Distributed scheduling problem, a novel model of intelligent manufacturing, urgently needs new scheduling methods to meet the dynamic market demand. The inverse scheduling in a distributed shop greatly impacts both its energy consumption and productivity. This paper proposes the energy-efficient distributed permutation flow-shop inverse scheduling problem to minimize adjustment and energy consumption simultaneously. This model contains some realistic constraints, controllable processing times and energy consumption factors. To solve the problem effectively, an effective hybrid collaborative algorithm with cooperative search scheme is designed. The heuristic method and random method are improved to initialize the population. In order to balance the global exploration and local development ability of the algorithm, a double-population cooperative search link based on learning mechanism is presented. Moreover, a dual-mode local search based on switching mechanism is addressed. The influence of key parameters on the performance of the algorithm is proved by using the ANOVA of design-of-experiment. Finally, the developed algorithm has been compared with other approaches for distributed inverse scheduling and assessed by satisfactory results on different set of distributed inverse scheduling problems.

分布式调度问题作为智能制造的一种新模式，迫切需要新的调度方法来满足动态的市场需求。分布式车间的逆向调度极大地影响了其能耗和生产率。本文提出了节能分布式置换流水车间逆调度问题，以同时最小化调整和能耗。该模型包含一些现实约束、可控处理时间和能耗因素。为有效解决该问题，设计了一种具有协同搜索方案的有效混合协同算法。改进了启发式方法和随机方法来初始化种群。为了平衡算法的全局探索和局部开发能力，提出了一种基于学习机制的双种群协同搜索链路。此外，还提出了基于切换机制的双模式本地搜索。通过实验设计的方差分析证明了关键参数对算法性能的影响。最后，将所开发的算法与其他分布式逆调度方法进行了比较，并通过对不同分布式逆调度问题的满意结果进行了评估。