The design of aerodynamic components of aircraft, such as wings or engines, involves a process of obtaining the most optimal component shape that can deliver the desired level of component performance, subject to various constraints, e.g., total weight or cost, that the component must satisfy. Aerodynamic design can thus be formulated as an optimization problem that involves the minimization of an objective function subject to constraints.
A new aerodynamic design optimization procedure based on neural networks and response surface methodology (RSM) incorporates the advantages of both traditional RSM and neural networks. The procedure uses a strategy, denoted parameter-based partitioning of the design space, to construct a sequence of response surfaces based on both neural networks and polynomial fits to traverse the design space in search of the optimal solution.
Some desirable characteristics of the new design optimization procedure include the ability to handle a variety of design objectives, easily impose constraints, and incorporate design guidelines and rules of thumb. It provides an infrastructure for variable fidelity analysis and reduces the cost of computation by using less-expensive, lower fidelity simulations in the early stages of the design evolution. The initial or starting design can be far from optimal. The procedure is easy and economical to use in large-dimensional design space and can be used to perform design tradeoff studies rapidly. Designs involving multiple disciplines can also be optimized.
Some practical applications of the design procedure that have demonstrated some of its capabilities include the inverse design of an optimal turbine airfoil starting from a generic shape and the redesign of transonic turbines to improve their unsteady aerodynamic characteristics.
In one practical application, the procedure was used to reconstruct the shape of a turbine airfoil given a desired pressure distribution and some relevant flow and geometry parameters. The shape of the airfoil was not known beforehand. Instead, it was evolved from a simple curved section of nearly uniform thickness. The evolved optimal airfoil closely matched the shape of the original airfoil that was used to obtain the pressure distribution. The progression of the design is depicted in the figure. The airfoil shape evolution is shown on the left, while the corresponding pressure distributions and the target pressure distribution are shown on the right. The surface pressures approach the target distribution as the design progresses until the optimal airfoil shown at the bottom has a pressure distribution that matches closely the target.
The technology developed and implemented in the neural-network-based design optimization procedure offers a unique capability that can be used in other aerospace applications such as external aerodynamics and multidisciplinary optimization, and has potential applications beyond aerospace design.
This work was done by Man Mohan Rai and Nateri K. Madavan of Ames Research Center. For further information, access the Technical Support Package (TSP) free on-line at www.techbriefs.com/tsp under the Information Sciences category.
This invention is owned by NASA, and a patent application has been filed. Inquiries concerning nonexclusive or exclusive license for its commercial development should be addressed to
the Patent Counsel
Ames Research Center
Refer to ARC-14281.