Data-Driven Block Replacement Scheduling for Fleets of Identical Machines

arXiv·low signal

This paper develops data-driven algorithms for maintaining N independent identical machines under a block-replacement policy, learning schedules directly from operational data rather than assuming known failure distributions. It targets the classic reliability/operations-research maintenance problem with a modern ML-driven twist. Limited generalizability to mainstream AI work, but relevant for predictive-maintenance and industrial-ops practitioners.