Data-based real-time scheduling in smart manufacturing

WU Xiu-li1 SUN Lin1

(1.School of Mechanic Engineering, University of Science and Technology Beijing, Beijing 100083)
【Knowledge Link】genetic algorithm

【Abstract】The smart manufacturing system employs a large number of advanced information technologies, which makes it possible to collect real-time data in production systems. The wide application of various types of information technology in the manufacturing process has enabled the manufacturing system to accumulate a large amount of data relating to production scheduling. Therefore, the historical production scheduling data and the real-time production data collected by smart equipment are used to establish a data-driven production scheduling method. With regard to real-time hybrid flow shop scheduling problems, a real-time data-driven scheduling method based on the BP neural network is proposed. Firstly, the sample data for scheduling knowledge mining is extracted from the historical optimal and near-optimal scheduling scenarios. Through the BP neural network, the mapping relationship network between the production system state and the dispatching rules is obtained, which is then applied to online real-time scheduling. Finally, numerical experiments verify that the proposed method outperforms the fixed single dispatching rule, which is stable under different scheduling objectives.

【Keywords】 smart manufacturing; hybrid flow shop; real-time scheduling; machine learning; artificial neural network;

【DOI】

【Funds】 National Natural Science Foundation of China (51305024)

Download this article

    References

    [1] Zhou J. Intelligent manufacturing-main direction of “made in China 2025” [J]. China Mechanical Engineering, 2015, 26 (17): 2273–2284 (in Chinese).

    [2] Ji Z, Li P, Zhou Y, et al. Toward new-generation intelligent manufacturing [J]. Engineering, 2018, 4 (1): 11–20.

    [3] Dai H M, Dai P H. 4. 0 industrial and intelligent machinery plant [J]. Packaging Engineering, 201637 (19): 206–211 (in Chinese).

    [4] Zhong R Y, Xu X, Klotz E, et al. Intelligent manufacturing in the context of industry 4. 0: A review [J]. Engineering2017, 3 (5): 616–630.

    [5] Ma Y, Qiao F, Lu J. Learning-based dynamic scheduling of semiconductor manufacturing system [C]. IEEE International Conference on Automation Science and Engineering. Texas: IEEE, 2016: 1394–1399.

    [6] Wu W, Ma Y, Qiao F, et al. Data mining based dynamic scheduling approach for semiconductor manufacturing system [C]. . Control Conference. Hangzhou: IEEE, 2015: 2603–2608.

    [7] Yuan L, Wang J Q, Chen Y X. Research on inference method of scheduling in dynamic workshop [J]. Agricultural Equipment & Vehicle Engineering, 201755 (12): 89–92 (in Chinese).

    [8] Bouazza W, Sallez Y, Beldjilali B. A distributed approach solving partially flexible job-shop scheduling problem with a Q-learning effect [J]. IFAC-Papers Online, 201750 (1): 15890–15895.

    [9] Wu Q D, Ma Y M, Li L, et al. Data-driven dynamic scheduling method for semicondutor production line [J]. Control Theory & Applications, 2015, 32 (9): 1233–1239 (in Chinese).

    [10] Zhang J, Qin W, Wu L H, et al. Fuzzy neural network-based rescheduling decision mechanism for semiconductor manufacturing [J]. Computers in Industry2014, 65 (8): 1115–1125.

    [11] Li L, Sun Z, Ni J, et al. Data-based scheduling framework and adaptive dispatching rule of complex manufacturing systems [J]. International Journal of Advanced Manufacturing Technology, 201366 (9/10/11/12): 1891–1905.

    [12] Su N, Zhang M, Johnston M, et al. Automatic programming via iterated local search for dynamic job shop scheduling [J]. IEEE Transactions on Cybernetics 2015, 45 (1): 1–14.

    [13] Zhang Y F, Wang J, Liu Y. Game theory based real-time multi-objective flexible job shop scheduling considering environmental impact [J]. Journal of Cleaner Production 2017, 167: 665–679.

    [14] Wang C L, Rong G, Weng W, et al. Mining scheduling knowledge for job shop scheduling problem [J]. IFACPapers on Line, 2015, 48 (3): 800–805.

    [15] Priore P, Pino R, Parreño J, et al. Real-time scheduling of flexible manufacturing systems using support vector machines and case-based reasoning [J]. Applied Artificial Intelligence, 2015, 3 (1): 54–59.

    [16] Olafsson S, Li X. Learning effective new single machine dispatching rules from optimal scheduling data [J]. International Journal of Production Economics, 2010128 (1): 118–126.

    [17] Wu L H. Research on proactive and reactive scheduling for mould manufacturing workshop under uncertain environments [D]. Guangzhou: School of Electro-Mechanical Engineering, Guangdong University of Technology, 2013 (in Chinese).

    [18] Luo H, Fang J, Huang G Q. Real-time scheduling for hybrid flowshop in ubiquitous manufacturing environment [J]. Computers & Industrial Engineering2015, 84: 12–23.

    [19] Chen B. Research on optimization and control methods for process based on data-driven [D]. Shenyang: Colledge of Information Science and Engineering, Northeastern University, 2011 (in Chinese).

    [20] Sieniutycz S, Szwast Z. 4-neural networks-Areview of applications [J]. Optimizing Thermal Chemical & Environmental Systems, DOI: 10.1016/B978-0-12-813582-2.00004-5.

    [21] Veronique Sels, Nele Gheysen, Mario Vanhoucke A comparison of priority rules for the job shop scheduling problem under different flow time-and tardiness-related objective functions [J]. International Journal of Production Research, 2012, 50 (15): 4255–4270.

    [22] Branke J, Su N, Pickardt C W, et al. Automated design of production scheduling heuristics: A review [J]. IEEE Transactions on Evolutionary Computation, 2016, 20 (1): 110–124.

    [23] Branke J, Pickardt C W. Evolutionary search for difficult problem instances to support the design of job shop dispatching rules [J]. European Journal of Operational Research, 2011, 212 (1): 22–32.

    [24] Zhao Z Y, Xu Y M. Introduction to fuzzy theory and neural networks and their application [M]. Beijing: Tsinghua University Press, 1996: 85–86 (in Chinese).

This Article

ISSN:1001-0920

CN: 21-1124/TP

Vol 35, No. 03, Pages 523-535

March 2020

Downloads:11

Share
Article Outline

Knowledge

Abstract

  • 0 Introduction
  • 1 Hybrid flow shop structure in smart manufacturing
  • 2 Real-time scheduling method of hybrid flow shops in smart manufacturing system
  • 3 Numerical experiment
  • 4 Conclusion
  • References