Multi-Agent Health Management System

For ground vehicle safety and condition-based maintenance, health management approaches have been developed and implemented for anomaly/fault detection/identification, degradation status estimation and Remaining Useful Life (RUL) prediction. However, the variability of vehicle’s capability, characteristics, and functionality poses a great challenge on the diagnostics and prognostics for the whole fleet with a vast number of Army ground vehicle platforms. A general diagnostics/prognostics model does not exist when dealing with a vast number of Army ground vehicle platforms. One promising solution to fleet-wide diagnostics/prognostics, as described in the solicitation, is to build a diagnostics/prognostics library on a powerful server and develop a server based tool set that can automatically generate diagnostic/prognostic algorithms for each vehicle in the fleet. Meanwhile, the vehicle diagnostic/prognostic algorithms can be updated and maintained by a set of services on server side. Intelligent Automation, Inc. (IAI), in collaboration with Wright State University and General Motors (GM), will enhance the Automated Algorithm Generator (A2G) framework and implement a full-scale A2G system for health management of ground vehicles. The A2G system will automatically generate and maintain diagnostic/prognostic algorithms for any vehicle/platform by embedding a library of advanced and light-weight diagnostic/prognostic algorithms into our multi-agent software infrastructure, CybeleTM.