NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
A Subsonic Aircraft Design Optimization With Neural Network and Regression ApproximatorsThe Flight-Optimization-System (FLOPS) code encountered difficulty in analyzing a subsonic aircraft. The limitation made the design optimization problematic. The deficiencies have been alleviated through use of neural network and regression approximations. The insight gained from using the approximators is discussed in this paper. The FLOPS code is reviewed. Analysis models are developed and validated for each approximator. The regression method appears to hug the data points, while the neural network approximation follows a mean path. For an analysis cycle, the approximate model required milliseconds of central processing unit (CPU) time versus seconds by the FLOPS code. Performance of the approximators was satisfactory for aircraft analysis. A design optimization capability has been created by coupling the derived analyzers to the optimization test bed CometBoards. The approximators were efficient reanalysis tools in the aircraft design optimization. Instability encountered in the FLOPS analyzer was eliminated. The convergence characteristics were improved for the design optimization. The CPU time required to calculate the optimum solution, measured in hours with the FLOPS code was reduced to minutes with the neural network approximation and to seconds with the regression method. Generation of the approximators required the manipulation of a very large quantity of data. Design sensitivity with respect to the bounds of aircraft constraints is easily generated.
Document ID
20040110838
Acquisition Source
Glenn Research Center
Document Type
Technical Memorandum (TM)
Authors
Patnaik, Surya N.
(Ohio Aerospace Inst. Brook Park, OH, United States)
Coroneos, Rula M.
(NASA Glenn Research Center Cleveland, OH, United States)
Guptill, James D.
(NASA Glenn Research Center Cleveland, OH, United States)
Hopkins, Dale A.
(NASA Glenn Research Center Cleveland, OH, United States)
Haller, William J.
(NASA Glenn Research Center Cleveland, OH, United States)
Date Acquired
September 7, 2013
Publication Date
August 1, 2004
Subject Category
Aircraft Design, Testing And Performance
Report/Patent Number
AIAA Paper 2004-4606
NASA/TM-2004-213059
E-14504
Meeting Information
Meeting: 10th Multidisciplinary Analysis and Optimization Conference
Location: Albany, NY
Country: United States
Start Date: August 30, 2004
End Date: September 1, 2004
Sponsors: American Inst. of Aeronautics and Astronautics
Funding Number(s)
WBS: WBS 22-708-24-05
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.
No Preview Available