Additive Repair of Fastener Holes by Cold Spray

The Chief of Naval Operations (OPNAV) has been responding to an increasing threat from peer competitorsÆ rapid development of aircraft, missiles, and ships. To support long-range operational concepts such as Distributed Maritime Operations and Navy Integrated Fire Control, OPNAV has committed to upgrading signals intelligence (SIGINT) collection and integrated fire control networks. The Navy is pioneering transformative netted solutions forĀextremely long-rangeĀcooperative engagement modes for next generation air defense and surface warfare. Mosaic proposesĀenhancements to the AEGIS combat system that provide operational prediction of track behavior and location using machine learning (ML) and artificial intelligence (AI) techniques. By leveraging surveillance historical data repositories, and applying æbig dataÆ AI/ML analysis techniques, the algorithms proposed herein will deliver a real-time, modular, and scalable solution that performs well even during gaps in surveillance coverage. In this Phase II, Mosaic will begin byĀretraining Phase I algorithmsĀusing operational surveillance and SIGINT sensor data. The team willĀiterate and hardenĀthe solution and use the results of Phase I development to prioritize/prepare code for scale and production deployment and ensure the models will generalize to environments they were not exposed to during the training. Third, work will beĀscaled upĀfor processing thousands of simultaneous tracks preparing the way for aĀdemonstrationĀof a Real-Time Simulation (RTS) Agent running in a land-based test site without impacting the production AEGIS configuration. This two-unit demonstration will take place in an AEGIS Virtual Twin (VTWIN) lab environment (e.g. IWSL or SAIL) and as part of an at-sea demo in a ship with VTWIN installed. MosaicÆs subcontractor, PMAT, Inc. previously used ONR funds to develop the Extensible Collaboration and Analytics Platform (X-CAP) to perform as a global, all-source information environment built on a scalable framework to provide national data to the tactical edge for improved battle space awareness, more effective combat identification, and long-range targeting. Through the Minotaur Family of Services (MFoS), X-CAP supports national-tactical integration, high side fusion, and combat systems integration. The Minotaur UI can be accessed by AEGIS combat system operators via the Minotaur Web service or trajectory prediction events can be provided to AEGIS for rendering in the existing AEGIS display system map. The use of X-CAP and MFoS will expedite that transition as both capabilities are fleet deployed at technology readiness level (TRL) 9. Mosaic has already developed and demonstrated a netted information architecture and foundational algorithms to performĀidentityĀandĀintentĀdetermination. Previous work provides a strong foundation for this Phase II; however, the innovation described in this proposal requires distinct tasks from those projects and has not been previously funded.