A Monte Carlo Diagnostic Analysis of Adaptive Maintenance Policies for Additive Manufacturing Systems

This paper develops a simulation‐based framework for condition‐based maintenance (CBM) decision‐making in Additive Manufacturing (AM) systems, with the aim of examining the trade‐offs among system reliability, operational downtime, and maintenance cost. Four maintenance strategies are analyzed: fixed inspection with fixed maintenance threshold ( Δ T , M ), adaptive inspection with fixed threshold ( Δ T k , M ), fixed inspection with adaptive threshold ( Δ T , M k ), and fully adaptive inspection and threshold ( Δ T k , M k ). System degradation is represented through a stochastic process and evaluated using Monte Carlo simulations under noisy condition‐monitoring information. A comparative assessment based on long‐run cost rate, downtime, reliability, and preventive‐to‐corrective maintenance ratios indicates that adaptive strategies enhance responsiveness to degradation information and marginally improve preventive intervention effectiveness; however, under the investigated operating conditions, differences in overall cost, downtime, and reliability remain limited across strategies. From a qualitative standpoint, fixed strategies offer greater structural simplicity and ease of implementation, whereas adaptive strategies provide increased flexibility at the expense of higher sensing, modeling, and computational requirements. The results emphasize that meaningful performance improvements in CBM for AM systems depend not only on adaptiveness, but also on careful parameterization and the quality of condition‐monitoring information.