• 한국정보전자통신기술학회논문지
• /
• 제9권3호
• /
• pp.257-265
• /
• 2016

이 연구는 과수원에 높은 통관 작업 기계에 적용되는 전동식 트럭 주행 시스템을 적용한 최적 설계가 제안되어 있습니다. 견인 성능과 언덕 등반 능력은 예측 및 기계 작업이 높은 틈새를 이용하여 과수원의 토양 특성을 고려하여 최적의 모터 주행 시스템을 평가 하였다. 견인 성능을 위한 설계 기준은 운동 저항을 뺀 견인력으로부터 산출 된 견인능력에 기초를 두었다. 등판 능력은 20%의 경사면을 3km/h의 속도로 수행되도록 하는 설계기준을 가지고 있다. 견인 및 등판 능력의 평가 결과에 따라 두 개의 DV48V, 4500rpm, 16kW AC 모터는 좌우 양쪽에서 독립적인 괘도를 갖는 것으로 적용된다. 각각의 모터는 50:1 감속기어 비율을 통하여 트랙형 주행 시스템의 구동 스프로켓에 동력을 전달하도록 설계되었다. 본 연구의 전동 트랙형 주행 시스템은 충분한 견인성능 및 등판 능력을 충분히 입증하고 20%의 경사지면을 갖는 과수원의 토양에서의 등반저항보다 12.5%가 더 높은 396kgf의 견인능력을 가지고 있는 것으로 밝혀졌습니다.

• 한국산학기술학회논문지
• /
• 제12권4호
• /
• pp.1523-1531
• /
• 2011

본 다축 차량은 험지와 야전에서 높은 이동성 때문에 비포장도로를 주행해야 하는 군용차량으로 사용된다. 특히 군용차량은 군 요구 사항에 의거 기본적으로 60% 경사로에서 안정적인 등판 성능을 지녀야 한다. 따라서 본 논문은 최적 타이어 힘 분배 방법을 통한 6WD/6WS차량의 등판능력 향상을 다루었다. 경사로 등판 시 사용할 최적 타이어 힘 분배 방법을 위하여 운전자로부터, 목표로 하는 종 방향 힘과 횡 방향 힘, 요 모멘트를 계산하였고, 마찰 원이론과 목적함수에 따른 최적화 된 토크가 각 륜에 분배되었다. 알고리즘 성능을 확인하기 위해서, 트럭심 소프트웨어를 이용하여 시뮬레이션 하였고, 비교를 위하여 2대의 차량을 제안하였다. 한 대의 차량은 최적타이어 힘 분배 방법이 적용되었고, 나머지 한 대는 궤도 차량과 같은 균등 힘 분배 방법이 적용되었다. 경사로에서 등판능력은 최적 타이어 힘 분배 방법에 의해서 향상 되어졌다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.111-113
• /
• 2006

DEAS is an direct searching and optimization method that based on the binary code space. It can be classified as an direct hill climbing searching. However, because of binary code space based searching, the searching in low resolution has random property. As the resolution of code increases during the search, its property of searching changes like that of hill climbing search. This paper propose a method for improving the performance of minimum seeking ability of DEAS with history information. The cost evaluation is increased. However the minimum searching ability of DEAS is improved along the same starting resolution.

• 제어로봇시스템학회논문지
• /
• 제7권10호
• /
• pp.819-826
• /
• 2001

Genetic algorithms are becoming more popular because of their relative simplicity and robustness. Genetic algorithms are global search techniques for nonlinear optimization. However, traditional genetic algorithms, though robust, are generally not the most successful optimization algorithm on any particular domain because they are poor at hill-climbing, whereas simulated annealing has the ability of probabilistic hill-climbing. Therefore, hybridizing a genetic algorithm with other algorithms can produce better performance than using the genetic algorithm or other algorithms independently. In this paper, we propose an efficient hybrid optimization algorithm named the adaptive random signal-based learning. Random signal-based learning is similar to the reinforcement learning of neural networks. This paper describes the application of genetic algorithms and simulated annealing to a random signal-based learning in order to generate the parameters and reinforcement signal of the random signal-based learning, respectively. The validity of the proposed algorithm is confirmed by applying it to two different examples.

• Journal of Multimedia Information System
• /
• 제2권1호
• /
• pp.179-186
• /
• 2015

This paper describes the application of a simulated annealing to a random signal-based learning. The simulated annealing is used to generate the reinforcement signal which is used in the random signal-based learning. Random signal-based learning is similar to the reinforcement learning of neural network. It is poor at hill-climbing, whereas simulated annealing has an ability of probabilistic hill-climbing. Therefore, hybridizing a random signal-based learning with the simulated annealing can produce better performance than before. The validity of the proposed algorithm is confirmed by applying it to two different examples. One is finding the minimum of the nonlinear function. And the other is the optimization of fuzzy control rules using inverted pendulum.

• 한국자동차공학회논문집
• /
• 제20권2호
• /
• pp.47-55
• /
• 2012

This work deals with dynamic analysis of a monorail system with magnetic caterpillar where magnets are embedded inside each articulated element of the caterpillar, augmenting traction force of main rubber wheels to climb up slope up to 15 degree grade. Considerations are first given to determine stiffness of the primary and secondary suspension springs in order for the natural frequencies of car body and bogie associated with vertical, pitch, roll and yaw motion to be within generally accepted range of 1-2 Hz. Equations for calculating magnetic force needed to climb up given slope are derived, and a magnetic caterpillar system for 1/6 scale monorail is designed based on the derivation. To assess the hill climbing ability and cornering stability, and make sure smooth operation of the side and vertical guiding wheels which is critical for safety, a multibody model that takes into account of every component level design characteristics of car, bogie, and caterpillar is set up. Through hill climbing simulation and comparison with measurement of the limit slope, the validity of the analysis and design of the magnetic caterpillar system are demonstrated. Also by studying the curving behavior, maximum curving speed without rollover, functioning of lateral motion constraint system, the effects of geometry of guiding rails are studied.

• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.256-262
• /
• 2021

In order for small electric vehicles to drive on hilly roads in Korea, methods to improve the climbing ability and power performance of vehicles should be taken. In order to improve the power performance of small electric vehicles, the performance of motors mounted on electric vehicles should be improved. However, if the performance of the motor is improved to improve the power performance of the electric vehicle, it is possible to lower the price competitiveness accordingly. In addition, the power consumption of the battery is rapidly increased to drive the high-performance motor, so in order to introduce the small electric vehicle into the domestic market, various problems must be overcome. In order to commercialize small electric vehicles that do not emit harmful exhaust gases to the human body in the hilly domestic terrain, it is effective to introduce a separate continuously variable transmission system that can improve the climbing ability and power transmission ability. In this study, we propose a proprietary model of continuously variable transmissions that can be applied to small electric vehicles. The proposed continuously variable transmission is equipped with a spring in the driving pulley and the driven pulley, and has the advantage of performing a shift that increases torque in a situation where the vehicle needs to increase torque when driving on a hill. In addition, the basic design for commercialization of the proposed continuously variable transmission was carried out, and the prototype manufactured and attached to the body of a small electric vehicle.

• 한국정보처리학회논문지
• /
• 제3권7호
• /
• pp.1773-1780
• /
• 1996

인공지능의 기호적 방법과 수치적 방법을 결합한 지식기반신경망은 다른 기계 학 습모델보다 우수한 성능을 나타내고 있다. 그러나 지식기반신경망은 신경망으로 형성 된 후 동적으로 그 구조를 변경할 수 없어서 영역이론정련화 기능을 갖추지 못하였다. 지식기반신경망의 이러한 단점을 보완하기 위하여 TopGen 알고리즘이 제안되었으나 삽입된 은닉노드를 모두 입력 노드에 연결한 점, 빔탐색을 이용한 등의 문제를 안고 있다. 본 논문에서는 TopGen의 문제점을 해소하기 위하여 은닉 노드를 다음 하위계층 의 노드에 링크 시켰으며, 역추적을 허용한 언덕 오르기를 이용하는 알고리즘을 설계 하였다.

• 한국자동차공학회논문집
• /
• 제19권5호
• /
• pp.7-13
• /
• 2011

The climate change due to the increased consumption with fossil fuel and rise of the oil price have been serious global issues. Automobile industry consumes 30% of the oil every year and causes air pollution and global warming by the exhaust emissions and carbon dioxide ($CO_2$). The demand of two-wheeled vehicle increases every year due to the parking and traffic problem caused by the increased automobiles in the urban area. Approximately 50,000,000 two-wheeled vehicles were produced in 2008. The development and sales of the hybrid two-wheeled vehicle industry become active due to its increased market demands. In this paper, the change of the motor and battery efficiency, driving distance, hill climbing ability with the change of the motor capacity was analyzed. Simulation of the peculiarities in urban driving schedule(World-wide Motorcycle Test Cycle(WMTC), Manhattan driving schedule), constant speed(10 km/h, 35 km/h) of small electronic two-wheeled vehicle was also carried out. Through the simulation result, appropriate capacities of the motor and battery for urban driving was acquired.

• 한국정보처리학회논문지
• /
• 제4권11호
• /
• pp.2780-2785
• /
• 1997

지식기반인공신경 망은 다른 기계학습알고리즘보다 우수한 성능을 나타내지만 인공신경망으로 형성된 후 동적으로 그 구조를 변경할 수 없어서 영역이론정련화 기능을 갖추지 못하였다. 지식기반인공신경망의 이러한 단점을 보완하기 위하여 TopGen 알고리즘이 제안되었으나 삽입된 은닉노드를 모든 입력 노드에 연결한 점, 빔탐색을 이용한 점 등의 문제를 안고 있다. 본 논문에서는 TopGen의 문제점을 해소하기 위하여 은닉노드를 입력 노드 중 관계가 깊은 일부의 노드에만 링크시켰으며, 역추적을 허용한 언덕오르기를 이용하는 알고리즘을 설계 하였다．