Digital Twins and Predictive Sustainment: Readiness Gains, Inventory Effects, and Performance-Based Logistics Alignment

Abstract

What if a Marine squadron commander could predict aircraft failures before deployment, optimize spare-part inventories before shortages occur, and select the right aircraft for the mission based on real-time sustainment forecasts? The U.S. Marine Corps H-1 fleet currently relies on fragmented data systems, reactive maintenance practices, and fleet-wide averages that obscure the unique condition of individual aircraft. This research explores how bureau-number-specific digital twins, powered by predictive analytics and AI-enabled logistics, can transform sustainment from a reactive process into a strategic readiness advantage. Using existing aviation maintenance and readiness data, the study proposes a Minimum Viable Digital Twin framework that integrates aircraft health, maintenance, and supply-chain information to forecast failures, improve mission-capable rates, and strengthen performance-based logistics decisions. The findings outline a practical pathway toward intelligent sustainment ecosystems that could reshape not only H-1 readiness, but the future of Department of Defense aviation logistics as a whole.