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.
Modelling of green water ingress into holds of an open-top containership in its preliminary design phase
In this paper a method is presented of modelling the green water ingress into holds of open-top containership, which can be useful in the preliminary ship design phase. As a result of the research a mathematical formula which makes it possible to determine a minimum freeboard height with a view of as- low- as- possible occurrence rate of green water ingress into holds at given ship design parameters, was obtained. The research was carried out under assumption of constant ship hull dimensions. The design formula was elaborated by using a method based on a goal-oriented conceptual approach to formulation of design criteria, proposed by IMO. On the basis of the concept a deterministic scenario describing operational conditions of the ship in question, was assumed, and for the conditions the research was performed.
Influence analysis of changes of design parameters of passenger-car ferries on their selected sea-keeping qualities
The main scientific aim of this research was to elaborate design guidelines which could make it possible to improve sea-keeping qualities of passenger-car ferries. The searched-for design guidelines were prepared in the form of regression functions as well as artificial neural networks on the basis of the results obtained from calculations with the use of numerical methods based on the theory of planar flow around a body. The guidelines make it possible to predict ship roll, sea-sickness index, lateral and vertical accelerations on the basis of quantities available in the preliminary stage of ship design.
On the modeling of car passenger ferryship design parameters with respect to selected sea-keeping qualities and additional resistance in waves
This paper presents the modeling of car passenger ferryship design parameters with respect to such design criteria as selected sea-keeping qualities and additional resistance in waves. In the first part of the investigations approximations of selected statistical parameters of design criteria of ferryship were elaborated with respect to ship design parameters. The approximation functions were obtained with the use of artificial neural networks. In the second part of the investigations design solutions were searched for by applying the singleand multi-criterial optimization methods. The multi-criterial optimization was performed by using Pareto method. Such approach made it possible to present solutions in such form as to allow decision makers (shipowner, designer) to select solutions the most favourable in each individual case.
The modeling of seakeeping qualities of Floating Production, Storage and Offloading (FPSO) sea-going ships in preliminary design stage
This paper presents an analysis of a presently applied approach to accounting for seakeeping qualities of FPSO sea-going ships and possible using it in preliminary design stage. Approximations of heaving, pitching, green water ingress on the deck and slamming of FPSO ships, based on main ship design and wave parameters, are presented. The approximations were elaborated with the use of the linear regression method and theory of artificial neural networks for a very wide range of FPSO ship dimensions and hull forms. In the investigations ship operational conditions were limited to those occurring in real service of FPSO ships, described by means of the so called operational scenario. Such approach made it possible to reach simultaneously high approximation accuracy and simple structure of mathematical model.
Modelling of seakeeping qualities of open-top container carriers in the preliminary design phase
In this paper are presented problems of modelling seakeeping qualities of open-top container carriers in the preliminary design phase. Approximations of accelerations and occurrence rate of green water ingress to holds are presented in function of main ship design and wave parameters. The approximations have been elaborated by applying theory of artificial neural networks in the wide range of ship hull dimensions and forms, while ship motion and wave parameters have been limited to real operational conditions described by means of the so called operational scenario. Such approach has made it possible to reach high accuracy of approximation and simple structure of mathematical model simulatneously.
Approximation of the index for assessing ship sea-keeping performance on the basis of ship design parameters
This paper presents a new approach which makes it possible to take into account seakeeping qualities of ship in the preliminary stage of its design. The presented concept is based on representing ship's behaviour in waves by means of the so called operational effectiveness index. Presented values of the index were calculated for a broad range of design parameters. On this basis were elaborated analytical functions which approximate the index depending on ship design parameters. Also, example approximations of the index calculated by using artificial neural networks, are attached. The presented approach may find application to ship preliminary design problems as well as in ship service stage to assess sea-keeping performance of a ship before its departure to sea.
Application of artificial neural networks to approximation and identification of sea-keeping performance of a bulk carrier in ballast loading condition
This paper presents an application of artificial neural networks to approximation and identification of additional wave-generated resistance, slamming and internal forces depending on ship motion and wave parameters. The analysis was performed for a typical bulk carrier in ballast loading conditions. The investigations were carried out on the basis of ship response data calculated by means of exact numerical methods. Analytical functions presented in the form of artificial neural networks were analyzed with a view of their accuracy against standard values. Possible ways of application of the artificial neural networks were examined from the point of view of accuracy of approximation and identification of the assumed ship response parameters.
Determination of optimum hull form for passenger car ferry with regard to its sea-keeping qualities and additional resistance in waves
This paper presents a method which makes it possible to determine optimum hull form of passenger car ferry with regard to selected sea-keeping qualities and additional resistance in waves. In the first phase of investigations a hull form characterized by the highest qualities was selected from the list of similar ships. Next, its optimum dimension ratios were determined. Design criteria were formulated by using a method based on deterministic scenarios, but objective functions of partial targets were determined in the form of artificial neural networks. To select the best design variants elements of fuzzy logic were used, that made it possible a.o. to show merits of the design by means of linguistic variables. Such approach made it possible to find the best hull form and its dimensions from the point of view of all considered criteria simultaneously.
The article presents the mathematical function to calculate the added wave resistance transfer function for bulk carriers. Based on this function, the statistical mean added wave resistance generated by an irregular head wave with arbitrary statistical parameters can be forecasted. The input parameters are: waterplane area, waterplane coefficient, ship speed, and frequency of the regular wave. The model has been developed based on the theory of artificial neural networks. The presented function can be used in design analyses, and for planning shipping routes in situations when basic geometrical parameters of the hull are only available and not the full technical documentation. The article presents sample cases of use of this function to calculate the added wave resistance transfer function and the statistical mean added wave resistance. Another presented application refers to waterplane coefficient optimisation taking into account the added wave resistance at the stage of preliminary bulk carrier design.