Electronic Warfare Asset Allocation with Human-Swarm Interaction
Finding the optimal placement of receiving assets among transmitting targets in a three-dimensional (3D) space is a complex and dynamic problem that is solved in this work. The placement of assets in R 6 to optimize the best coverage of transmitting targets requires the placement in 3D-spatiality, center frequency assignment, and antenna azimuth and elevation orientation, with respect to power coverage at the receiver without overloading the feed-horn, maintaining sucient power sensitivity levels, and maintaining terrain constraints. Further complexities result from the human-user having necessary and time-constrained knowledge to real-world conditions unknown to the problem space, such as enemy positions or special targets, resulting in the requirement of the user to interact with the solution convergence in some fashion. Particle Swarm Optimization (PSO) approaches this problem with accurate and rapid approximation to the electronic warfare asset allocation problem (EWAAP) with near-real-time solution convergence using a linear combination of weighted components for tness comparison and particles representative of asset con- gurations. Finally, optimizing the weights for the tness function requires the use of unsupervised machine learning techniques to reduce the complexity of assigning a tness function using a Meta-PSO. The result of this work implements a more realistic asset allocation problem with directional antenna and complex terrain constraints that is able to converge on a solution on average in 488.7167 ± 15.6580 ms and has a standard deviation of 15.3901 for asset positions across solutions.
Christopher, Purdue University.
Computer Engineering|Artificial intelligence
Off-Campus Purdue Users:
To access this dissertation, please log in to our