DIGITAL ENGINEERING- Artificial Intelligence/Machine Learning (AI/ML) Hull Mechanical & Electrical Controls

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Trusted AI and Autonomy; Integrated Sensing and Cyber 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: Develop an Artificial Intelligence/Machine Learning (AI/ML) engine capable of improving alignment, operation, recoverability, and fault detection for Hull, Mechanical, and Electrical (HM&E) control systems. DESCRIPTION: An autonomous system that deconflicts, decomposes, and triages tasks in HM&E control systems is necessary in multi-enclave ships when inter-enclave commands secured by boundary defense and intrusion detection systems are required. While a ship is underway, a self-improving rules system for de-conflicting and prioritization can improve long-term operations and sustainment of Navy surface combatants, but software rules that codify normal inter-system operations equivalent to teams of sailors currently have little precedent, either in commercial or Navy domains. The Ship Domain Controller (SDC) is a government-owned monitoring, controlling, and integrating system currently fielded on Navy combatants for ship control systems. Prior work on autonomous integration systems such as SDC are tightly integrated with legacy surface combatant platforms and have no ability to apply prioritization and de-confliction operations to HM&E control systems. The Navy seeks a system capable of prioritizing, de-conflicting, and decomposing tasks into control actions. Command messages must have cyber-secure message authentication from the system (refer to NIST 800-82 for details on the requirement and NIST-800-52, NIST 800-56, NIST 80-57, and FIPS 140-2 for guidance on implementation). Commands should be distinguishable from operator commands. An advanced AI algorithm should be developed and trained using sensor data taken from training sets and representative signal databases that will be supplied to Phase I awardees by the Navy. Autonomous controls will greatly reduce cognitive burden on operators in the monitoring, operation, and actuation of engineering plants plus the detection, diagnosing, troubleshooting, and recovery of machinery casualties. This enables reductions in manning and provides more timely response to and recovery from engineering plant casualties and their impacts, improving the robustness of the plants and overall survivability of the ship. PHASE I: Develop a concept of an advanced AI algorithm trained using sensor data taken from training sets and representative signal databases. Key technologies, commercial software, and libraries should be identified and demonstrated in a simulated environment. Developments during Phase I will identify further training sets desired to mature the effort in Phase II. The Phase I Option, if exercised, will include the initial design specifications and capabilities description to build a prototype solution in Phase II. PHASE II: Develop and deliver a mature AI/ML prototype that meets all requirements in the Description, with a final demonstration in a relevant environment with other Navy-owned HM&E control systems. Documentation and on-boarding guides will be furnished for other systems to interface with the AI engine. PHASE III DUAL USE APPLICATIONS: Support Navy in transitioning the technology for Government use. Develop deployable designs with specific interface and storage requirements for the control systems. Control systems across manufacturing and process industries as well as in DOD can benefit from incorporating AI/ML decision making technologies; manpower reduction, operational efficiencies, troubleshooting and prognostics. REFERENCES: 1. 1. Moacdieh, Nadine Marie, and Sarter, Nadine. The Effects of Data Density, Display Organization, and Stress on Search Performance: An Eye Tracking Study of Clutter. IEEE Transactions on Human-Machine Systems 47, December 2017: 886-895. https://ieeexplore.ieee.org/document/7971994 2. 2. Yang, Canjun, Zhu, Yuanchao, and Chen, Yanhu. A Review of Human Machine Cooperation in the Robotics Domain. IEEE Transactions on Human-Machine Systems 52, December 2021: 12-25. https://ieeexplore.ieee.org/document/9653727 KEYWORDS: Machine learning; Artificial Intelligence; Hull, Mechanical, and Electrical; Controls Automation; Ship Domain Controller; Boundary Defense and Intrusion Systems