Skip navigation links

ContentsAuthors & ContactsMore R&T ReportsSearch NASAGlenn HomeNASA Home

Cascade Optimization Strategy With Neural Network and Regression Approximations Demonstrated on a Preliminary Aircraft Engine Design

A preliminary aircraft engine design methodology is being developed that utilizes a cascade optimization strategy together with neural network and regression approximation methods. The cascade strategy employs different optimization algorithms in a specified sequence. The neural network and regression methods are used to approximate solutions obtained from the NASA Engine Performance Program (NEPP), which implements engine thermodynamic cycle and performance analysis models. The new methodology is proving to be more robust and computationally efficient than the conventional optimization approach of using a single optimization algorithm with direct reanalysis. The methodology has been demonstrated on a preliminary design problem for a novel subsonic turbofan engine concept that incorporates a wave rotor as a cycle-topping device. Computations of maximum thrust were obtained for a specific design point in the engine mission profile. The results (depicted in the figure) show a significant improvement in the maximum thrust obtained using the new methodology in comparison to benchmark solutions obtained using NEPP in a manual design mode.

bar chart of normalized thrust (y-axis) versus type of solution (x-axis); results given for benchmark solution (66,941 lb), NLPQ regression (infeasible 75,232 lb), NLPQ neural network (infeasible 63,291 lb), cascade 1 (FD-SUMT-NLPQ) regression (66,893 lb), cascade 1 neural network (66,911 lb), cascade 2 (NLPQ-FD-NLPQ) regression (66,897 lb), cascade 2 neural network (66,890 lb), and cascade 3 (NLPQ (NN)-FD (regression)-NLPQ (NEPP) (66,901 lb)

Optimum thrust for a subsonic wave-rotor-topped engine for the sixth operating point.

Optimization method

Description

Benchmark solution

Average thrust obtained using 10 different initial designs.

NLPQ (Regression)

Thrust obtained using NLPQ and regression approximation.

NLPQ (NN)

Thrust obtained using the quadratic programming algorithm (NLPQ) and the neural network (NN) approximation.

Cascade 1a (Regression)

Thrust obtained using the Cascade 1 strategy and the regression approximation.

Cascade 1a (NN)

Thrust obtained using the Cascade 1 strategy and the neural network approximation.

Cascade 2 (Regression)

Thrust obtained using the Cascade 2 strategy and the regression approximation.

Cascade 2 (NN)

Thrust obtained using the Cascade 2 strategy (NLPQ-FD-NLPQ) and the neural network approximation.

Cascade 3 (Interspersed)

Thrust obtained using the interspersed cascade strategy (NLPQ with NN, FD with regression, and NLPQ with the NASA Engine Performance Program (NEPP) reanalysis).

aThe Cascade 1 strategy uses three algorithms: the Method of Feasible Directions (FD) followed by the Sequential Unconstrained Minimization Technique (SUMT) and the quadratic programming algorithm (NLPQ).

Glenn contact: Dale A. Hopkins, (216) 433–3260, Dale.A.Hopkins@grc.nasa.gov

Authors: Dale A. Hopkins and Dr. Surya N. Patnaik

Headquarters program office: OAST

Programs/Projects: Propulsion System R&T

next page Next article

previous page Previous article

Last updated April 24, 2000, 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

NASA Web Privacy Policy and Important Notices