Ship design is related to several disciplines such as hydrostatic, resistance, propulsion and economic. The traditional ship design process only involves independent design optimization with some regression formulas within each discipline and there is no guarantee to achieve the optimum design. At the same time, it is crucial to improve the efficiency of modern ship design. Nowadays, the methods of computational fluid dynamics (CFD) has been brought into the ship design optimization. However, there are still some problems such as calculation precision and time consumption especially when CFD software is inlaid into the optimization procedure. Modeling is a far-ranging and all-around subject, and its precision directly affects the scientific decision in future. How to establish an accurate approximation model instead of the CFD calculation will be the key problem. The Support Vector Machines (SVM), a new general machine learning method based on the frame of statistical learning theory, may solve the problems in sample space and be an effective method of processing the non-liner classification and regression. The classical SVR has two parameters to control the errors. A new algorithm of Support Vector Regression proposed in this article has only one parameter to control the errors, adds b2/2 to the item of confidence interval at the same time, and adopts the Laplace loss function. It is named Single-parameter Lagrangian Support Vector Regression (SPL-SVR). This effective algorithm can improve the operation speed of program to a certain extent, and has better fitting precision. In practical design of ship, Design of Experiment (DOE) and the proposed support vector regression algorithm are applied to ship design optimization to construct statistical approximation model in this paper. The support vector regression algorithm approximates the optimization model and is updated during the optimization process to improve accuracy. The result indicates that the SPL-SVR method to establish approximate models can effectively solve complex engineering design optimization problem. Finally, some suggestions on the future improvements are proposed.
A novel method for the holistic, simulation driven ship design optimization under uncertainty in the big data era
