Comparison of meta-modeling methodologies through the statistical-empirical prediction modeling of hydrodynamic bodies

Abstract

A methodology for directly establishing the forces and moments on a maneuvering body based on the instantaneous state of the vehicle is demonstrated. Both classical and modern Design of Experiments were used to develop experimental design regions consisting of different combinations of inflow conditions. Data was generated using computational fluid dynamic simulations which were performed on DARPA SUBOFF and the Virginia Tech ellipsoid model at the parameters prescribed by the designed experiments. Nonlinear polynomial regression modeling and artificial neural network modeling were used to develop prediction models for the normal and side force coefficients of both geometries with functional dependence on the inflow conditions. The prediction models were compared to published experimental data which showed excellent agreement within the experimental design region. The classical and modern approaches were also compared to each other and various strengths and applicability were illustrated. Nonlinear polynomial regression modeling and classical Design of Experiments proved to be very insightful by elucidating which inflow parameters and inflow parameter interactions were significant to the prediction model. Artificial neural network modeling coupled with modern Design of Experiments was shown to be more accurate, however, gave no insight to the underlying physical flow phenomena.