一种考虑显隐性干扰的节能车间动态调度方法

An Energy-Efficient Shop Floor Dynamic Scheduling Method Considering Explicit and Hidden Disturbances

摘要

在实际生产制造中，复杂的车间环境通常伴有显性和隐性动态干扰．显性干扰包括随机工件到达、机器故障、订单取消等，可能直接导致系统停工；隐性干扰如设备装夹、运输问题引发的机器空转和生产状态偏差，会逐渐导致能源浪费和系统性能下降．针对上述问题，本文提出一种低碳柔性作业车间(FJSP)自适应动态调度方法．该方法利用车间状态数据，针对显性干扰构建多目标动态调度模型，以最小能耗、最大完工时间、设备总负载和稳定度为优化目标，通过部分重调度保障车间生产稳定性．针对隐性干扰，设计了量化动态生产状态的 14 维决策特征，基于仿真数据建立生产状态数据集，并结合反向传播神经网络(BPNN)为基础构建自适应动态调度决策模型，该模型可进行 3 种典型调度策略的自适应选择，有效应对隐性干扰的影响．实验结果表明：该策略在决策精度和生产优化方面均表现出优异性能，显著提升了车间的低碳生产效率和系统适应能力．

Abstract

In actual manufacturing，complex workshop environments are often accompanied by explicit and hidden dynamic disturbances. Explicit disturbances include random job arrivals，machine breakdowns，order cancellations，and other explicit dynamic disturbances，which may directly lead to system shutdowns. Hidden disturbances，such as machine idling and production state deviation owing to problems with machine equipment clamping and transportation，gradually result in considerable energy consumption and system performance decline on the shop floor. To solve the above problems，this study proposes a low-carbon flexible job shop(FJSP)adaptive dynamic scheduling method. It utilizes the state data of a production plant to establish a multi-objective FJSP dynamic scheduling model for explicit disturbances with minimum energy consumption，maximum completion time，and total equipment load and stability，workshop production stability is ensured through partial rescheduling. For hidden disturbances，a 14-dimensional decision feature to quantify the dynamic production state is designed. Based on the simulation data，the production state dataset of the workshop under hidden disturbances is established，and an adaptive dynamic scheduling decision-making model is established based on the back propagation neural network(BPNN). The model can adaptively select among three typical scheduling strategies，effectively coping with the impact of implicit disturbances. The results show that the proposed strategy has good performance in terms of decision accuracy and production optimization，and considerably improves the low-carbon production efficiency and system adaptability of the workshop.

关键词

显性干扰 / 隐性干扰 / 动态调度 / 神经网络

Key words

explicit disturbance / hidden disturbance / dynamic scheduling / neural network

参考文献

[1] Li P S, Wu W, Zhao Z H, et al. Indoor positioning systems in industry 4.0 applications：Current status，opportunities，and future trends[J]. Digital Engineering, 2024, 3:100020.

[2] 国家统计局. 中国统计年鉴 2024[M]. 北京： 中国统计出版社， 2024.

[3] National Bureau of Statistics . China Statistical Yearbook 2024[M]. Beijing：China Statistics Press， 2024(in Chinese).

[4] Mouzon G, Yildirim M B, Twomey J. Operational methods for minimization of energy consumption of manufacturing equipment[J]. International Journal of Production Research, 2007, 45(18):4247-4271.

[5] Wu X L, Sun Y J. A green scheduling algorithm for flexible job shop with energy—saving measures[J]. Journal of Cleaner Production, 2018, 172:3249-3264.

[6] Gong G L, Chiong R, Deng Q W, et al. A two—stage memetic algorithm for energy—efficient flexible job shop scheduling by means of decreasing the total number of machine restarts[J]. Swarm and Evolutionary Computation, 2022, 75:101206.

[7] Cheng L P, Tang Q H, Wu Z J, et al. Mathematical model and enhanced cooperative co—evolutionary algorithm for scheduling energy—efficient manufacturing cell[J]. Journal of Cleaner Production, 2021, 326:129310.

[8] Tian S L, Wang T Y, Zhang L, et al. Real—time shop floor scheduling method based on virtual queue adaptive control：Algorithm and experimental results[J]. Measurement, 2019, 147:106689.

[9] Zhao F Q, Liu Y B, Xu T P, et al. A reinforcement learning hyper—heuristic algorithm for the distributed flowshops scheduling problem under consideration of emergency order insertion[J]. Applied Soft Computing, 2024, 167:112461.

[10] Luo C, Gong W Y, Lu C. Knowledge—driven two—stage memetic algorithm for energy—efficient flexible job shop scheduling with machine breakdowns[J]. Expert Systems with Applications, 2024, 235:121149.

[11] Lü L L, Fan J X, Zhang C J, et al. A multi—agent reinforcement learning based scheduling strategy for flexible job shops under machine breakdowns[J]. Robotics and Computer—Integrated Manufacturing, 2025, 93:102923.

[12] Gao Q L, Liu J H, Li H T, et al. Digital twin—driven dynamic scheduling for the assembly workshop of complex products with workers allocation[J]. Robotics and Computer—Integrated Manufacturing, 2024, 89:102786.

[13] 刘明周, 单晖, 蒋增强, 等. 不确定条件下车间动态重调度优化方法[J]. 机械工程学报, 2009, 45(10)， 137-142.

[14] Liu Mingzhou, Shan Hui, Jiang Zengqiang, et al. Dynamic rescheduling optimization of job—shop under uncertain conditions[J]. Journal of Mechanical Engineering, 2009, 45(10)， 137-142(in Chinese).

[15] Sobaszek Ł, Gola A, Kozłowski E. Job—shop scheduling with machine breakdown prediction under completion time constraint[C]// Proceedings of the 2018 Federated Conference on Computer Science and Information Systems. Piscataway，USA, 2018：437-440.

[16] Abumaizar R J, Svestka J A. Rescheduling job shops under random disruptions[J]. International Journal of Production Research, 1997, 35(7):2065-2082.

[17] Tian C L, Zhou G H, Zhang J J, et al. Optimization of cutting parameters considering tool wear conditions in low—carbon manufacturing environment[J]. Journal of Cleaner Production, 2019, 226， 706-719.

[18] 田颖, 邵文婷, 王太勇. 车间生产过程能量足迹建模与加工参数协同优化[J]. 中国机械工程, 2021, 32(22):2744-2753.

[19] Tian Ying, Shao Wenting, Wang Taiyong. Energy footprint modeling and parameter optimization in workshop manufacturing process[J]. China Mechanical Engineering, 2021, 32(22):2744-2753(in Chinese).

[20] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm：NSGA—Ⅱ[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197.

[21] Wahab M I M, Wu D S, Lee C G. A generic approach to measuring the machine flexibility of manufacturing systems[J]. European Journal of Operational Research, 2008, 186(1):137-149.

[22] 周启超. BP 算法改进及在软件成本估算中的应用[J]， 计算机技术与发展, 2016, 26(2):195-198.

[23] Zhou Qichao. Improvement of BP algorithms and its application in software cost estimation[J]. Computer Technology and Development, 2016, 26(2):195-198(in Chinese).

[24] 王嵘冰, 徐红艳, 李波, 等. BP 神经网络隐含层节点数确定方法研究[J]. 计算机技术与发展, 2018, 28(4):31-35.

[25] Wang Rongbing, Xu Hongyan, Li Bo, et al. Research on method of determining hidden layer nodes in BP neural network[J]. Computer Technology and Development, 2018, 28(4):31-35(in Chinese).

[26] Brandimarte P. Routing and scheduling in a flexible job shop by tabu search[J]. Annals of Operations Research, 1993, 41:157-183.

基金资助

国家自然科学基金资助项目(51975407)