Block construction method is generally used in modern shipyards. In this method, interim products are built by assembling parts, and the ship is built from these interim products. This process can be referred as "Assembling Hierarchy" in this paper. In order to construct the ship effectively, an appropriate Assembling Hierarchy plan which considering the configurations of interim products is required. So in this paper, an optimization system of ship Assembling Hierarchy using Genetic Algorithms (GA) and Product Model is discussed.In order to realize the optimization using GA, it is necessary to define the chromosomes and to examine the GA operations. Therefore, Joint Hierarchy Chromosome is newly introduced. Joint hierarchy chromosome is genotype or encoded solution of Assembling Hierarchy. In this chromosome, the level of Assembling Hierarchy on each joint is set as design variable. By using this chromosome, various plans of ship Assembling Hierarchy can be generated. Effective GA operations such as selection, crossover and mutation are also shown. Moreover, proposed system is integrated with Product Model. Therefore, fitness with penalty of the plan is calculated by the use of Product Model data.Finally, an example of the optimization is shown in the paper to confirm the validity of the developed method.

This paper presents a practical method for the structural optimization of a tanker with a double hull and double bottom system by the Sequential Unconstrained Minimization Technique (SUMT) and the Multiplier Method. The weight of one tank hold length is taken as the objective function and the scantlings of the transverse and longitudinal members in the midship segment are chosen as the design variables. A lot of constraints such as plastic collapse of ship hull and of transverse frames, plastic collapse and buckling strength of longitudinal stiffeners and of plates, and buckling strength of transverse strut under the hogging and sagging loading conditions are considered. The minimum values of design variables are also included in the constraints. The focuses are attached on the variation of the optimized weight with the number of transverse ring spaces and the comparison between the SUMT method and the multiplier method on condition that the effective width of attached plates in transverse members is taken into consideration. A numerical example with 41 design variables and 118 constraints has been made and the results are presented.

No abstract

At the design stage of the large-scale steel structure, displacement and stress are generally analyzed by using the FEM. At the initial design stage, it is required for evaluating conditions of numerous design candidates. Therefore, it is not efficient to use FEM with fine mesh for analyzing the strength of structures in spite of requiring accuracy in the evaluation.In this paper, Neural Network System is developed for predicting displacement and stress based on a coarse mesh with the same accuracy of fine mesh. It is able to predict accurate displacement and stress at stiffened plate using FEM analytical results with coarse mesh as input factors for Neural Network System. In order to improve the approximation accuracy of Neural Network System, Multiple linear regression method is introduced for selecting input factors for a Neural Network System. This technique improves the accuracy of Neural Network System and reduce manpower used for structure design. The proposed Neural Network System is able to predict displacement and stress in spite of changing the load, plate thickness, and the number of stiffeners.