Real-Time Simulation Based Design Part II: Changes in Hull Geometry

Abstract

As a second step, and a critical milestone, in the development of a new simulation based design (SBD) tool based on recursive neural network (RNN) technologies the capability to change hull geometries and compute in real-time the new vehicle dynamics has been tested. Previously, this approach was successfully demonstrated for design changes on the ONR Body 1 submarine appendages (sternplane and rudder). The advantages of this RNN based tool are that simulation based design can be performed in a real-time nonlinear simulation (RNS) environment, and this approach enables the fusion of experimental data, when available, with steady Reynolds Averaged Navier-Stokes (RANS) solutions. Building upon the previous work done using RNNs to support submarine simulation based design, the focus of this paper is on the extension of these RNN based approaches, and in particular for the design and modification of hull shape and size, including the computation of non-symmetric hull shapes. As in the previous SBD work on the appendages, a parent training data set for a particular vehicle was used to train an RNN to model how input forces and moments lead to particular output motions. Design changes to the vehicle were then implemented by changing the input force and moment database. As previously shown, appendages can be changed directly by specifying a new geometry and/or lift coefficient. As described herein, the hull geometry can be modified either through the use of other empirical data and/or through the use of steady RANS solutions. The new force and moment database for the hull and the new geometry are used as the input into the RNS based design code to determine the design change impact on vehicle maneuvering. Since only the input force and moment database is changed, no re-training of the RNN is required. As such, the new design simulations can be made in real-time, and the design cycle can, in theory, be shortened significantly. With the results for the hull geometry changes the full utility of this approach can now be defined, and bounds placed on the use of RNN based SBD approaches. This approach resolves the main limitation in RNN technology, namely that it was difficult or impossible to design vehicles using this technology. Now, RNNs can be used not only for vehicle design, but also to determine the result of the design changes in real-time.