动态柔性生产车间实例及智能感知、自动重构、自主决策软件构件数据集

动态柔性作业车间调度是智能制造领域的一个新难题，与柔性作业车间调度相比，作业抵达时间的不确定性进一步加剧了获得最优调度的难度。同时，大规模的生产调度同样是运筹学领域的研究热点之一，生产规模的增加会导致传统方法的求解时间指数级增加，无法应用到实际生产中。项目研究人员提出了一种基于分层强化学习的大规模动态车间调度算法，本数据集服务于该调度算法，为算法提供了包括模型训练、验证与测试所需的生产实例。本数据集由300个生产实例组成，其中生产实例来源均为程序生成，主要使用场景为模型的训练及测试。通过该调度算法与数据集，可以完成实际生产中的智能感知、自动重构、自主决策等复杂任务需求。

Dynamic Flexible Job Shop Scheduling is a new challenge in the field of intelligent manufacturing. Compared with Flexible Job Shop Scheduling, the uncertainty of job arrival times further increases the difficulty of obtaining optimal scheduling. Meanwhile, large-scale production scheduling is also one of the research hotspots in the field of operations research. As production scale expands, the solution time of traditional methods increases exponentially, making them unable to be applied to actual production. The project's researchers proposed a large-scale dynamic workshop scheduling algorithm based on hierarchical reinforcement learning. This dataset serves this scheduling algorithm, providing the production instances required for the algorithm's model training, validation and testing. This dataset consists of 300 production instances, all of which are program-generated, and its main application scenarios are model training and testing. Through this scheduling algorithm and dataset, complex task requirements such as intelligent perception, automatic reconstruction and autonomous decision-making in actual production can be fulfilled.

搜集汇总

背景与挑战

背景概述

该数据集包含300个程序生成的生产实例，服务于基于分层强化学习的大规模动态车间调度算法，用于模型训练、验证和测试。它旨在支持智能制造中的智能感知、自动重构和自主决策等复杂任务需求。