面向生产扰动的航天制造车间鲁棒性调度方法研究  

A Robust Scheduling Method for Aerospace Manufacturing Workshops with Production Disturbance

作　　者：郭具涛 戴铮[2] 张洁 吕佑龙[3] 孙晓凤 GUO Jutao;DAI Zheng;ZHANG Jie;LYU Youlong;SUN Xiaofeng(Shanghai Shenjian Precision Machinery Technology Co.,Ltd.,Shanghai 201600,China;Shanghai Spaceflight Precision Machinery Institute,Shanghai 201600,China;Institute of Artificial Intelligence,Donghua University,Shanghai 201620,China)

机构地区：[1]上海神剑精密机械科技有限公司,上海201600 [2]上海航天精密机械研究所,上海201600 [3]东华大学人工智能研究院,上海201620

出　　处：《工业工程》2025年第2期69-77,共9页Industrial Engineering Journal

基　　金：上海市青年科技启明星计划项目(22QB1404200);国家自然科学基金项目资助(52375486)。

摘　　要：针对航天产品多品种、变/小批量的典型离散制造特点,考虑紧急插单、工艺变更和工艺偏离等生产扰动,构建以工序开始偏离时间、订单交付偏离时间鲁棒性指标和最大完工时间效率指标为优化目标的鲁棒调度模型。通过构建鲁棒评价模型对生产扰动影响下的调度方案进行鲁棒性能评价,设计基于代理机制的师徒进化算法,实现生产扰动的多目标综合优化。为验证鲁棒调度方法的性能,在3种不确定生产时间场景下与原始师徒进化算法、经典粒子群算法进行性能比较。结果表明,所提算法在考虑不同类型不确定性的条件下,其调度性能明显优于其他智能优化算法,能有效兼顾调度过程的效率和鲁棒性。For the typical discrete manufacturing characteristics of aerospace products with multiple varieties and variable/small batch sizes,a robust scheduling model is established with optimization objectives of minimizing deviation time at the start of a process,order delivery deviation time,robustness indices,and maximum completion time efficiency,with consideration of production disturbance such as emergency order insertion,process change and process deviation.A robust evaluation model is developed to evaluate the robustness of scheduling schemes with production disturbance.A master-apprentice evolutionary algorithm based on the agent mechanism is designed to achieve multi-objective comprehensive optimization of production disturbance.To verify the performance of the robust scheduling method,performance comparisons are conducted between the original master-apprentice evolutionary algorithm and classical particle swarm algorithm under three uncertain processing time scenarios.Results show that the proposed algorithm significantly outperforms other intelligent optimization algorithms in scheduling performance under the condition of considering different types of uncertainties,effectively balancing the efficiency and robustness of the scheduling process.

关 键 词：生产扰动 鲁棒调度 代理机制 师徒进化算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TB497[自动化与计算机技术—控制科学与工程]