Project Announcement: Predictive Vehicle Maintenance Through Data Acquisition

The challenges of U.S. Army vehicle maintenance and repair continue to present new obstacles to the United States of America. As more vehicles are introduced, the methods for maintaining those new vehicles as well as the existing vehicles currently in operation continue to become more and more obsolete and cumbersome. As this phase of the vehicle development nears the end and the vehicle is deployed, the way maintenance has always been accomplished is easily used simply due to the readily available tools. Unfortunately, these methods and tools are no longer sufficient nor are they accurate.

Acquiring the data to discover which vehicles need to be repaired or what maintenance needs to be accomplished is difficult.

Data sources for U.S. Army vehicle maintenance and repair are disparate. Over the years the need for repairing U.S. Army vehicles and ensuring they operate in a state of readiness has been and will remain a critical part of a vehicles’ lifecycle. Vehicle information is nice to have but it needs to be the right data. Data needs to be analyzed to ensure it is interpreted correctly so that the right repairs are predicted and performed. Repairs must be accurate and well executed to give soldiers the confidence they require to know the vehicle in which they ride is reliable. The right maintenance must be scheduled and performed so that all vehicles remain operational and at their peak performance.

The overall objective of this project is to give the U.S. Army visibility into improvements for their vehicle repair and maintenance methods and to identify a way in which these methods of data acquisition and predictive analysis can be accomplished.

Those interested in participating in this project should contact Marc Sharp, marcs@ncms.org or (734) 995-7051 by August 14th, 2017. We encourage participation of Disadvantaged Business Enterprises (DBEs), including Minority Business Enterprises (MBEs) and Women’s Business Enterprises (WBEs).