Redesigning Gas-Generator Turbines for Improved Unsteady Aerodynamic Performance Using Neural Networks

Abstract

A recently developed neural network-based aerodynamic design procedure is used in the redesign of a gasgenerator turbine stage to improve its unsteady aerodynamic performance. The redesign procedure used incorporatestheadvantagesofbothtraditionalresponse-surfacemethodologyandneuralnetworksbyemployingastrategy called parameter-based partitioning ofthedesign space.Starting from thereferencedesign, a sequenceofresponse surfaces based on both neural networks and polynomial e ts is constructed to traverse the design space in search of an optimal solution that exhibits improved unsteady performance. The procedure combines the power of neural networks and the economy of low-order polynomials (in terms of number of simulations required and network training requirements ). A time-accurate, two-dimensional, Navier ‐Stokes solver is used to evaluate the various intermediate designs and provide inputs to the optimization procedure. The procedure yields a modie ed design that improves theaerodynamicperformancethrough small changesto thereferencedesign geometry. Theseresults demonstrate the capabilities of the neural network-based design procedure and also show the advantages of including high-e delity unsteady simulationsthatcapturetherelevante owphysicsin thedesignoptimization process.