动态柔性车间容错调度任务数据集

针对联宝智能工厂笔记本装配线中订单频繁变动与产品高度定制化所带来的复杂调度挑战，本文提出了一种高保真度的仿真数据集构建方法，以支持主动容错调度算法的开发与评估。传统静态调度数据集难以反映实时生产中的多样化加工需求、设备故障及紧急插单等不确定因素，因此亟需一种能够动态反映生产环境变化与扰动的仿真数据集。通过系统化的数据预处理，并采用“随机化+约束化”原则进行数据模拟，准确再现了实际生产中的多重不确定性与资源限制，如紧急订单到达、设备故障及维护需求。该数据集涵盖任务级别信息、加工时间矩阵及机器特性，经过严格的质量控制与评估。此仿真数据集为主动容错调度算法提供了坚实的基础，帮助研究者在接近实际生产环境中验证调度策略的鲁棒性和适应性，从而优化生产效率，减少停机损失与交付延误风险。

To address the complex scheduling challenges arising from frequent order fluctuations and highly customized products in the notebook assembly line of Lianbao Intelligent Factory, this paper proposes a high-fidelity simulation dataset construction method to support the development and evaluation of active fault-tolerant scheduling algorithms. Traditional static scheduling datasets fail to reflect uncertain factors in real-time production, such as diverse processing demands, equipment failures and emergency order insertions. Therefore, there is an urgent need for a simulation dataset that can dynamically reflect production environment changes and disturbances. Through systematic data preprocessing and data simulation following the "randomization + constraint" principle, this method accurately reproduces multiple uncertainties and resource constraints in actual production, including emergency order arrivals, equipment failures and maintenance requirements. This dataset covers task-level information, processing time matrices and machine characteristics, and has undergone strict quality control and evaluation. This simulation dataset provides a solid foundation for active fault-tolerant scheduling algorithms, enabling researchers to verify the robustness and adaptability of scheduling strategies in near-real production environments, thereby optimizing production efficiency and reducing downtime losses and risks of delivery delays.

搜集汇总

背景与挑战

背景概述

该数据集是一个针对智能制造柔性车间动态调度的高保真度仿真数据集，旨在解决联宝智能工厂笔记本装配线中订单频繁变动和产品高度定制化带来的复杂调度挑战。它通过模拟紧急订单、设备故障等不确定因素，提供任务级别信息、加工时间矩阵和机器特性，用于支持主动容错调度算法的开发与评估，以优化生产效率并减少停机损失。