Real time disruption management for a two-stage batch production–inventory system with reliability considerations

• A real time disruption recovery model is developed in a two-stage production–inventory system.
• A nonlinear constraints mathematical model is developed to suggest a recovery plan.
• A new approach is proposed that deals with a series of disruptions over a period of time.
• The model is implemented in a real world case from a pharmaceutical company.
• Process reliability is also considered because imperfect production processes are common.

In this research, a two-stage batch production–inventory system is introduced. In this system, the production may be disrupted, for a given period of time, either at one or both stages. In this paper, firstly, a mathematical model has been developed to suggest a recovery plan for a single occurrence of disruption at either stage. Secondly, multiple disruptions have been considered, for which a new disruption may or may not affect the recovery plan of earlier disruptions. We propose a new approach that deals with a series of disruptions over a period of time, which can be implemented for disruption recovery on a real time basis. In this approach, the model formulated for single disruption has been integrated to generate initial solutions for individual disruptions and the solutions have been revised for multiple dependent disruptions with changed parameters. With the proposed approach, an optimal recovery plan can be obtained in real time, whenever the production system experiences either a sudden disruption or a series of disruptions, at different points in time. Some numerical examples and a real-world case study are presented to explain the benefits of our proposed approach.