NTRS - NASA Technical Reports Server

Back to Results
Surrogate Modeling of High-Fidelity Fracture Simulations for Real-Time Residual Strength PredictionsA surrogate model methodology is described for predicting, during flight, the residual strength of aircraft structures that sustain discrete-source damage. Starting with design of experiment, an artificial neural network is developed that takes as input discrete-source damage parameters and outputs a prediction of the structural residual strength. Target residual strength values used to train the artificial neural network are derived from 3D finite element-based fracture simulations. Two ductile fracture simulations are presented to show that crack growth and residual strength are determined more accurately in discrete-source damage cases by using an elastic-plastic fracture framework rather than a linear-elastic fracture mechanics-based method. Improving accuracy of the residual strength training data does, in turn, improve accuracy of the surrogate model. When combined, the surrogate model methodology and high fidelity fracture simulation framework provide useful tools for adaptive flight technology.
Document ID
Document Type
Technical Memorandum (TM)
Spear, Ashley D.
(Cornell Univ. Ithaca, NY, United States)
Priest, Amanda R.
(Cornell Univ. Ithaca, NY, United States)
Veilleux, Michael G.
(Cornell Univ. Ithaca, NY, United States)
Ingraffea, Anthony R.
(Cornell Univ. Ithaca, NY, United States)
Hochhalter, Jacob D.
(NASA Langley Research Center Hampton, VA, United States)
Date Acquired
August 25, 2013
Publication Date
January 1, 2011
Subject Category
Metals And Metallic Materials
Report/Patent Number
Funding Number(s)
WBS: WBS 284848.
Distribution Limits
Public Use Permitted.
No Preview Available