面向智能生产的分布式流水车间调度研究

Research on Distributed Flow Shop Scheduling for Intelligent Production

为了使传统流水车间的调度模型更灵活和更智能化以适应不同生产环境,课题组提出了基于深度学习的分布式流水车间调度方法。通过学习和分析分布式车间系统中的大量数据,利用策略梯度方法在多次迭代优化后使目标得到近似最优解,获取了更智能、适应性更强的生产计划和调度策略;并通过实验和仿真进行验证。结果表明该方法能提高生产效率和资源利用率,并具有成本控制方面的潜力。该研究为制造业的分布式生产环境提供了一种先进的调度策略,为车间管理者提供更准确、更智能的决策参考。

In order to make the traditional flow shop scheduling model more flexible and intelligent to adapt to different production environments,scheduling strategy of distributed flow shop based on deep learning was proposed.By learning and analyzing a large amount of data in the distributed shop floor system,the strategy gradient method was used to obtain the approximate optimal solution after several iterations of optimization,and a more intelligent and adaptable production planning and scheduling strategy was obtained.It was verified by experiments and simulation.The results show that this method can improve production efficiency and resource utilization,and has potential in cost control.The research provides an advanced scheduling strategy for distributed production environment of manufactur industry,and provides more accurate and intelligent decision reference for shop floor managers.