Optimization of a Transonic Turbine Airfoil Using Artificial Intelligence, CFD and Cascade Testing

Abstract

A transonic turbine airfoil design is optimized using an artificial intelligence engineering design shell coupled with an inviscid, adaptive grid, CFD solver. The objective of the optimization is to minimize the downstream static pressure variation resulting from the trailing edge shock structure. Cascade test results verify the analytical predictions. Techniques are described which were used to couple the optimization shell to the 2-D turbine airfoil shape to allow the search for optimal designs and indicate the quality of those designs. The emphasis of the discussion is upon the application of these techniques rather than the physical details of the resulting blade design.