DADTMA Gen3 - Distributed Acquisition Digital Twin Maintenance Architecture

Digital twins can be imagined as virtual, continuously-learning digital representations of physical assets. Such simulations have the potential to marry virtual and physical understanding of assets such that analog data from the physical product and its surrounding sustainment ecosystem is converted into digital data that is stored, analyzed, modeled, and learned by artificial neural networks (NNs) and other automation algorithms. When implemented as a big-data relational database, this framework allows prediction, trending, query, and analysis of the digital twin model to an extent that would be impossible on the actual product alone. FTL's “DADTMA” (Distributed Acquisition Digital Twin Maintenance Ecosystem) is a comprehensive architecture for curating a Machine Learning (ML) driven database of any product to perceive current condition, simulate possible performance scenarios, and predict impending failures. DADTMA enables novel database technology that enables data captured on the depot floor to automate data collection, project future outcomes, and provide profound situational awareness across a fleet of assets. This results in a physical-virtual-physical ecosystem that leads to improved mission readiness of Naval aviation products.