Abstract
Industry 4.0 adoption intensifies operational complexity in manufacturing SMEs, challenging concurrent optimization of resource allocation, sustainability, and resilience under stochastic conditions. Addressing this tripartite challenge, we engineer a novel Markov Decision Process (MDP) framework utilizing empirical manufacturing data. System states encapsulate triadic operational parameters: equipment functional states, discretized energy consumption, and production throughput metrics. Adaptive control actions dynamically reconfigure resource policies. Empirical validation confirms significant improvements: 15% reduced machine idle time, 12% lower specific energy consumption, and 10% higher throughput. These quantified outcomes demonstrate superiority over rule-based systems, establishing practical viability as a decision-support mechanism for sustainable Industry 4.0 transitions in resource-constrained environments. The evidenced equilibrium between operational efficiency and sustainability underscores the model's paradigmatic potential for resilient SME manufacturing systems.

This publication has 23 references indexed in Scilit: