Multi-agent based dynamic scheduling optimisation of the sustainable hybrid flow shop in a ubiquitous environment

With the increased awareness of the market competition and protection of the environment, many studies have examined sustainable manufacturing, which combines lean production and sustainable performance, but there still exist barriers between the theories and the practices. This paper proposes a dynamic scheduling unit (DSU) with the multi-agent system (MAS) to build and formulate a kind of sustainable hybrid flow shop in a ubiquitous environment. The processing time, energy consumption and carbon emission are considered the sustainability indicators; and the machine failure, job inserting and job reworking are considered the disruption events. Then, a GA-based dynamic scheduling optimisation with variable priorities is proposed, including a weighted sum of indicators-genetic algorithm (WSI-GA) and an event-driven priority weights local search (EPW-LS) to dynamically generate the prescheduling and rescheduling solutions of the sustainable hybrid flow shop. Lastly, the proposed theories are applied to a computational case of part machining via the discrete event simulation method to demonstrate their validity and feasibility. The results show that the WSI-GA for prescheduling is superior to the referenced traditional priority-based genetic algorithms in the four different production modes and that EPW-LS for rescheduling can effectively improve the solutions of the preschedulings once disruption events occur.

Automated summary

This study proposes a dynamic scheduling optimization approach for sustainable manufacturing by integrating multiple Agent systems to build a hybrid flow shop, performing better in handling machine failures and energy consumption compared to traditional methods.