نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده مهندسی صنایع و سیستم‌ها، دانشگاه تربیت مدرس، تهران، ایران.

10.22105/dmor.2022.310377.1504

چکیده

در این مقاله، پس از به دست آوردن مدل یادگیری تقویتی زمانبندی با در نظر گرفتن نت پیشگویانه، چندین رویکرد ابتکاری برای ارزیابی مدل مطرح شده است. برای اینکه یک مدل یادگیری تقویتی آموزش داده شود، باید تابع پاداش و زیان آن با توجه به شرایط محیط کارگاه، تعیین شود. یکی از نوآوری های مقاله ارائه تعریف تابع پاداش برای مسئله مورد نظر می باشد. این مدل یادگیری در حالت های مختلف ورود کار به کارگاه مورد بررسی قرار گرفته و نتایج به دست آمده از روش های دیگر زمانبندی، خروجی های بهتری را از خود نشان می‌دهد. مدل نت پیشگویانه، با چهار روش مدل سازی یادگیری مورد ارزیابی و کیفیت مدل ها مورد بررسی قرار می گیرد. با انتخاب و اضافه کردن بهترین مدل خرابی ماشین به مدل یادگیری تقویتی زمانبندی، کارهای بلادرنگ وارد شده به کارگاه، به ماشین ها تخصیص داده می شوند. با مقایسه روش مطرح شده و روش های پیشین مشخص شد که بهترین عملکرد را از خود نشان داده است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Online Job Shop Scheduling and Dynamic Predictive Maintenance by Machine Learning

نویسندگان [English]

  • Haed Tavakkoli-Moghaddam
  • Seyed Hesamoddin Zegordi
  • Mohammad Reza Amin-Nasseri

Faculty of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran.

چکیده [English]

This paper proposes several innovative approaches to model evaluation after obtaining the reinforcement learning model of scheduling with predictive maintenance. To train this model, its reward and loss function must be determined according to the conditions of the workshop environment. One of the innovations of this paper is to provide a definition of the reward function for the issue. This learning model is examined in different modes of work entry into the workshop and the results obtained from other scheduling methods show better outputs. The predictive maintenance model is evaluated by four learning methods and the quality of these models is examined. By selecting and adding the best machine failure model to the scheduling reinforcement learning model, the instant tasks entered into the workshop are assigned to the machines. By comparing the proposed method with the previous ones, the best performance is found and shown.

کلیدواژه‌ها [English]

  • Real-time scheduling
  • Predictive Maintenance
  • Machine Learning
  • Reinforcement Learning
  • Data Mining
Abdulkareem, N. M., & Abdulazeez, A. M. (2021). Machine learning classification based on Radom Forest algorithm: a review. International journal of science and business5(2), 128-142.
Allahverdi, A. (2015). The third comprehensive survey on scheduling problems with setup times/costs. European journal of operational research246(2), 345-378. https://doi.org/10.1016/j.ejor.2015.04.004
An, D., Kim, N. H., & Choi, J. H. (2015). Practical options for selecting data-driven or physics-based prognostics algorithms with reviews. Reliability engineering & system safety133, 223-236. https://doi.org/10.1016/j.ress.2014.09.014
Bouazza, W., Hamdadou, D., Sallez, Y., & Trentesaux, D. (2019). Effective dynamic selection of smart products scheduling rules in FMS. Manufacturing letters20, 45-48. https://doi.org/10.1016/j.mfglet.2019.05.004
Bousdekis, A., Lepenioti, K., Apostolou, D., & Mentzas, G. (2019). Decision making in predictive maintenance: literature review and research agenda for industry 4.0. IFAC-Papersonline52(13), 607-612. https://doi.org/10.1016/j.ifacol.2019.11.226
Diggle, P. J., Chetwynd, A. G., & Chetwynd, A. (2011). Statistics and scientific method: an introduction for students and researchers. Oxford University Press. https://academic.oup.com/book/26710
Ðurasević, M., & Jakobović, D. (2018). A survey of dispatching rules for the dynamic unrelated machines environment. Expert systems with applications113, 555-569. https://doi.org/10.1016/j.eswa.2018.06.053
Fink, O. (2020). Data-driven intelligent predictive maintenance of industrial assets. In Women in industrial and systems engineering (pp. 589-605). Springer, Cham. https://doi.org/10.1007/978-3-030-11866-2_25
Gao, R., Wang, L., Teti, R., Dornfeld, D., Kumara, S., Mori, M., & Helu, M. (2015). Cloud-enabled prognosis for manufacturing. CIRP annals64(2), 749-772. https://doi.org/10.1016/j.cirp.2015.05.011
Márquez, F. P. G., Tobias, A. M., Pérez, J. M. P., & Papaelias, M. (2012). Condition monitoring of wind turbines: techniques and methods. Renewable energy46, 169-178. https://doi.org/10.1016/j.renene.2012.03.003
Gorriz, J. M., & Suckling, J. (2020). A connection between the pattern classification problem and the General Linear Model for statistical inference. IEEE journal of biomedical and health informatics. DOI: 10.1109/JBHI.2021.3101662
Gu, C., He, Y., Han, X., & Chen, Z. (2017). Product quality oriented predictive maintenance strategy for manufacturing systems. 2017 prognostics and system health management conference (phm-harbin) (pp. 1-7). IEEE. DOI: 10.1109/PHM.2017.8079213
Hwang, S., Jeong, J., & Kang, Y. (2018). SVM-RBM based predictive maintenance scheme for IoT-enabled smart factory. 2018 thirteenth international conference on digital information management (ICDIM) (pp. 162-167). IEEE. DOI: 10.1109/ICDIM.2018.8847132
Kalathas, I., & Papoutsidakis, M. (2021). Predictive maintenance using machine learning and data mining: a pioneer method implemented to Greek railways. Designs5(1), 5. https://doi.org/10.3390/designs5010005
Modoni, G. E., Trombetta, A., Veniero, M., Sacco, M., & Mourtzis, D. (2019). An event-driven integrative framework enabling information notification among manufacturing resources. International journal of computer integrated manufacturing32(3), 241-252. https://doi.org/10.1080/0951192X.2019.1571232
Jimenez, J. J. M., Schwartz, S., Vingerhoeds, R., Grabot, B., & Salaün, M. (2020). Towards multi-model approaches to predictive maintenance: a systematic literature survey on diagnostics and prognostics. Journal of manufacturing systems56, 539-557. https://doi.org/10.1016/j.jmsy.2020.07.008
Sakib, N., & Wuest, T. (2018). Challenges and opportunities of condition-based predictive maintenance: a review. Procedia cirp78, 267-272. https://doi.org/10.1016/j.procir.2018.08.318
Takata, S., Kirnura, F., van Houten, F. J., Westkamper, E., Shpitalni, M., Ceglarek, D., & Lee, J. (2004). Maintenance: changing role in life cycle management. CIRP annals53(2), 643-655. https://doi.org/10.1016/S0007-8506(07)60033-X
Tidriri, K., Chatti, N., Verron, S., & Tiplica, T. (2016). Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: a review of researches and future challenges. Annual reviews in control42, 63-81. https://doi.org/10.1016/j.arcontrol.2016.09.008
Wang, L., Hu, X., Wang, Y., Xu, S., Ma, S., Yang, K., ... & Wang, W. (2021). Dynamic job-shop scheduling in smart manufacturing using deep reinforcement learning. Computer networks190, 107969. https://doi.org/10.1016/j.comnet.2021.107969
Yadav, A., & Jayswal, S. C. (2018). Modelling of flexible manufacturing system: a review. International journal of production research56(7), 2464-2487. https://doi.org/10.1080/00207543.2017.1387302
Zhang, W., Yang, D., & Wang, H. (2019). Data-driven methods for predictive maintenance of industrial equipment: a survey. IEEE systems journal13(3), 2213-2227. DOI: 10.1109/JSYST.2019.2905565