Prediction of submarine hydrodynamics using CFD-based calculations and RBF neural network

To explore the usage of CFD techniques into the optimization design process of submarine maneuverability, CFD-based calculations and RBF neural network were combined to predict the submarine hydrodynamics. The fullness of the nose and stern index was introduced to the geometric description of submarine axisymmetric hull, thus creating a five-parameter model for the hull geometry expression. A series of 30 similar hull bodies was adopted by the uniform design approach. For each of the models, 9 different drift angle cases were calculated, and 270 groups of data were achieved consisting of the longitudinal force, the lateral force and the yaw moment. To improve the efficiency and accuracy of the computation, automatic mesh and computation using the ANSYS ICEM CFD scripts and ANSYS FLUENT journal functions were used, as well as the drift sweep procedure. A RBF neural network was adopted and trained by the computation results to predict the hydrodynamics of other submarines. For the SUBOFF case, the hydrodynamics were predicted and compared with the CFD-based calculation results, the experimental results and literature values. The results agreed well with each other. It indicates that the method used in this paper is suitable for the practical application in engineering and has a better accuracy and higher efficiency.