Please use this identifier to cite or link to this item:
Title: Leverage Artificial Intelligence to Learn, Optimize, and Wargame (LAILOW) for Navy Ships
Authors: Ying Zhao, Gabe Mata
Erik Hemberg, Una May O'Reillu
Nate Derbinsky, Bruce Cormany
Joy Allen, Andrew Haley
Adam Hilliard
Keywords: Artificial Intelligence
Navy Ships
Issue Date: 10-May-2021
Publisher: Acquisition Research Program
Citation: Published--Unlimited Distribution
Series/Report no.: Acquisition Management;SYM-AM-21-089
Abstract: Navy ships are complex enterprises comprised of multiple organizations that must interact smoothly and interface externally without threats to efficiency and combat-readiness. As logistical challenges increase and technology pushes response times, it is critical to introduce state of the art computational methods for analyzing the interlocked systems and training for different events. To address these challenges in this context, we introduce a framework called LAILOW: learn, optimize, and wargame. LAILOW exploits data arising from multiple sources in a complex enterprise by offering data mining, machine learning, and predictive algorithms that can be used for analysis and discovery of patterns, rules, and anomalies. LAILOW’s output can then be used to optimize business processes and course of actions. We show three use cases of using the of LAILOW framework. We show the whole LAILOW framework to search for vulnerability of a major Marine equipment’s maintenance and supply system for difficult tests and evolve resilience and novel solutions accordingly. We show using of lexical link analysis (LLA) as part of LAILOW to improve the prediction accuracy of probability of failure of critical Navy Ship parts, related to C4I systems, for NAVWARSYSCOM’s Predictive Risk Sparing Matrix (PRiSM) product. We also show the comparison of LLA prioritizing items in the Financially Restricted Work Que (FRWQ) with the baseline calculation.
Description: Acquisition Management / Defense Acquisition Community Contributor
Appears in Collections:Annual Acquisition Research Symposium Proceedings & Presentations

Files in This Item:
File Description SizeFormat 
SYM-AM-21-089.pdf1.57 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.