FAST PHM™ - An Integrated Process and False Alarm Mitigation Design Tool for PHM

Award Information
Agency: Department of Defense
Branch: Navy
Contract: N68335-07-C-0097
Agency Tracking Number: N051-028-0286
Amount: $749,941.00
Phase: Phase II
Program: SBIR
Awards Year: 2006
Solicitation Year: 2005
Solicitation Topic Code: N05-028
Solicitation Number: 2005.1
Small Business Information
200 Canal View Blvd, Ste 300, Rochester, NY, 14623
DUNS: 073955507
HUBZone Owned: N
Woman Owned: N
Socially and Economically Disadvantaged: N
Principal Investigator
 Carl S Byington
 Director, Research and De
 (814) 861-6273
Business Contact
 Mark Redding
Title: President
Phone: (585) 424-1990
Research Institution
Impact Technologies proposes to develop an open-interface software module encapsulating the algorithms and statistical analysis package used in verification software test environment. Developments include system-engineering analysis to identify the additional technical and procedural sources of false alarms, models and analysis techniques to be used for mitigation in addition to analysis of rate and time-based false alarm performance metrics. The result will be achieved through an assessment of the best technical approaches for PHM design using limited sources of fault data and models. Impact’s False Alarm Statistics Toolbox (FAST™) enables the user to access the integrated toolset through a graphical user interface to determine the optimal strategy for false alarm mitigation on a fleet-wide basis. The toolset builds upon PHM design guidelines developed for false alarm mitigation coupled with vibration and non-vibration based datasets. Standardized analysis metrics are implemented to characterize the performance of a variety of features derived from Impact’s PHM modules including ImpactEnergy™ bearing fault detection, GearMod™ gear fault detection and user-defined feature extraction routines. Impact will demonstrate the FAST™ product across a variety of datasets while implementing a suite of algorithms including: sensor validation, mode detection, feature extraction, feature fusion, fault detection, fault classification, threshold selection and reasoning.

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

Agency Micro-sites

SBA logo
Department of Agriculture logo
Department of Commerce logo
Department of Defense logo
Department of Education logo
Department of Energy logo
Department of Health and Human Services logo
Department of Homeland Security logo
Department of Transportation logo
Environmental Protection Agency logo
National Aeronautics and Space Administration logo
National Science Foundation logo
US Flag An Official Website of the United States Government