You are here

Navy Artificial Intelligence Maintenance System (AIMS)

Award Information
Agency: Department of Defense
Branch: Navy
Contract: N68335-20-F-0590
Agency Tracking Number: N193-A01-0457
Amount: $1,592,781.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: N193-A01
Solicitation Number: 19.3
Timeline
Solicitation Year: 2019
Award Year: 2020
Award Start Date (Proposal Award Date): 2020-05-01
Award End Date (Contract End Date): 2021-11-15
Small Business Information
17150 W 95th Place
Arvada, CO 80007-1111
United States
DUNS: 130770055
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Christopher Bowman
 (303) 469-9828
 cbowman@df-nn.com
Business Contact
 Dr. Christopher Bowman
Phone: (303) 469-9828
Email: cbowman@df-nn.com
Research Institution
N/A
Abstract

The DF&NN team proposes to further develop the AIMS prototype developed and tested under Phase I to perform predictive maintenance on Naval aircraft.  Technical efforts will include improved machine learning performance, all-data source input from Navy sources, customized Navy maintenance personnel user interface and additional trust scoring of predictions. We plan to apply the AIMS Deep Multi-Start Residual Training (D-MSRT) NNs, Smoking Gun, and maintenance condition categorization D-MSRT NNs capabilities for as many aviation systems as available. We will train D-MSRT abnormality detection NNs to learn the labeled repair conditions that were used for each categorization NN to provide a categorization NN result trust score to the user. We will incorporate into AIMS our existing goal-driven turnkey NN capabilities that determine when to retrain, what data to retrain on, what data to test on, how to evaluate, and when to promote to on-line operations. This allow AIMS to automatically evolve and improve its performance based on progressing user goals. We will adapt the AIMS graphical user interfaces (GUI) for user-tier roles with a standardized software deployment approach designed for ease of deployment and upgrade (i.e., Docker REpresentational State Transfer (REST) API services) which support sharing of NNs and results across distributed operations. We will use these to validate AIMS performance and increase user trust in AIMS results. We will work closely with the sponsor to identify operational transition opportunities. AIMS will not be a black box solution. An objective of AIMS is to provide a system that develops trust with operators and provides CBM capabilities.  Our approach will be consistent with the strategy: “The purpose of the CBM strategy is to perform maintenance only when there is an objective evidence of need, while ensuring safety, equipment reliability, equipment availability, and reduction of total ownership cost. The fundamental goal of CBM is to optimize readiness while reducing maintenance and manning requirements.”  Deployment of AIMS capability will allow the Naval Aviation Enterprise (NAE) to implement CBM within the Naval Aviation Maintenance Program (NAMP) in a deliberate and phased manner.  Initially running in parallel with time and operating hour-based inspections, AIMS will provide early detection and characterization of system anomalies and component failures.  As the NAE gains confidence in AIMS performance, aircraft systems not critical to safety of flight could be transitioned from schedule-based maintenance to CBM.  Once proven, AIMS would facilitate transition of all appropriately instrumented aircraft systems to CBM.

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

US Flag An Official Website of the United States Government