You are here

Semiautonomous Anomaly Monitoring and Early Detection (SAMY) System

Award Information
Agency: National Aeronautics and Space Administration
Branch: N/A
Contract: 80NSSC23CA069
Agency Tracking Number: 222523
Amount: $849,969.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: H10
Solicitation Number: SBIR_22_P2
Solicitation Year: 2022
Award Year: 2023
Award Start Date (Proposal Award Date): 2023-06-01
Award End Date (Contract End Date): 2025-05-31
Small Business Information
888 Easy Street
Simi Valley, CA 93065-1812
United States
DUNS: 611466855
HUBZone Owned: No
Woman Owned: Yes
Socially and Economically Disadvantaged: Yes
Principal Investigator
 Stephen Oonk
 (805) 582-0582
Business Contact
 Emily Melgarejo
Phone: (805) 582-0582
Research Institution

NASA Ames Research Center (ARC)#39;s innovative autonomous operations technologies (AOT) for ground and launch systems require minimized or even eliminated human iteration/intervention, and presence due to hazardous operational environments. Towards this goal, American GNC Corporation (AGNC) and The University of Texas at Arlington (UTA) are proposing the quot;Semiautonomous Anomaly Monitoring and Early Detection (SAMY)quot; System to advance NASA#39;s operations and maintenance (Oamp;M) infrastructure while increasing ground system availability to support mission operations. The SAMY system is to provide innovative Prognostics and Health Management (PHM) technology for planetary or lunar surface-based infrastructure that are related to the preparation of launch vehicles and payloads for flight.nbsp; SAMY can also improve NASA#39;s Stennis Space Center (SSC) test stand infrastructure by taking into account earth applications. The system builds upon: (i) automated anomaly detection, analysis, and characterization (ADAC) to identify incipient fault conditions and benign new operational conditions; (ii) generalized prognostic methodology based on optimized Multilayer Perceptron (MLP) discriminant; and (iii) suite of cutting edge algorithms operating collaboratively, including semiautomated incremental learning, selected deep learning paradigms, and inference methods for both Fault Detection and Identification (FDI) and guidance in maintenance operations.nbsp;Phase II design constraints include: (a) developing a sound framework that can handle with concept drift and structured data (e.g., multi-source, distributed, and heterogenous); (b) automated new knowledge assimilation once that change is detected and found a new condition; (c) developing a generalized prognostics scheme to provide Remaining Useful Life estimations; (d) blending strengths of advanced machine learning paradigms and achieving collaborative operation while for Prognostics and Health Management system; and (e) thorough Vamp;V

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government