• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.1-10
• /
• 2024

The research on predicting the routes of ships, which constitute the majority of maritime transportation, can detect potential hazards at sea in advance and prevent accidents. Unlike roads, there is no distinct signal system at sea, and traffic management is challenging, making ship route prediction essential for maritime safety. However, the time intervals of the ship route datasets are irregular due to communication disruptions. This study presents a method to adjust the time intervals of data using appropriate interpolation techniques for ship route prediction. Additionally, a deep learning model for predicting ship routes has been developed. This model is an LSTM model that predicts the future GPS coordinates of ships by understanding their movement patterns through real-time route information contained in AIS data. This paper presents a data preprocessing method using linear interpolation and a suitable deep learning model for ship route prediction. The experimental results demonstrate the effectiveness of the proposed method with an MSE of 0.0131 and an Accuracy of 0.9467.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2016.05a
• /
• pp.199-201
• /
• 2016

The performance of navigational equipments is advanced, but the importance of the practical capability of bridge device by ship's officer, ie the ability of risk prediction and the obligation of avoidance for reducing sea accident, has been constantly augmenting. This abilities and obligation may be represented in the cognitive competence of navigational officer. Different levels of ship's bridge team was carried out rescue maneuvering by ship handling simulator and then it analyzed the resulting of initial response in cognitive progress by case based on trajectory. Further, the data will be used as training and evaluation model of cognitive situation.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.277-279
• /
• 2022

Rapid Development and adoption of AIS as a survailance tool has resulted in widespread application of data analysis technology, in addition to AIS ship trajectory clustering. AIS data-based clustering has become an increasingly popular method for marine traffic pattern recognition, ship route prediction and anomaly detection in recent year. In this paper we propose a route waypoint extraction by clustering ships CoG variance trajectory using Density-Based Spatial Clustering of Application with Noise (DBSCAN) algorithm in both port approach channel and coastal waters. The algorithm discovers route waypoint effectively. The result of the study could be used in traffic route extraction, and more-so develop a maritime anomaly detection tool.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.8 no.1
• /
• pp.17-22
• /
• 2005

The movement of drifting ships on the sea is closely related to marine environmental forces such as waves, currents, winds, etc. To develop a prediction model for trajectories oi drifting ships, an experiment on the movement of drifting ships was carried out in the Southeastern Sea of Korea. Five types of ships including a lire raft and tour ships with G/T 10tons, G/T 2o tons, G/T 50 tons, and G/T 80 tons, were considered in the experiment. The G/T 50 ton class ship was used as a base ship for obtaining the currents, winds and heading angles of ship following the trajectory. The trajectory of each ship was measured by DGPS(Differential Global Positioning System) and collected using APRS(Automatic Position Reporting System) installed on the base ship. The error range in position fix of DGPS are approximately ±1 m. The drift speed of ship in the experiment was between 3％ to 5％ of wind speed and drift direction of ship was deflected by ±90° from wind direction. Also, the heading of drifting ship was normal to wind direction.

• Journal of Navigation and Port Research
• /
• v.43 no.6
• /
• pp.369-376
• /
• 2019

Ship hydrodynamics in the confined waterways is challenging. When a ship is maneuvering in confined waterways, the hydrodynamic behavior may vary significantly because of the hydrodynamic interaction between the bottom of the ship hull and the seabed, or so-called shallow water effects. Thus, an accurate prediction of shallow water and bank effects is essential to minimizing the risk of the collision and the grounding of the ships. The hydrodynamic derivatives measured by the virtual captive model test provide a path to predicting the change in ship maneuverability. This paper presents a numerical simulation of captive model tests to predict the maneuverability of a ship in confined waterways. Also, straight and zig-zag simulation were conducted to predict the trajectory of a ship maneuvering in confined waterways. The results showed that the asymmetric flow around a ship induced by vicinity of banks causes pressure differences between the port and starboard sides and the trajectory of a ship maneuvering in confined waterways.

• Journal of Ocean Engineering and Technology
• /
• v.35 no.3
• /
• pp.173-182
• /
• 2021

The maneuvering performance of a ship on the actual sea is very different from that in calm water due to wave-induced motion. Enhancement of a ship's maneuverability in waves at the design stage is an important way to ensure that the ship navigates safely. This paper focuses on the maneuvering prediction of a Russian trawler in wind and irregular waves. First, a unified seakeeping and maneuvering analysis of a Russian trawler is proposed. The hydrodynamic forces acting on the hull in calm water were estimated using empirical formulas based on a database containing information on several fishing vessels. A simulation of the standard maneuvering of the Russian trawler was conducted in calm water, which was checked using the International Maritime Organization (IMO) standards for ship maneuvering. Second, a unified model of seakeeping and maneuvering that considers the effect of wind and waves is proposed. The wave forces were estimated by a three-dimensional (3D) panel program (ANSYS-AQWA) and used as a database when simulating the ship maneuvering in wind and irregular waves. The wind forces and moments acting on the Russian trawler are estimated using empirical formulas based on a database of wind-tunnel test results. Third, standard maneuvering of a Russian trawler was conducted in various directions under wind and irregular wave conditions. Finally, the influence of wind and wave directions on the drifting distance and drifting angle of the ship as it turns in a circle was found. North wind has a dominant influence on the turning trajectory of the trawler.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1176-1179
• /
• 2020

Vessel path prediction methods generally predict the latitude and longitude of a future location directly. However, in the case of direct prediction, errors could be large since the possible output range is too broad. In addition, error accumulation could occur since recurrent neural networks-based methods employ previous predicted data to forecast future data. In this paper, we propose a vessel path prediction method that does not directly predict the longitude and latitude. Instead, the proposed method predicts the acceleration of the vessel. Then the acceleration is employed to generate the velocity and direction, and the values decide the longitude and latitude of the future location. In the experiment, we show that the proposed method makes smaller errors than the direct prediction method, while both methods employ the same model.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2016.05a
• /
• pp.285-286
• /
• 2016

We aim to propose the prediction modeling method of ship's position with extracting ship's trajectory model through pattern recognition based on the data that are being collected in VTS centers at real time. Support Vector Machine algorithm was used for data modeling. The optimal parameters are calculated with k-fold cross validation and grid search. We expect that the proposed modeling method could support VTS operators' decision making in case of complex encountering traffic situations.

• Journal of Ship and Ocean Technology
• /
• v.1 no.2
• /
• pp.19-30
• /
• 1997

The accurate prediction of the flow and the pressure distribution near the tip of the blade is crucial in determining the tip vortex cavitation inception which usually occurs on the blade tip or inside the core of the tip vortex just downstream of the blade tip. An improved boundary element method is applied to the prediction of the flow around propeller blades, with emphasis at the tip region. In the method, the Blow adapted grid and a higher order panel method, which combines a hyperboloidal panel geometry with a hi-quadratic dipole distribution, are used in order to accurately model the trailing wake geometry and the highly rolled-up regions in the wake. The method is applied to several propeller geometries and the results have been found to agree well to the existing experimental data. Inviscid flow methods are able to predict the pressures at the tip as well as the shape of the trailing wake. On the other hand, they are unable to determine the flow inside the viscous core of the tip vortex, where cavitation inception often occurs. Thus, a method is presented that treats the flow inside the viscous core. The inner flow is treated with a 2-D Clavier-stokes solution without making any assumptions for axisymmetric flow and conicity of the flow along the tip trajectory. The method can thus allow the treatment of general propeller blade configurations. The velocity and pressure distributions inside the core are shown and compared to those from other numerical methods.

• Aerospace Engineering and Technology
• /
• v.13 no.2
• /
• pp.177-184
• /
• 2014

Flight safety analyses concerned with Launch Vehicle are performed to measure the risk to the people, ship and aircraft using impact point and impact dispersion area of debris generated by on-trajectory failures and malfunction turns. Predictions of impact point and impact dispersion area are essential for launch vehicle's flight safety analysis. Usually, impact dispersion area can be estimated in using Monte-Carlo simulation. However, Monte-Carlo method requires more several hundreds of iterative calculations which requires quite some time to produce impact dispersion area. Herein, we check the possibility of applying JU(Julier Uhlmann) transformation and Taguchi method instead of Monte-Carlo method and we propose a best method in terms of compuational time to produce impact dispersion area by comparing the results of the three methods.