GPU Accelerated Large Eddy Simulation for Low Pressure Turbine Design

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Advanced Computing and Software;Directed Energy (DE) The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. OBJECTIVE: The objective of this topic is to demonstrate a capability to define, capture, organize, label, and reason over the data that is generated by end-user devices and servers in the Tactical Assault Kit (TAK) ecosystem for use by machine learning model development, re-training, fine tuning, and federated learning of existing models, or consumption by AFRL ML tools. DESCRIPTION: The TAK ecosystem currently has a wealth of sensor data, usage data, and analytics that is under-utilized for artificial intelligence/machine learning (AI/ML). Leverage general-purpose machine learning (ML) tools (StreamlinedML/MISTK, WingmanAI), Android sensor hubs (TAK-ML sensor framework, Foresight and Sensor Manager), and semantic network/knowledge graphing tools (KnowML, FuelAI) to extend the TAK-ML framework. Accept analytics back from any frameworks, models, or plugins developed for further refinement. Use of digital engineering tools to at a minimum define open application programming interfaces (APIs) and where applicable build reference implementations is preferred. PHASE I: This topic is intended for technology proven ready to move directly into a Phase II. Therefore, a Phase I award is not required. The offeror is required to provide detail and documentation in the Direct to Phase II proposal which demonstrates accomplishment of a Phase I-type effort, including experience with extension, modification, or creation of enterprise machine learning life cycle management toolkits for knowledge graphic, data curation, and related machine learning tasks. PHASE II: Phase II objectives include the development of technologies to collect, reason over, and harness data from the TAK ecosystem for use in machine learning tasks, demonstrating integrations with (and extensions of) AFRL toolkits such as TAK-ML, StreamlinedML/MISTK, and KnowML to apply broader Air Force machine learning development to the tactical edge. PHASE III DUAL USE APPLICATIONS: Successful Phase II technology effort reaching suitable TRL (6-7) will be candidates for additional Phase III development, including potential for transition to the Tactical Assault Kit (TAK) ecosystem in partnership with the TAK Product Center (TPC) or to other AFRL programs developing next generation AI/ML capabilities. REFERENCES: 1. https://github.com/raytheonbbn/tak-ml; 2. https://dl.acm.org/doi/abs/10.1109/MILCOM52596.2021.9652909; 3. https://mistkml.github.io/; 4. https://tak.gov; 5. https://civtak.org; KEYWORDS: semantic web; knowledge graphing; mobile machine learning; end-user devices; data analytics; ATAK