John Gallagher (Advisor), Michael Raymer (Committee Member), Mateen Rizki (Committee Member)
Master of Science in Computer Engineering (MSCE)
This thesis investigates the use of an artificial neural network (ANN), in particular a Multi-Layer Perceptron (MLP), to perform function approximation on truth data representing a weapon engagement zone's (WEZ) maximum launch range. The WEZ of an air-to-air missile represents the boundaries and zones of effectiveness for a one-vs-one air-to-air combat engagement . The intent is for the network to fuse table lookup and interpolation functionality into a physically compact and computationally efficient package, while improving approximation accuracy over conventional methods. Data was collected from simulated firings of a notional air-to-air missile model and used to train a two layer perceptron using the Bayesian Regularization training algorithm. The resulting best network was able to improve approximation accuracy and reduce the amount of truth data needed. With basic feasibility established, future efforts can be focused on more comprehensive comparisons with existing methods and deployment within practical models.
Department or Program
Department of Computer Science and Engineering
Year Degree Awarded
Copyright 2011, all rights reserved. This open access ETD is published by Wright State University and OhioLINK.