<img height="1" width="1" alt="" style="display:none" src="https://www.facebook.com/tr?id=648880075207035&amp;ev=NoScript">
BayesiaLab
3rd Annual BayesiaLab Conference

Presentation on October 7, 2015, at the 3rd Annual BayesiaLab Conference:

Using Bayesian Networks to Optimize Specific Fuel Consumption in Army Command Post Electrical Power Grids

David Aebischer
Chief of Special Projects, US Army Communications Electronics Command (CECOM), Training Support Division (TSD)

Providing reliable electrical power for complex weapon systems deployed anywhere in the world represents a unique and multi-faceted challenge for the Army. The Central Power Solution (CPS) family of integrated tactical power systems – developed by the DOD Project Manager for Expeditionary Energy & Sustainment Systems (PM E2S2) – combines precise, diesel engine-driven, power sources with power distribution modules and cabling to create a flexible and scalable tactical power grid that effectively supplies power to all weapon system, lighting, and HVAC loads in the Command Post (CP). But field test data show that while the CPS is effective in providing power, it can be inefficient in terms of fuel consumption due to routine operation at sub-optimal loads. Brake Specific Fuel Consumption (BSFC) is a measure of fuel consumed per unit of work and is normally displayed graphically on an “island map” that pinpoints the coordinates along a diesel engine power curve where the engine is doing the most work with the least amount of fuel – a zero slope point on the curve where diesel fuel efficiency is maximum and BSFC is minimum. A CECOM Training Support Division (TSD) analysis of this problem has determined that all the necessary hardware pieces are in place and that - given a tool that is capable of representing and manipulating the CP as an aggregated BSFC curve – soldiers can optimize the layout of the power grid and Army units can realize significant cost savings through efficient use of the CPS. TSD, in conjunction with its industry partners, is using BayesiaLab to develop this tool.

Please Register to Download Presentation Slides