🤖 AI Summary
This study addresses the scheduling challenge in manufacturing supply chains arising from the dynamic evolution of workforce qualifications—such as skill decay and training-induced labor unavailability—and their tight coupling with production, inventory, and training decisions. The work proposes the first closed-loop skill-constrained Model Predictive Controller (MPC) that explicitly models mechanisms of skill acquisition, maintenance, and expiration. At each shift, the controller solves a finite-horizon mixed-integer program encompassing production, inventory, backorders, and training, incorporating binary qualification states, hard eligibility constraints, and an interpretable terminal value function that quantifies future skill gaps. Rolling optimization is employed to implement only the first-period actions. In SkillChain-Gym simulations under multidimensional disturbances, the policy significantly outperforms static cross-training and reactive heuristics when skill or labor bottlenecks are foreseeable; however, lightweight static strategies remain competitive under sudden shocks or ample redundancy, indicating the approach’s advantage stems from proactive exploitation of qualification dynamics rather than mere adaptivity.
📝 Abstract
In skill-constrained production-inventory systems, the qualified human capacity available tomorrow depends on training decisions made today: production requires certified workers, certifications decay unless maintained, and training consumes the same scarce worker hours that production needs now. We study a closed-loop skill-constrained model predictive controller that, at every shift, solves a finite-horizon mixed-integer program over production, inventory, backlog, and training, with binary predicted certification, hard production eligibility, and an interpretable terminal value that prices certified-capacity gaps at the horizon boundary; only the first-period action is applied before replanning. On synthetic, seed-controlled SkillChain-Gym scenarios - announced and surprise new-skill shocks, demand shocks, absenteeism, forecast- and availability-quality modes, capacity-boundary and training-rate sweeps, and negative controls - we evaluate the controller against production-only and maintenance-only ablations, static cross-training insurance plans, and a strong reactive heuristic, under an ex-ante locked configuration and paired statistics. The result is regime dependence, not superiority: no policy class dominates. Predictive control helps when skill or labor bottlenecks are forecastable early enough for training to complete; lean static insurance remains hard to beat under surprise shocks, near the demand-capacity boundary, and wherever pre-shock slack makes insurance cheap. Attribution ablations separate certification maintenance, re-acquisition of lapsed certifications, and greenfield skill acquisition. Forecastability, not adaptivity per se, decides when predictive control pays.