Bi-objective scheduling for energy-efficient distributed assembly blocking flow shop

Energy-efficient scheduling plays a pivotal role in distributed sustainable manufacturing. This study provides the first attempt to use a knowledge-based bi-objective collaborative optimization algorithm with Q-learning (KBCQL) to address an energy-efficient distributed assembly blocking flow shop scheduling problem (EEDABFSP) considering the total assembly completion time and total assembly energy consumption. Constructive heuristics are introduced to establish a favorable initial population characterized by high quality and diversity. Experimental results on benchmark instances demonstrated that the proposed KBCQL can effectively balance these two objectives and outperform comparative algorithms for solving the EEDABFSP problem.