Machine learning-based dynamic production planning and control in unreliable manufacturing systems with supply disruptions

This paper addresses a production planning and control problem within failure-prone manufacturing systems disrupted by irregular raw material supply. It introduces a machine learning-based approach that supports dynamic and responsive decision-making for integrated production and replenishment control policies, minimising expected long-term total costs under stochastic conditions. Our approach enables continuous adjustments to production rates, as well as replenishment order size and triggers, in response to system states and delivery lead time variations. By integrating machine learning techniques, experimental design, and simulation modelling, we assess the impact of control policies parameters and raw material delivery lead times on total costs. The optimised machine learning model then dynamically adjusts these parameters, defining a hedging point production policy combined with an economic order quantity-type replenishment strategy. Numerical experiments show that the dynamic control policies resulting from our approach reduces costs by up to 15% compared to semi-dynamic policies and up to 25% compared to static policies, particularly in environments with high delivery lead time variability. This highlights significant gains in resilience and economic performance over existing approaches. Additionally, our approach can be applied in production environments affected by supply uncertainties, enabling continuous inventory and production adjustments based on observed system conditions.