• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.314-324
• /
• 2020

Due to the nonlinearity and environmental uncertainties, the design of the ship's steering controller is a long-term challenge. The purpose of this study is to design an intelligent autopilot based on Extended Kalman Filter (EKF) trained Radial Basis Function Neural Network (RBFNN) control algorithm. The newly developed free running model scaled surface vessel was employed to execute the motion control experiments. After describing the design of the EKF trained RBFNN autopilot, the performances of the proposed control system were investigated by conducting experiments using the physical model on lake and simulations using the corresponding mathematical model. The results demonstrate that the developed control system is feasible to be used for the ship's motion control in the presences of environmental disturbances. Moreover, in comparison with the Back-Propagation (BP) neural networks and Proportional-Derivative (PD) based control methods, the EKF RBFNN based control method shows better performance regarding course keeping and trajectory tracking.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.184-185
• /
• 2022

국제해사기구(IMO)에서는 2017년 미래선박으로서 자율운항선박(MASS)의 개념을 채택한 바 있으며, 실해역 운항을 위한 국제법규 및 규정 검토를 진행하고 있다. 무인선은 악천후시 유인선이 수행하기 힘든 임무를 대체하거나 지원하기 위하여 원격 혹은 자율적으로 운용되는 일종의 소형 자율운항선박을 의미한다. 선박해양플랜트연구소에서는 2011년부터 해양수산부 연구개발사업을 통하여, 무인선 아라곤호 시리즈를 개발하였으며, 아라곤1호, 2호, 3호 등 총 3척을 운용하고 있다. 해당 선박은 길이 8미터, 배수량 약 3톤급의 활주선형으로 원격운항, 경로추종 및 충돌회피 등 자율운항 기능이 적용되어 있다. 한편, 무인선은 공중 드론과 달리 탑재중량이 크고, 항속시간이 길어 해상에서 감시,첩보, 정찰 등에 효용성이 높으며, 최근 한척보다는 여러 척을 운용하는 것이 효과적이어서 무인선 군집(USV Swarm)으로 해상임무를 수행하려는 연구가 다양하게 진행되고 있다. 선박해양플랜트연구소에서는 2019년부터, 기존의 아라곤호 시리즈 무인선들을 활용하여, 무인선 군집 자율운항 시스템 개발을 위한 "인공지능 기반 무인선 상황인식 및 자율운항 기술 개발" 과제를 진행하고 있다. 해상에서 불법선박이 출현시 이를 효과적으로 단속하기 위하여 추적 기동이 필요한데, 본 연구에서는 무인선 3척을 활용하여 불법선박을 추적하는 해상 감시 실해역 시험을 수행하였다. 본 논문에서는 무인선 군집 자율운항 시스템에 대하여 소개하고, 무인선 군집을 활용한 불법선 추적에 관한 실해역 시험결과에 대해 소개한다.

• Journal of Ocean Engineering and Technology
• /
• v.32 no.2
• /
• pp.138-142
• /
• 2018

The marine industry is rapidly developing as a result of the increase in various needs in the marine environment. In addition, accidents involving ship fires and explosions and the resulting casualties are increasing. Generally, manpower and safety problems exist in fire fighting. A fire fighter in the form of an autonomous surface robot would be ideal for marine fire safety, because it has no manpower and safety problems. Therefore, an autonomous surface robot with the abilities of fire recognition and tracking, nozzle selection, position and attitude control, and fire fighting was developed and is discussed in this paper. The test and evaluation results of this robot showed the possibility of real-size applications and the need for additional studies.

• Journal of Welding and Joining
• /
• v.8 no.1
• /
• pp.23-30
• /
• 1990

The robotic welding has been adapted positively in many welding shops forthe purpose of improving the welding efficiency and liberating operators from the severe working atmosphere. But for a large-size structure with thick plates like ship-building and every kind of plants manufacturing, the application of the arc welding robots is not established yet. The reason is assumed that the conventional arc welding robots are not adaptive for multi-pass welding of thick plates whose grooves are not so accurate. As one solution to this problem, a guidance system which uses the welding arc itself as a sensor is largely used. In this study the velocity controller which changes the tip to workpiece distance for regulating the weld proposed. The proportional and integral gain of velocity controller were determined by using the computer simulation of the control system, and the simulation results compared with the experimental ones. It was revealed that the developed control system using the arc sensor principle has a good capability of tracking the weld joint, although some more studies will be needed to refine the model of arc current.

• Journal of Navigation and Port Research
• /
• v.35 no.3
• /
• pp.227-233
• /
• 2011

This paper presents the tracking and stabilization problem of a night vision system for marine surveillance. Both a hardware system and software modules are developed to control azimuth and elevation axes independently with compensation for ship motion. A two degree of freedom(2DOF) PID controller is designed and its parameters are tuned using a real-coded genetic algorithm(RCGA). Simulation demonstrates the effectiveness of the proposed method.

• Journal of Ocean Engineering and Technology
• /
• v.11 no.3
• /
• pp.170-179
• /
• 1997

This paper presents a hybrid navigation system for AUV to locate its position precisely in rough sea. The tracking system is composed of various sensors such as an inclinometer, a tri-axis magnetometer, a flow meter, and a super short baseline(SSBL) acoustic position tracking system. Due to the inaccuracy of the attitude sensors, the heading sensor and the flowmeter, the predicted position slowly drifts and the estimation error of position becomes larger. On the other hand, the measured position is liable to change abruptly due to the corrupted data of the SSBL system in the case of low signal to noise ratio or large ship motions. By introducing a sensor fusion technique with the position data of the SSBL system and those of the attitude heading flowmeter reference system (AHFRS), the hybrid navigation system updates the three-dimensional position robustly. A Kalman filter algorithm is derived on the basis of the error models for the flowmeter dynamics with the use of the external measurement from the SSBL. A failure detection algorithm decides the confidence degree of external measurement signals by using a fuzzy inference. Simulation is included to demonstrate the validity of the hybrid navigation system.

• Proceedings of KOSOMES biannual meeting
• /
• 2006.11a
• /
• pp.277-282
• /
• 2006

The purpose in having a control surface on a ship is to control the motion of the ship. The control surface may be composed entirely of a single movable surface or of a combination of fixed and movable portion A control surface has one sole function to perform in meeting its purpose, and that is to develop a control force in consequence of its orientation and movement relative to the water. The forces and moments generated as a result of this rotation and angle of attack then determine the maneuvering characteristics of the ship. In this paper the study of flapped rudder's 2-dimensional section was accomplished. Model tests had been carried out with different angles of attack of a main foil and flap's deflection angles to predict the performance of the flapped rudder and the 2 frame particle tracking method had been used to obtain the velocity distribution in the flow field $Re=2.8\times10^4$ had been used during the whole experiments and measured results had been compared with each other.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.15 no.2
• /
• pp.111-117
• /
• 2009

IMO is treating various and numerous agenda with time, and the contents of agenda have been tending to achieve international standardization for details of technology, for example GBS(Goal based new ship construction standards), PSPC(Performance Standards of Protective Coating), LRIT(Long-Range Identification and Tracking of Ships), etc. This paper presents the latest agenda trend of IMO committees and analyzes the ROK's activities in response to IMO committees. In the result of analysis, ROK lacks in performance ability as a A-category council member as well as infrastructure to support the government activities in IMO continuously. Therefore, ROK should be conscious of policy approaches to international maritime tendency and needs to complete the internal/external infrastructure which leads the international maritime policy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.3
• /
• pp.310-315
• /
• 2014

The domestic maritime environment shows higher frequency of maritime accidents amidst greater traffic volume arising from increasing international seaborne trade and maritime leisure activities. To reduce such maritime accidents, there exist various kinds of safety navigation devices in the ship bridge aimed to mitigate burdens of navigators and support their accurate decision making. Amongst is the AIS considered very important, which is an automatic tracking system to assist understanding of the circumstances in the vicinity by receiving information of other ships and also sending its own; where the information contains errors initially, however, such wrong information is periodically transmitted, accordingly giving rise to hindrance sometimes in decision making by shore operators or ship navigators at sea. This study is to propose the error data and field management algorithm using fuzzy theory toward improving reliability and accuracy in ship related information received from AIS.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.5
• /
• pp.564-570
• /
• 2014

This paper propose a method to detect and track a human face using depth information as well as color images for detection of drowsy driving. It consists of a face detection procedure and a face tracking procedure. The face detection procedure basically uses the Adaboost method which shows the best performance so far. But it restricts the area to be searched as the region where the face is highly possible to exist. The face detected in the detection procedure is used as the template to start the face tracking procedure. The experimental results showed that the proposed detection method takes only about 23 % of the execution time of the existing method. In all the cases except a special one, the tracking error ratio is as low as about 1 %.