• Journal of the Society of Naval Architects of Korea
• /
• v.33 no.1
• /
• pp.153-160
• /
• 1996

This paper presents a method that determines the stem profile dimensions for full, slow-speed ship using fuzzy modeling applied the genetic algorithm and compares with the database of ships.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.118-124
• /
• 1995

본 연구에서는 유전자 알고리즘과 Hooke & jeeves 방법을 적용한 퍼지모델링 기법 을 이용하여 저속비대선에서 선미형상의 주요치수를 결정하고, 이를 실적선과 비교하였다.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.4
• /
• pp.234-242
• /
• 2021

In this study, we introduce the prediction of brake power for low-speed full ships and container carriers using the linear regression and a machine learning approach. The residual resistance coefficient, wake fraction coefficient, and thrust deduction factor are predicted by regression models using the main dimensions of ship and propeller. The brake power of a ship can be calculated by these coefficients according to the 1978 ITTC performance prediction method. The mean absolute error of the predicted power was under 7%. As a result of several validation cases, it was confirmed that the machine learning model showed slightly better results than linear regression.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.27 no.1
• /
• pp.84-98
• /
• 1990

Fifteen(l5) series hull forms for full slow-speed ships were prepared by expanding the basic parent hull form developed through the extensive theoretical and experimental studies, and model tests were carried out for each of the series hull forms. A set of systematic data was prepared from the test results and utilized to derive regression equations for the prediction of resistance and powering characteristics by statistical analysis. Computer program has been prepared based on the results of analysis and a sample run is presented.

• Journal of the Society of Naval Architects of Korea
• /
• v.37 no.3
• /
• pp.11-20
• /
• 2000

The flow characteristics around the stern region of two VLCCs with the same forebody and slightly different afterbody are investigated along with propulsive performance of the ship. The local mean flow measurements and the resistance and self-propulsion tests are carried out in the towing tank for the two VLCC hull forms. The measured results clearly show the formation of bilge vortices and their effect on propulsive efficiency. The comparisons are made for the two VLCC hull forms and the relation between stern framelines and bilge vortex strength is explored. Experimental data can provide a good test case to validate the accuracy of numerical methods and turbulence model of CFD codes for ship flow calculation.

• Proceedings of KOSOMES biannual meeting
• /
• 2017.04a
• /
• pp.127-127
• /
• 2017

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1274-1280
• /
• 2022

The resistance performance evaluation of general ships using computational fluid dynamics requires a lot of time and cost, and various methods are being studied to reduce the time and cost. Existing methods using main particulars or cross sections of ships have limitations in estimating resistance performance that is greatly dependent on the shape of the ship. In this paper, we propose a deep neural network model that can quickly predict the resistance performance of the hull surface by inputting the geometric information of the hullform mesh. The proposed deep neural network model based on Perceiver IO can immediately predict resistance performance, unlike computational fluid dynamics techniques that require calculation in each time step. It shows the result of estimating the resistance performance with an average error of less than 1% in the data set for a 50 K tanker ship, a type of low-speed full ship.

• Journal of the Society of Naval Architects of Korea
• /
• v.57 no.6
• /
• pp.312-321
• /
• 2020

In this study, machine learning techniques were applied to predict the residual resistance coefficient (Cr) of low-speed full ships. The used machine learning methods are Ridge regression, support vector regression, random forest, neural network and their ensemble model. 19 hull form variables were used as input variables for machine learning methods. The hull form variables and Cr data obtained from 139 hull forms of KRISO database were used in analysis. 80 % of the total data were used as training models and the rest as validation. Some non-linear models showed the overfitted results and the ensemble model showed better results than others.

• Journal of the Society of Naval Architects of Korea
• /
• v.42 no.4 s.142
• /
• pp.307-314
• /
• 2005

In recent years, many environmentally disastrous oil spill accidents from damaged vessels become worse especially when the early treatment is not prompt enough. To properly handle this type of accidents and prevent further disasters, international organizations establish and impose various rules and regulations. In assessing the damages and providing salvage operations, the propulsive performance of damaged vessels is of great importance, as well as for containing oil spill while the vessels are being towed or self-propelled. Until now, many naval hydrodynamics researches have focused on the propulsive performance in normal operating conditions and only a few studies for damaged vessels are found in literature. In this paper experimental method is used to study the Propulsive performance of a very large crude-oil carrier (VLCC) in .heeled and/or trimmed conditions.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.5
• /
• pp.447-456
• /
• 2019

In the early stage of ship design, the rapid prediction of resistance of hull forms is required. Although there are more accurate prediction methods such as model test and CFD analysis, statistical methods are still widely used because of their cost-effectiveness and quickness in producing the results. This study suggests the prediction formula for the residual resistance coefficient (Cr) of the low-speed full ships. The formula was derived from the statistical analysis of model test results in KRISO database. In order to improve prediction accuracy, the local variables of hull forms are defined and used for the regression process. The regression formula for these variables using only principal dimensions of hull forms are also provided.