Title:
A methodology for ballistic missile defense systems analysis using nested neural networks

dc.contributor.advisor Mavris, Dimitri N.
dc.contributor.author Weaver, Brian Lee en_US
dc.contributor.committeeMember Biltgen, Patrick
dc.contributor.committeeMember Ender, Tommer
dc.contributor.department Aerospace Engineering en_US
dc.date.accessioned 2008-09-17T19:29:06Z
dc.date.available 2008-09-17T19:29:06Z
dc.date.issued 2008-07-10 en_US
dc.description.abstract The high costs and political tensions associated with Ballistic Missile Defense Systems (BMDS) has driven much of the testing and evaluation of BMDS to be performed through high fidelity Modeling and Simulation (M&S). In response, the M&S environments have become highly complex, extremely computationally intensive, and far too slow to be of use to systems engineers and high level decision makers. Regression models can be used to map the system characteristics to the metrics of interest, bringing about large quantities of data and allowing for real-time interaction with high-fidelity M&S environments, however the abundance of discontinuities and non-unique solutions makes the application of regression techniques hazardous. Due to these ambiguities, the transfer function from the characteristics to the metrics appears to have multiple solutions for a given set of inputs, which combined with the multiple inputs yielding the same set of outputs, causes troubles in creating a mapping. Due to the abundance of discontinuities, the existence of a neural network mapping from the system attributes to the performance metrics is not guaranteed, and if the mapping does exist, it requires a large amount of data to be for creating a regression model, making regression techniques less suitable to BMDS analysis. By employing Nested Neural Networks (NNNs), intermediate data can be associated with an ambiguous output which can allow for a regression model to be made. The addition of intermediate data incorporates more knowledge of the design space into the analysis. Nested neural networks divide the design space to form a piece-wise continuous function, which allows for the user to incorporate system knowledge into the surrogate modeling process while reducing the size of a data set required to form the regression model. This thesis defines nested neural networks along with methods and techniques for using NNNs to relieve the effects of discontinuities and non-unique solutions. To show the benefit of the approach, these techniques are applies them to a BMDS simulation. Case studies are performed to optimize the system configurations and assess robustness which could not be done without the regression models. en_US
dc.description.degree M.S. en_US
dc.identifier.uri http://hdl.handle.net/1853/24675
dc.publisher Georgia Institute of Technology en_US
dc.subject Neural network en_US
dc.subject Nested neural network en_US
dc.subject Ballistic missile defense en_US
dc.subject Non-unique en_US
dc.subject Regression en_US
dc.subject Surrogate modeling en_US
dc.subject BMDS analysis en_US
dc.subject.lcsh Ballistic missile defenses
dc.subject.lcsh Neural networks (Computer science)
dc.subject.lcsh Regression analysis
dc.subject.lcsh Approximation theory
dc.subject.lcsh Simulation methods
dc.title A methodology for ballistic missile defense systems analysis using nested neural networks en_US
dc.type Text
dc.type.genre Thesis
dspace.entity.type Publication
local.contributor.advisor Mavris, Dimitri N.
local.contributor.corporatename Daniel Guggenheim School of Aerospace Engineering
local.contributor.corporatename Aerospace Systems Design Laboratory (ASDL)
local.contributor.corporatename College of Engineering
local.relation.ispartofseries Master of Science in Aerospace Engineering
local.relation.ispartofseries Master of Science in Aerospace Engineering
relation.isAdvisorOfPublication d355c865-c3df-4bfe-8328-24541ea04f62
relation.isOrgUnitOfPublication a348b767-ea7e-4789-af1f-1f1d5925fb65
relation.isOrgUnitOfPublication a8736075-ffb0-4c28-aa40-2160181ead8c
relation.isOrgUnitOfPublication 7c022d60-21d5-497c-b552-95e489a06569
relation.isSeriesOfPublication 2fef2987-f871-4c1d-acfa-e642641793f5
relation.isSeriesOfPublication 09844fbb-b7d9-45e2-95de-849e434a6abc
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
weaver_brian_l_200808_mast.pdf
Size:
3.44 MB
Format:
Adobe Portable Document Format
Description: