Mr. Louis J. Hogge is the Engineering Flight Chief of the 416th Supply Chain Management Squadron (416 SCMS) in the 448th Supply Chain Management Wing. The wing provides the planning and execution of depot-level repairable and consumable spare parts to sustain Air Force Programmed Depot Maintenance operations and more than 5,000 operational aircraft and 16,000 engines across the globe. With an operating budget of $7.2 billion, managing 106,000 items with an inventory value of $71.3 billion, the wing qualifies as a Fortune 500 company. Mr. Hogge is responsible for engineering management and technical direction of the Squadron (more than 160 assigned personnel, 40 engineers) including all engineering sub-functions; avionics systems, mechanical/structural systems, and support equipment. Louis has long-term interest in data analytics and its practical use in day-to-day operations. He initiated, managed, and oversaw operational deployment for several successful data analytics projects. His earlier analytics work was related to systems reliability, more recent work is in AI for maintenance and logistics processes. Mr. Hogge has BS in Electrical Engineering (Cum Laude) from the University of Utah and MS in Systems Engineering from the Air Force Institute of Technology.
US Air Force operates thousands of aircraft. The cost of Supply Chain management operation required to keep them flying is over $16B per year in parts and labor. At the same time, mission readiness of the fleet is just 70%. Digital modernization and predictive analytics could improve the availability and reduce the cost. Currently, much supply chain data is being collected and stored in the databases but not analyzed systematically because of analyst shortage. As result, effectiveness of the supply chain processes, including repair of the parts, is not known very well and hard to manage.
This talk will focus on Explainable AI for mission critical applications in Supply Chain management. Several years ago, our group has documented over $200M cost avoidance from data analytics for a single aircraft fleet. This prompted efforts to develop scalable AI applications that automatically analyze Supply Chain effectiveness based on existing maintenance and logistics data. The AI uses reliability and logistics models understood by the analysts. It addresses issues related to quality of available data.