Comparison of aircraft weight obtained by using approximate methods and actual analysis. (a) As a function of engine thrust. (b) As a function of wing area.
NASA Lewis Research Center’s CometBoards Test Bed was used to create regression and neural network models for a High-Speed Civil Transport (HSCT) aircraft. Both approximation models that replaced the actual analysis tool predicted the aircraft response in a trivial computational effort. The models allow engineers to quickly study the effects of design variables on constraint and objective values for a given aircraft configuration. For example, an engineer can change the engine size by 1000 lb of thrust and quickly see how this change affects all the output values without rerunning the entire simulation. In addition, an engineer can change a constraint and use the approximation models to quickly reoptimize the configuration. Generating the neural network and the regression models is a time-consuming process, but this exercise has to be carried out only once. Furthermore, an automated process can reduce calculations substantially.
One issue that needs to be addressed is the generation of output for a given set of design variables. The analysis tools must be smart enough to respond completely to changes in design values. For example, a change in the overall pressure ratio of an engine will affect several behavior parameters besides an increase in the pressure. For example, the overall efficiency of the compressor will change, the cooling flow temperature will rise, more cooling flow will be required, and the compressor will increase in weight. These problems, however, can be overcome with more capable tools and a little planning.
Comparison of aircraft weight obtained by using approximate methods and actual analysis. (a) As a function of engine thrust. (b) As a function of wing area.
The figure shows how closely the neural network and regression techniques track the output value of aircraft gross weight from the actual analysis. Both approximation techniques have been shown to produce good agreement for all desired response parameters.
Lewis contacts: Dr. Surya N. Patnaik, (216) 433–5916, Surya.N.Patnaik@grc.nasa.gov; Dale A. Hopkins, (216) 433–3260, Dale.A.Hopkins@grc.nasa.gov; and Thomas M. Lavelle, (216) 977–7042, Thomas.M.Lavelle@grc.nasa.gov
Authors: Dr. Surya N. Patnaik, Dale A. Hopkins, and Thomas M. Lavelle
Headquarters program office: OAT
Programs/Projects: HSCT, AST, HSR
Next article
Last updated June 18, 1999, by Nancy.L.Obryan@nasa.gov
Responsible NASA Official:
Gynelle.C.Steele@nasa.gov
216-433-8258
Point of contact for NASA Glenn's Research & Technology reports:
Cynthia.L.Dreibelbis@nasa.gov
216-433-2912
SGT, Inc.
Web page curator:
Nancy.L.Obryan@nasa.gov
216-433-5793
Wyle Information Systems, LLC
