• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1809-1815
• /
• 2003

This paper presents a human friendly system using fuzzy inference as a Part of study to embody intelligent ship. We also build intelligent ship's steering system to take advantage of speech recognition that is a part of the human friendly interface. It can bring an effect such as labor decrement in ship. In order to design the voice instruction based ship's steering gear control system, we build of the voice instruction based learning(VIBL) system based on speech recognition and intelligent learning method at first. Next, we design an quartermaster's operation model by fuzzy inference and construct PC based remote control system. Finally, we applied the unposed control system to the miniature ship and verified its effectiveness.

• Journal of the Society of Naval Architects of Korea
• /
• v.34 no.3
• /
• pp.19-26
• /
• 1997

This paper is concerned with the design of neural-network based autopilot control system. The back-propagation neural network introduced in the previous paper by authors is applied to the autopilot control system. As a result, two neural-network controllers are developed, which are the model reference adaptive neural controller and the instantaneous optimal neural controller. The model reference adaptive neural controller is the control technique that the heading angle and angular velocity are controlled by the rudder angle to follow the output of the reference model. The instantaneous optimal neural controller optimizes the transition from one state to the next state. These control techniques are applied to a simple ship maneuvering model and their effectiveness is proved by numerical examples.

• Journal of Navigation and Port Research
• /
• v.26 no.2
• /
• pp.193-197
• /
• 2002

This paper suggests a method to design TSK(Takagi-Sugeno-Kang) fuzzy nonlinear control system for automatic steering system which contains the nonlinear component of ship's maneuvering equation. A TSk fuzzy model can be identified using input-output data and represent a nonlinear system very well. A TSK fuzzy controller can be designed systematically from a TSK fuzzy model because the consequent part of TSK fuzzy rule is a linear input-output equation having a constant term. Therefore, this paper suggests the method identifying the TSK fuzzy model and designing the TSK fuzzy controller based on the TSK fuzzy model for ship steering.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.5
• /
• pp.604-609
• /
• 2004

Recently, various studies had been made for automatic control system of small ships, in order to improve maneuvering and to reduce labor and working on board. To achieve efficient operation of small ships, it had been accomplished to rapid development of automatic technique, but the ship operation had been more complicated because of the need to handle various gauges and instruments. To solve these problems, there are examples to be applied to the speech information processing technologies which is one of the human interface methods in the system operation of ship, but the implementation of definite system is still incomplete. Therefore, the purpose of this paper is to implement the control system for ship steering using the voice recognition module.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 1999.10a
• /
• pp.35-35
• /
• 1999

최근 미사일 및 차세대 비행체에는 초기 고기동이나 무수한 제어력의 특성을 지닌 TVC 시스템이 많이 사용되고 있다. 기존의 공력 조타에 의한 비행 자세 제어방법은 속도의 2승에 비례하는 제어력을 발생하지만, TVC(Thrust Vector Control)를 이용하면 추력 방향을 변경하여 제어력을 얻음으로써 방향 제어에 보다 월등한 성능을 발휘할 수 있기 때문이다. TVC를 이용한 방향제어는 저속도 경우와 공기가 희박한 고 고도에서도 충분한 제어력을 얻을 수 있다. 그러나 그 우수성에 비추어 국내에서는 아직 그 성능에 대해 충분한 자료가 없는 실정이다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2002.03a
• /
• pp.141-144
• /
• 2002

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.91-92
• /
• 2023

이 연구에서는 선박이 군집을 이뤄 항해하는 방법으로, 추종 선박이 리더 선박의 궤적을 따라 항해하는 추종 알고리즘을 구현하고, 성능 검증을 위해 소형 RC 모형 보트를 사용하여 해상 실험을 수행하였다. 이 알고리즘은 추종 선박이 리더 선박의 궤적을 추종점으로 저장하고, 추종점까지의 목표 침로를 계산하여 추종하는 방법이다. 목표 침로는 시선각 유도법칙을 통해 계산하였으며, 목표 침로를 추종하기 위해 PD 제어를 적용한 침로 제어기를 구현하였다. 또한, 전방 선박과의 충돌을 방지하기 위해 전방 선박과의 거리에 따라 속력을 제어하는 알고리즘을 구현하였다. 구현된 알고리즘을 검증하기 위해 해상 실험을 진행하였으며, 결과를 분석하였다.

• Proceedings of KOSOMES biannual meeting
• /
• 2006.11a
• /
• pp.71-74
• /
• 2006

Currently offshore fisheries are one of shrinking industries and fishermen are getting older. Moreover it is difficult to work fisheries for decreasing fishermen as the time goes. Two people per a boat work together at least for proper fisheries. If the unskilled fisherman boards on boat, it will make some troubles to speak each other and diminish the efficiency of working because one person should control the boat. So it need to study the remote control system for leasure and outboard engine that can control and work at the same time. The remote control system is consisted of engine revolution, steering gear and forward reverse neutral gear controls. These three controls are made by position and speed control using DC motor, and microprocessor is used to communicate and control the engine speed This system can be controled and worked alone and we tested the system at sea and confirmed that the system works properly.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2011.11a
• /
• pp.1-2
• /
• 2011

최근 많은 분야에 무인시스템이 도입되고 있다. 초기에는 산업분야에서 인간이 하기 힘들거나 위험한 작업을 대신하는 단순 반복적인 자동화기술이 대부분이었으나, 최근에는 전자통신 기술발달에 힘입어 무인자동차, 무인항공기, 무인잠수정, 무인선박 등이 연구 개발되고 있다. 본연구에서는 자율형 소형무인선을 개발하고자 하였으며, 이와 관련하여 인터넷기반의 무선통신제어, 동력 추진 조타 냉각시스템, GPS 영상 헤딩센서 등 센싱시스템, 자율운항을 위한 제어기설계, GUI 등을 연구하였다. 아울러, 해상실험을 통해 유효성을 검증하였다.

• Journal of the Society of Naval Architects of Korea
• /
• v.34 no.2
• /
• pp.56-63
• /
• 1997

This paper is concerned with the design of neural-network based autopilot control system. In this paper, the back-propagation algorithm is introduced and explained in detail. The system identification method based on neural networks for ship motion is developed and its efficacy is verified by using a simple ship maneuvering model. Problems which may arise in a complex maneuvering model are then discussed. The neural-network based system identification method developed in this paper can be used effectively for reconstructing the ship maneuvering moodel which is known to have nonlinearity.