Satellite Fault Identification

TECH FOCUS AREAS: General Warfighting Requirements (GWR) TECHNOLOGY AREAS: Space Platform OBJECTIVE: Currently, for USSF satellites there is a team of >5 SMEs furiously monitoring the state of a satellite's health. Fault classification software plus already existing fault detection software would remove the need for constant monitoring. This would not only allow the operators to focus on the congested and contested manner of space but also mitigate faults in a satellite quickly and effectively. DESCRIPTION: For an operator to mitigate a satellite fault quickly and effectively, the fault's cause must be understood. This requirement is due to the fact many faults have similar effects on the satellite but completely different causes. For instance, a solar Coronal Mass Ejection (CME) looks similar to a developer's bug in the software and various types of cyber-attacks. All of these faults might require completely different mitigation steps. For a CME, one way to fix the satellite is a restart after the event, the developer's code fix should be uploaded, and the cyber-attack could require a variety of responses depending on the attacker and the severity of the attack. These events also might not exist in the same dataset if they exist at all [1,2]. Therefore, this classification must also work for unknown unknown events so that it can be prepared to interact with the dynamic environment of space. This topic's objective is to develop algorithms and code classifying a detected fault. The contractor will be given different satellite datasets either simulated or real on which to train. A separate dataset will be provided to prove out the algorithm. PHASE I: In Phase I, selected companies will conduct a comprehensive comparative assessment with trade-offs of various classification algorithms and approaches. Implementation complexity of candidate techniques and conduct trade-offs will be assessed with respect to impact on SWAP-C and operational suitability. Deliverables of this should include a trade study and appropriate analysis reporting. PHASE II: If selected for Phase II, companies will design, implement, integrate, and test the most promising and effective algorithm with ground software to classify detected satellite faults in near real time. Deliverables will include any relevant reporting analysis and software developed where appropriate. PHASE III DUAL USE APPLICATIONS: In cooperative efforts with one or more satellite software manufacturers and military satellite system developers, Phase III efforts would integrate the proposed algorithms with satellite software; demonstrate the algorithm running on board a satellite; and evaluate transition opportunities for utilization in approved Government civilian applications. NOTES: 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 proposed tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct questions to the Air Force SBIR/STTR Help Desk: usaf.team@afsbirsttr.us REFERENCES: 1. Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning.Springer, New York, NY, 2001.; 2. D. T. Magill. Optimal adaptive estimation of sampled stochastic processes. IEEE Transactions on Systems, Man and Cybernetics, AC-10:434 439, October 1965. KEYWORDS: Satellite Faults; fault classification