Skip to content

Ustawienia dostępności

Rozmiar czcionki
Wysoki kontrast
Animacje
Kolory

Tryb ciemny włączony na podstawie ustawień systemowych.
Przejdź do , żeby zmienić ustawienia.

Godło Polski: orzeł w złotej koronie, ze złotymi szponami i dziobem, zwrócony w prawo logo-signet of the Maritime University of Technology in Szczecin - griffin head, anchor elements and PM mark Maritime University of Szczecin

Unia Europejska

Department of Naval Architecture and Shipbuilding Tomasz Cepowski

Title: Determination of design formulas for container ships at the preliminary design stage using artificial neural network and multiple nonlinear regression

Author/Authors: Cepowski T., Chorab P.

Place of publication: OCEAN ENGINEERING

Year: 2021

Keywords: container ship, main dimensions, regression, ship design, ANN

Abstract: This article presents preliminary design formulas developed using a database of container ships built since 2015. Artificial neural networks and multiple nonlinear regressions with randomly searched functions were used to develop these formulas. The use of random search for nonlinear functions in a Multiple Nonlinear Regression model gave estimates which were just as precise as estimates created by the artificial neural network. All equations presented in this paper could have practical application for the estimation of dimensions, such as: length between perpendiculars, breadth, draught moulded and side depth. The equations were developed in relation to deadweight, TEU capacity and ship speed. These kinds of relationships have not been demonstrated before in ship theory. A statistical analysis showed that the main dimensions of the container ships can be estimated highly accurately by using the equations presented in the paper. The study showed that taking into account deadweight, TEU capacity and ship speed as three input parameters can improve the accuracy of an estimation by up to 44 percent, than when compared to the estimate accuracy of the design equations which are based on one input parameter.

Website address (link) to the full text
of the publication: https://www.sciencedirect.com/science/article/pii/S0029801821010969?via%3Dihub

 

DOI: 10.1016/j.oceaneng.2021.109727

Title: The Use of Artificial Neural Networks to Determine the Engine Power and Fuel Consumption of Modern Bulk Carriers, Tankers and Container Ships

Author/Authors: Cepowski T., Chorab P.

Place of publication: Energies

Year: 2021

Keywords: air pollution, bulk carrier, container carrier, deadweight, engine power, fuel consumption, sea transport, speed, tanker, ANN

Abstract: The 2007–2008 financial crisis, together with rises in fuel prices and stringent pollution regulation, led to the need to update the methods concerning ship propulsion system design. In this article, a set of artificial neural networks was used to update the design equations to estimate the engine power and fuel consumption of modern tankers, bulk carriers, and container ships. Deadweight or TEU capacity and ship speed were used as the inputs for the ANNs. This study shows that even a linear ANN with two neurons in the input and output layers, with purelin activation functions, offers an accurate estimation of ship propulsion parameters. The proposed linear ANNs have simple mathematical structures and are straightforward to apply. The ANNs presented in the article were developed based on the data of the most recent ships built from 2015 to present, and could have a practical application at the preliminary design stage, in transportation or air pollution studies for modern commercial cargo ships. The presented equations mirror trends found in the literature and offer much greater accuracy for the features of new-built ships. The article shows how to estimate CO2 emissions for a bulk carrier, tanker, and container carrier utilizing the proposed ANNs.

Website address (link) to the full text
of the publication: https://www.mdpi.com/1996-1073/14/16/4827

 

DOI: 10.3390/en14164827

Title: APPLICATION OF AN ARTIFICIAL NEURAL NETWORK AND MULTIPLE NONLINEAR REGRESSION TO ESTIMATE CONTAINER SHIP LENGTH BETWEEN PERPENDICULARS

Author/Authors: Cepowski T., Chorab P., Łozowicka D.

Place of publication: Polish Maritime Research

Year: 2021

Keywords: container ship, regression, ship design, ANN, length

Abstract: Container ship length was estimated using artificial neural networks (ANN), as well as a random search based on Multiple Nonlinear Regression (MNLR). Two alternative equations were developed to estimate the length between perpendiculars based on container number and ship velocity using the aforementioned methods and an up-to-date container ship database. These equations could have practical applications during the preliminary design stage of a container ship. The application of heuristic techniques for the development of a MNLR model by variable and function randomisation leads to the automatic discovery of equation sets. It has been shown that an equation elaborated using this method, based on a random search, is more accurate and has a simpler mathematical form than an equation derived using ANN.

Website address (link) to the full text
of the publication: https://sciendo.com/article/10.2478/pomr-2021-0019

 

DOI: 10.2478/pomr-2021-0019

Title: An estimation of motor yacht light displacement based on design parameters using computational intelligence techniques

Author/Authors: Cepowski T.

Place of publication: OCEAN ENGINEERING

Year: 2021

Keywords: artificial neural network, preliminary, regression, Yacht, Light displacement

Abstract: The article presents equations for the estimation of steel motor yacht light displacement based on selected design parameters, such as length overall, draught and breadth. The data of 240 build steel motor yachts from 2000 to 2020 with lengths from 30 m to 86 m were used to develop these equations. The complex design equations based on all design parameters were developed through the use of computational intelligence techniques, such as random search and Artificial Neural Networks. The simple relationships based on only one input design parameter were developed using common linear and non-linear regression. The study showed that the random search method, which utilizes a Multiple Nonlinear Regression model, offers good results that are as accurate as those developed through the use of artificial neural networks. The developed equations may have practical application for the parametric design of yachts.

Website address (link) to the full text
of the publication: https://www.sciencedirect.com/science/article/pii/S0029801821005217?via%3Dihub

 

DOI: 10.1016/j.oceaneng.2021.109086

Title: The prediction of ship added resistance at the preliminary design stage by the use of an artificial neural network

Author/Authors: Cepowski T.

Place of publication: OCEAN ENGINEERING

Year: 2020

Keywords: Ship design, Added resistance, Artificial neural network, Preliminary design, Approximation Model tests, Head waves

Abstract: This article focuses on the use of an artificial neural network to estimate added resistance in regular head waves while using ship design parameters, such as length, breadth, draught or Froude number. In order to create a reliable model, only experimental data determined through model test measurements was used to train the neural network. This study showed that added wave resistance values predicted by the neural network soundly correlated with measured data and had good generalization ability. The developed neural network was presented in the form of mathematical function. This article presents examples of the use of this function to calculate added wave resistance. Functions presented here could have practical application in ship resistance analysis at the preliminary design stage.

Adres strony internetowej (link) do pełnego tekstu publikacji: https://www.sciencedirect.com/science/article/pii/S0029801819307772

 

DOI: 10.1016/j.oceaneng.2019.106657

Title: An analysis of vertical shear forces and bending moments during nodule loading for a standard bulk carrier in the Clarion-Clipperton Zone

Author/Authors: Cepowski T., Kacprzak P.

Place of publication: Scientific Journals of the Maritime University of Szczecin-Zeszyty Naukowe Akademii Morskiej w Szczecinie

Year: 2020

Keywords: shear force, polymetallic nodules, ship, loading, bulk carrier, waves

Abstract: This article presents an analysis of vertical shear forces and bending moments during nodule loading in the case of a standard bulk carrier around the Clarion–Clipperton Zone. An operational efficiency index was applied to an assessment of internal forces during loading which took into account wave heights and periods around this zone. The aim of this research was to investigate whether waves could have a negative effect on loading efficiency and to estimate the nodule mass that can safely be loaded onto a standard bulk carrier taking these waves into account. Moreover, a calculation was made to discover the acceptable vertical shear force percentage limit, while also taking into account wave activity during loading.

Website address (link) to the full text

of the publication:http://repository.am.szczecin.pl/handle/123456789/2566

 

DOI: 10.17402/388

Title: Regression Formulas for The Estimation of Engine Total Power for Tankers, Container Ships and Bulk Carriers on The Basis of Cargo Capacity and Design Speed

Author/Authors: Cepowski T.

Place of publication: Polish Maritime Research

Year: 2019

Keywords: preliminary design, total power, regression, bulk carrier, tanker, container vessel

Abstract: This article presents regression formulas for the preliminary design of tankers, bulk carriers and container vessels, based on the data of ships built from 2000 to 2018. The formulas could have practical application for the estimation of total engine power by using ship’s deadweight or TEU capacity and speed. The regressions presented in this article are based on the most recent data and were developed for individual sub-types of tankers, bulk carriers and container ships. The presented regressions comply with trends found in the literature and offer greater accuracy for characteristics of new-built ships.

Website address (link) to the full text 
of the publication: https://content.sciendo.com/configurable/contentpage/journals$002fpomr$002f26$002f1$002farticle-p82.xml

DOI: 10.2478/pomr-2019-0010

Title: Determination of regression formulas for main tanker dimensions at the preliminary design stage

Author/Authors: Cepowski T.

Place of publication: Ships and Offshore Structures

Year: 2019

Keywords: ship, design, preliminary, tanker, main dimensions, regression

Abstract: This article presents design formulas for the preliminary design of tankers built from 2000 to 2018. These formulas could have practical application for the estimation of main tanker dimensions, such as: length between perpendiculars, breadth and draught moulded. All equations presented in this paper have been developed in relation to deadweight and velocity using a regression method. These kinds of relationships have not been demonstrated before in ship theory. The equations presented in the literature are only based on deadweight capacity and do not take design velocity into account. The regressions presented in this article were developed for individual tanker subtypes, such as: Handysize, Medium Range, Panamax, Post Panamax, Aframax, Suezmax and VLCC. The number of equations presented in this article may be used to extend design formulas published by other authors.

Website address (link) to the full text
of the publication: https://www.tandfonline.com/doi/full/10.1080/17445302.2018.1498570

DOI: 10.1080/17445302.2018.1498570

Title: Computational equation discovery of relationships between container ship fuel consumption and hull and propeller fouling phenomena

Author/Authors: Cepowski T., Drozd A.

Place of publication: Walter de Gruyter (Sciendo)

Year: 2019

Keywords: fuel consumption, ship, fouling, regression, curve, fitting, software, equation, discovery

Abstract: This article presents the relationship between fuel consumption, hull and propeller fouling phenomena and ship operational parameters. The study clearly shows the relationship between the fuel consumption of a container ship and the number of months since its last docking. Data, on which to base estimations, was measured and recorded from a container ship during 96 months at sea. The author developed a new heuristic algorithm to semi-automatically discover these relationship by the use of regression and evolution theory based on computational equation discovery methods. NdCurveMaster software was developed on the basis of this algorithm by the author and applied to discover the relationships presented in this paper. All relationships presented in this paper could have practical application in maritime transport analysis during ocean travel and speed up the development of ship theory development.

Website address (link) to the full text
of the publication: https://content.sciendo.com/view/journals/mape/2/1/article-p24.xml

DOI: 10.2478/mape-2019-0029

Title: Identification Accuracy of Additional Wave Resistance Through a Comparison of Multiple Regression and Artificial Neural Network Methods

Author/Authors: Cepowski T.

Place of publication: Walter de Gruyter (Sciendo)

Year: 2018

Keywords: Identification, neural networks, regression, wave resistance

Abstract: The article presents the use of multiple regression method to identify added wave resistance. Added wave resistance was expressed in the form of a four-state nominal function of: “thrust”, “zero”, “minor” and “major” resistance values. Three regression models were developed for this purpose: a regression model with linear variables, nonlinear variables and a large number of nonlinear variables. The nonlinear models were developed using the author’s algorithm based on heuristic techniques. The three models were compared with a model based on an artificial neural network. This study shows that non-linear equations developed through a multiple linear regression method using the author’s algorithm are relatively accurate, and in some respects, are more effective than artificial neural networks.

Website address (link) to the full text
of the publication: https://content.sciendo.com/view/journals/mape/1/1/article-p197.xml

DOI: 10.2478/mape-2018-0026

Title: An Estimation of the Final Price of Container Ships Based on Main Ship Parameters with the Use of ndCurveMaster Curve Fitting Software

Author/Authors: Cepowski T.

Place of publication: Walter de Gruyter (Sciendo)

Year: 2018

Keywords: container ship, price, ndCurveMaster, deadweight, regression

Abstract: The paper presents regression formulas that allow us to estimate the final price of new container ships, based on TEU and deadweight capacity, service speed, length between perpendiculars and gross tonnage of container ships built from 2005 to 2015. The formulas were developed using the author’s own method based on curve fitting techniques and regression methods. The study shows that utilising the author’s method to predict the final price could offer greater accuracy solutions than any standard methods presented in literature. This method was implemented properly with ndCurveMaster curve fitting software which was developed by the author and was applied to develop regression equations presented in the article. The formulas presented in the article have practical application for estimation of container ship final price needed in transport studies or preliminary parametric container ship design. These equations refer to the most up to date vessels and offer the chance to advance ship design theory.

Website address (link) to the full text
of the publication: https://content.sciendo.com/view/journals/ntpe/1/1/article-p365.xml?rskey=wPSXOy&result=1

 

DOI: 10.2478/ntpe-2018-0045

Title: Determination of Regression Formulas for Key Design Characteristics of Container Ships at Preliminary Design Stage

Author/Authors: Abramowski T., Cepowski T., Zvolenský P.

Place of publication: Walter de Gruyter (Sciendo)

Year: 2018

Keywords: ship, containership, design, main dimensions, regression

Abstract: This article presents regression equations to estimate container ship design characteristics based on the most up-to-date data and deadweight capacity, the number of containers and their combination at the preliminary design stage. These design formulas could have application for the estimation of key container ship characteristics such as: main ship dimensions, geometric parameters, main engine total power, ship velocity, final price and others. Regression equations were performed on the basis of IHS Maritime & Trade main container ship data built from 2005-2015. All equations presented in this paper could have practical application at the preliminary design stage and increase ship design theory development.

Website address (link) to the full text
of the publication: https://content.sciendo.com/view/journals/ntpe/1/1/article-p247.xml?rskey=6McNjk&result=1

 

DOI: 10.2478/ntpe-2018-0031

Title: Interim fuel consumption estimation based on ship service parameters in real weather conditions with the use of ndCurveMaster curve fitting software

Author/Authors: Cepowski T., Drozd A.

Place of publication: Zeszyty Naukowe Akademii Morskiej w Szczecinie

Year: 2017

Keywords: ship, fuel consumption, ndCurveMaster, weather routing, curve fitting, regression, hull fouling

Abstract: This paper deals with fuel consumption estimations relating to container ships on the basis of ship service and wave parameters. Data, on which to base estimations, was measured and recorded from a container ship during 96 months at sea. Approximating functions were calculated by the use of curve fitting techniques and regression methods, utilizing newly developed software named ndCurveMaster. The approximation function presented in this paper could have practical application for the estimation of container ship fuel consumption, while considering weather routing. In addition the study clearly shows the relationship between the fuel consumption of a container ship and the number of months since its last docking. These results may form the basis for further research in this direction.

Website address (link) to the full text
of the publication: http://repository.scientific-journals.eu/handle/123456789/2405

 

DOI: 10.17402/213

Title: Prediction of the Main Engine Power of a New Container Ship at the Preliminary Design Stage

Author/Authors: Cepowski T.,

Place of publication: Management Systems in Production Engineering

Year: 2017

Keywords: container ship, design parameter, preliminary design stage, main engine power, lengthbetween, perpendiculars, number of containers, TEU capacity, design, simple regression, multiple regression, approximation

Abstract: The paper presents mathematical relationships that allow us to forecast the estimated main engine power of new container ships, based on data concerning vessels built in 2005-2015. The presented approximations allow us to estimate the engine power based on the length between perpendiculars and the number of containers the ship will carry. The approximations were developed using simple linear regression and multivariate linear regression analysis. The presented relations have practical application for estimation of container ship engine power needed in preliminary parametric design of the ship. It follows from the above that the use of multiple linear regression to predict the main engine power of a container ship brings more accurate solutions than simple linear regression.

Website address (link) to the full text
of the publication: http://wydawnictwo.panova.pl/attachments/article/536/mspe-2017-0014.pdf

 

DOI: 10.1515/mspe-2017-0014

Title: Prediction of a Newbuilding Price of the Bulk Carriers Based on Gross Tonnage GT and Main Engine Power

Author/Authors: Cepowska Ż., Cepowski T.

Place of publication: Management Systems in Production Engineering

Year: 2017

Keywords: neural networks, artificial neural networks (ANN), shipbuilding, sea navigation

Abstract: The paper presents mathematical relationships that allow us to forecast the newbuilding price of new bulk carriers, based on data concerning vessels built in 2005-2015. The presented approximations allow us to estimate the price based on a gross tonnage capacity and a main engine power The approximations were developed using linear regression and the theory of artificial neural networks. The presented relations have practical application for estimation of bulk carrier newbuilding price needed in preliminary parametric design of the ship. It follows from the above that the use of artificial neural networks to predict the price of a bulk carrier brings more accurate solutions than linear regression.

Website address (link) to the full text
of the publication: http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.ekon-element-000171454373

 

DOI:

Autor: Website Administrator

Przeglądarka Internet Explorer nie jest wspierana

Zalecamy użycie innej przeglądarki, aby poprawnie wyświetlić stronę