Abstract: As a typical distributed production model, distributed flexible job shop scheduling faces new challenges under the global manufacturing pattern. In light of the shortcomings of transportation time modeling and production-distribution cooperative optimization in existing research, this study proposes for the first time an integrated scheduling problem of distributed flexible job shop production and distribution considering automatic guided vehicle transportation. Firstly, a mixed integer programming model is established to minimize the maximum completion time and total tardiness. Secondly, a learning-driven multi-objective artificial bee colony algorithm is presented to address the model. Based on the artificial bee colony algorithm, an encoding and decoding method incorporating the problem characteristics, a heuristic population initialization strategy, neighborhood structures considering the problem features, a Q-learning-driven neighborhood structure selection mechanism, and an iterative local search method are adopted to further improve the global and local search abilities of the developed approach. Finally, a set of problem test instances is constructed by integrating production and distribution benchmarks, and the comparative experiments are carried out: 1) Compared with the CPLEX solver, the effectiveness of the established model is verified, and the advantages of the proposed algorithm in solving large-scale problems are proved. 2) Compared with the basic artificial bee colony algorithm, the positive roles of Q-learning method are verified. 3) Compared with three famous meta-heuristics in the existing literature, the superiority of the proposed algorithm in solving most of instances is demonstrated. The experiment results can assist managers and practitioners in making more sensible and appropriate decisions for integrated scheduling of production and distribution considering automated guided vehicle transportation in distributed production environments.

Key words: distributed flexible job shop scheduling, integrated scheduling of production and distribution, automated guided vehicle transportation, artificial bee colony algorithm, Q-learning method