You are here

Autonomous Operations Technologies for Ground and Launch Systems (SBIR)

Award Information
Agency: National Aeronautics and Space Administration
Branch: N/A
Contract: 80NSSC22PA942
Agency Tracking Number: 222523
Amount: $149,993.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: H10
Solicitation Number: SBIR_22_P1
Timeline
Solicitation Year: 2022
Award Year: 2022
Award Start Date (Proposal Award Date): 2022-07-21
Award End Date (Contract End Date): 2023-01-25
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
 Francisco Maldonado
 (805) 582-0582
 fmald@americangnc.com
Business Contact
 Emily Melgarejo
Phone: (805) 582-0582
Email: emelgarejo@americangnc.com
Research Institution
N/A
Abstract

To support NASA#39;s Kennedy Space Center (KSC) in the generation of innovative autonomous operations technologies (AOT) for ground and launch systems, American GNC Corporation (AGNC) is proposing the ldquo;Semiautonomous Anomaly Monitoring and Early Detection (SAMY)rdquo; System to advance NASA operations and maintenance (Oamp;M) infrastructure while increasing ground systems availability to support mission operations. Typical health monitoring systems focus to Failure Detection and Identification (FDI) of fully developed and known fault conditions. SAMY goes beyond this traditional approach, where in addition to FDI the SAMY system focus to: (a) detecting newly emerging health behaviors that could correspond to incipient faults; (b) tracking the fault growth process; and (c) identifying system changes that may correspond to system deterioration to deeply understand and assess the availability status of NASA ground systems. Based on these capabilities Phase I address a comprehensive design of the anomaly detection and prognostics framework (in addition to FDI), which is embedded within cutting edge sensor network. Core technologies are: (1) approximate bayes discriminant by Multilayer Perceptron for anomaly analysis and prognostics; (2) AGNC-LaTechrsquo;s Variogram for change detection; (3) incremental learning based on AGNCrsquo;s eCLE; (4) health monitoring by Deep Neural Network (DNN) with optimized footprint for integration within hardware platforms with minimized Size, Weight, and Power Consumption (SWaP); (5) top layer with ensemble of reasoning applications; and (6) smart sensor network based on cutting edge ISA100 technology and Zigbee. Successful completion of Phase I will result in the implementation of an innovative smart sensor network with embedded incremental learning system for detection of anomalies and new emerging health behaviors to better understand operational status in NASA ground systems. Phase II is expanded this foundation for an enterprise implementation.

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

US Flag An Official Website of the United States Government