In this research effort, GTD Unlimited will develop a toolset that leverages machine learning and analytics to analyze E-2Ds system maintenance with Automated Logistics Environment (ALE) data collected across the fleet to design and develop improved maintenance procedures that will improve readiness. GTD will determine key performance metrics of the platform that are of value to the maintainer, IPT, and the enterprise (Feature Extraction); implement algorithms to facilitate Condition Based Maintenance (CBM), demonstrate the feasibility of a toolset to analyze ALE data with a Graphical User Interface (GUI); and generate prototype plans for Phase II (Phase II plan).
Benefit: This research will result in a user-friendly software toolset and strategy for condition-based maintenance. The machine condition monitoring market is expected to grow from $2.38B in 2018 to $3.5B by 2024. While the Navys E-2D is the primary focus for the toolset, GTD has already found a need for this capability among Army aerial platforms. This toolset has the potential to be used across the aircraft industry as well as large installations such as oil platforms, power plants, ships, and other infrastructure.
Keywords: Prognostics, Prognostics, maintenance,, CBM, GUI, Machine Learning
