“Planned maintenance, based on timely data and predictive analytics, is critical to maximize rotorcraft uptime and mission readiness, especially for our Apache and Blackhawk helicopters deployed in forward operating areas,” said John Moffatt, Project Manager for the U.S. Army Aviation Applied Technology Directorate. “Intelligent maintenance practices are also critical in keeping the Army’s costs down in the face of increasing budget pressures. This project seeks to combine wireless communications with advanced oil analysis for our rotorcraft fleet to increase the velocity of actionable maintenance information and enhance the predictability of maintenance issues before they lead to costly downtime.”

Mitch Shikowitz, Director of Business Development for Spectro, added, “Existing Heath Usage Monitoring Systems (HUMS) and Condition Based Maintenance (CBM) help protect the Army’s rotorcraft fleet, but the focus of HUMS has been vibration and stress monitoring.  We envision this project’s development of an intelligent, real-time oil monitoring system-backed by state-of-the-art data mining-as a valuable extension of current HUMS technologies”.

“Ultimately,” Mr. Shikowitz concluded, “we want to change the way machine oil analysis is viewed-in both military and commercial applications-as a best practice that utilizes oil analysis as a cost effective maintenance tool to track machine condition and equipment wear.  By quickly and effectively identifying, analyzing, and communicating information about machine condition, we aim to significantly improve maintenance planning, reduce the frequency and cost of repairs, and optimize asset uptime.”

“We are pleased to team with Spectro and QinetiQ North America, which are world-class technology providers, to develop such a high-value potential solution for our armed services,” said Kenneth Ehrman, President of I.D. Systems.  “In addition to building a smart, wireless, on-craft communication module for this project, we will be creating middleware and a graphical user interface to help correlate the real-time machine oil data to an extensive historical database of oil-related maintenance prognostics. We view this effort as having upside potential for many applications, in both government and industrial environments.”