Rescheduling of Distributed Manufacturing System with Machine Breakdowns

This study attempts to explore the dynamic scheduling problem from the perspective of operational research optimization. The goal is to propose a rescheduling framework for solving distributed manufacturing systems that consider random machine breakdowns as the production disruption. We establish a mathematical model that can better describe the scheduling of the distributed blocking flowshop. To realize the dynamic scheduling, we adopt an "event-driven" policy and propose a two-stage "predictive-reactive" method consisting of two steps: initial solution pre-generation and rescheduling. In the first stage, a global initial schedule is generated and considers only the deterministic problem, i.e., optimizing the maximum completion time of static distributed blocking flowshop scheduling problems. In the second stage, that is, after the breakdown occurs, the rescheduling mechanism is triggered to seek a new schedule so that both maximum completion time and the stability measure of the system can be optimized. At the breakdown node, the operations of each job are classified and a hybrid rescheduling strategy consisting of "right-shift repair + local reorder" is performed. For local reorder, we designed a discrete memetic algorithm, which embeds the differential evolution concept in its search framework. To test the effectiveness of DMA, comparisons with mainstream algorithms are conducted on instances with different scales. The statistical results show that the ARPDs obtained from DMA are improved by 88%.