SBIR-STTR Award

Military communications and weapons systems depend on the health of their components to perform reliably over extended periods of time. Maintenance is an important aspect of reliability, assuring that the equipment is on line and operational when it is needed. Military-developed and commercial off-the-shelf (COTS) equipment now co-exist in complex military systems. The trend toward electronic/networked maintenance documentation presents an opportunity to improve maintainer effectiveness, but new tools must be developed to manage interactions between the information sources and maintainers. Instrumental Sciences, Inc. (ISI) proposes an Automated Multimedia Maintenance Support Tool (AMMST) based on the artificial intelligence field of cooperative multi-agent distributed work environments. Our approach combines the multi-agent architecture with statistical analysis and maintenance decision-making technology that ISI has developed for Predictive Fault Detection applications to produce a distributed information management tool set that gathers relevant information from diverse sources upon user request or maintenance scenario identification, combines and filters the information, then formats it for multimedia interactive presentation to the user. The primary objectives of the Phase I research are to (1) determine the feasibility of the AMMST concept and (2) characterize the potential of the tool to reduce downtime, and thus to improve system availability.

Keywords:
Maintenance, Intelligent Agent, Knowledge Representation, Diagnostics, Prognostics, Data Acquisition, Multimedia User Interface

Military communications and weapons systems depend on the health of their components to perform reliably over extended periods of time. Maintenance is an important aspect of reliability, assuring that equipment is on line and operational when it is needed. The trend toward electronic/networked maintenance documentation presents an opportunity to improve maintainer effectiveness, but new tools must be developed to manage interactions between the information sources and maintainers. In Phase I Instrumental Sciences, Inc. (ISI), with subcontract team member Sentar, Inc., researched techniques for an Automated Multimedia Maintenance Support Tool (AMMST) based on the artificial intelligence field of cooperative multi-agent distributed work environments. In the Phase II continuation, ISI will develop an engineering prototype AMMST, building on the successful Phase I results. Our approach applies the multi-agent architecture to produce a distributed information management tool set to support maintenance operations. These tools gather relevant information from diverse sources upon user request or maintenance scenario identification, then they filter the information and format it for interactive multimedia presentation to the user. The Phase I results included a successful demonstration of a distributed information-gathering architecture, employing cooperative agents to interface with local and distant maintenance resources.

Keywords:
Maintenance, Intelligent Agent, Knowledge Representation, Diagnostics, Prognostics, Data Acquisition, Multimedia User Interface, Condition-Based Maint