산 딥러닝 환경에서 실험을 통해 최적의 배치 사이즈 선택에 영향을 미치는 주요 요인을 분석한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.687-693
• /
• 2012

In this paper, we propose a optimal deployment method for cooperative exploration of swarm robots. The proposed method consists of two parts such as optimal deployment and path planning. The optimal area deployment is proposed by the K-mean Algorithm and Voronoi tessellation. The path planning is proposed by the potential field method and A* Algorithm. Finally, the numerical experiments demonstrate the effectiveness and feasibility of the proposed method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.15-24
• /
• 2019

The optimum solutions of MOSCOS antenna arrangement were studied to solve the EMI between it and EWT mounted on an MTB. Two candidates of optimal place for MOSCOS antenna were determined by using a fishbone diagram to determine seven reasons based on 4M1E, to identify the design factors on Friis equations, and to analyze the case study of EMI related to MOSCOS. MOSCOS antenna was rearranged by the final optimal position, which was selected by measuring the Power Spectral Density (PSD) at two locations, and the proposed improvement was tested on board to determine its efficiency.

• Journal of Korea Society of Industrial Information Systems
• /
• v.2 no.2
• /
• pp.87-103
• /
• 1997

설비 배치는 기업의 장단기 생산능력 효율에 상당한 영향을 미치므로 제품 및 서비스의 생산에 있어 최대의 효율을 올릴 수 있도록 배치되어야 하나, 최적의 설비 배치안을 찾는다는 것은 매우 어려운 일이다. 이러한 설비 배치 문제는 이차할당문제(Quadratic Assignment Problem : QAP)로 모형화할 수 있으며, 이의 해결을 위해 일반적으로 휴리스틱 알고리즘은 전통적인 검색 기법에 비해 우위에 있는 것으로 알려지고 있다. 따라서 본 연구에서는 설비 배치 문제의 해결을 위하여 유전 알고리즘의 개발을 시도하였으며, 선행 연구들과의 비교 분석 결과 기존 연구들에 비해 더 우수한 해을 제시할 수 있었다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.9
• /
• pp.55-63
• /
• 2003

An attitude control system using reaction thrusters for the upper stage of a launch vehicle is considered. The thruster configuration (position and direction) determines control system response, fuel consumption, effective torque and system fault tolerance. We propose a procedure for finding the optimal thruster configuration with desired control effectiveness over the range of selected torque commands. An optimization technique called Particle Swarm Optimization is used for the numerical experiments. The validity of the solution is checked through computer simulations.

• Journal of the Korea Society for Simulation
• /
• v.26 no.1
• /
• pp.39-46
• /
• 2017

An arrangement of passive sonars is considered to be a fixed underwater surveillance system for detecting an anti-submarine consistently. An effectiveness score for optimizing the arrangement of passive sonars is defined in a function of the probability of detection and localization. These two features contain various probabilistic variations including seasons, sea states, depths of water, etc. Due to this reason, the effectiveness scores show probabilistic characteristics from the input of the arrangement of passive sonars. This paper defines the optimization problem having the results of probabilistic characteristics from various parameters of input conditions. Also, we suggest a simulation-based process of deciding the optimized arrangement of passive sonars using DPSO(Discrete binary version of PSO) method.