🤖 AI Summary
This paper addresses the heterogeneity in component failure rates arising from dual-sourcing (traditional manufacturing and additive manufacturing) in spare parts management for shutdown-sensitive assets. To handle performance and reliability uncertainties induced by process variations, we propose a novel method integrating dynamic demand modeling with adaptive optimization. Specifically, we develop an End-to-end Parametric Learning (EPL) framework enabling policy generalization across multiple part types and parameter configurations, and introduce a synergistic optimization mechanism combining iterative heuristics with deep reinforcement learning (DQN/PPO). Simulation results show an average optimality gap of only 0.4%; in an energy-sector case study, the approach outperforms baseline methods in 91.1% of scenarios, reducing average costs by 22.6%. This work is the first to systematically characterize the coupling among manufacturing processes, failure characteristics, and dynamic demand, establishing a scalable intelligent decision-making paradigm for mission-critical spare parts logistics.
📝 Abstract
This paper investigates dual sourcing problems with supply mode dependent failure rates, particularly relevant in managing spare parts for downtime-critical assets. To enhance resilience, businesses increasingly adopt dual sourcing strategies using both conventional and additive manufacturing techniques. This paper explores how these strategies can optimise sourcing by addressing variations in part properties and failure rates. A significant challenge is the distinct failure characteristics of parts produced by these methods, which influence future demand. To tackle this, we propose a new iterative heuristic and several reinforcement learning techniques combined with an endogenous parameterised learning (EPL) approach. This EPL approach - compatible with any learning method - allows a single policy to handle various input parameters for multiple items. In a stylised setting, our best policy achieves an average optimality gap of 0.4%. In a case study within the energy sector, our policies outperform the baseline in 91.1% of instances, yielding average cost savings up to 22.6%.