Artificial neural network-based streamline tracing strategy applied to hypersonic waverider design

Abstract

Streamline tracing in hypersonic flows is essential for designing a high-performance waverider and intake. Conventionally, the streamline equations are solved after obtaining the velocity field over a basic flow field from simplified flow differential equations or three-dimensional computational fluid dynamics. The hypersonic waverider shape is generated by repeatedly applying the streamline tracing approach along several planes. This approach is computationally expensive for iterative waverider optimization. We provide a novel strategy where an Artificial Neural Network (ANN) is trained to directly predict the streamlines without solving the differential equations. We consider the standard simple cone-derived waverider using Taylor–Maccoll equations for the conical flow field as a template for the study. First, the streamlines from the shock are solved for a wide range of cone angle and Mach number conditions resulting in an extensive database. The streamlines are parameterized by a third-order polynomial, and an ANN is trained to predict the coefficients of the polynomial for arbitrary inputs of Mach number, cone angle, and streamline originating locations. We apply this strategy to design a cone-derived waverider and compare the geometry obtained with the standard conical waverider design method and the simplified waverider design method. The ANN technique is highly accurate, with a difference of 0.68% from the standard method in the coordinates of the waverider. The performance of the three waveriders is compared using Reynolds averaged Navier–Stokes simulations. The ANN-derived waverider does not indicate severe flow spillage at the leading edge. The new ANN-based approach is 20 times faster than the standard method.