SOPHIA: An Event-Based IoT and Machine Learning Architecture for Predictive Maintenance in Industry 4.0

Information (Switzerland) - Tập 11 Số 4 - Trang 202
Matteo Calabrese1, Martin Cimmino1, Francesca Fiume1, Martina Manfrin1, Luca Romeo2, Silvia Ceccacci3, Marina Paolanti2, Giuseppe Toscano4, Giovanni Ciandrini4, Alberto Carrotta4, Maura Mengoni3, Emanuele Frontoni2, Dimos Kapetis1
1Accenture Digital, ICEG Artificial Intelligence Center of Excellence (CoE), viale Monza 265-259, 20126 Milan, Italy;
2Dipartimento di Ingegneria dell'Informazione, Università Politecnica delle Marche, viale Brecce Bianche 12, 60131 Ancona, Italy;
3Dipartimento di Ingegneria di Ingegneria Industriale e Scienze Matematiche, Università Politecnica delle Marche, viale Brecce Bianche 12, 60131 Ancona, Italy;
4BIESSE GROUP SpA, viale della Meccanica 16, 61122 Pesaro, Italy;

Tóm tắt

Predictive Maintenance (PdM) is a prominent strategy comprising all the operational techniques and actions required to ensure machine availability and to prevent a machine-down failure. One of the main challenges of PdM is to design and develop an embedded smart system to monitor and predict the health status of the machine. In this work, we use a data-driven approach based on machine learning applied to woodworking industrial machines for a major woodworking Italian corporation. Predicted failures probabilities are calculated through tree-based classification models (Gradient Boosting, Random Forest and Extreme Gradient Boosting) and calculated as the temporal evolution of event data. This is achieved by applying temporal feature engineering techniques and training an ensemble of classification algorithms to predict Remaining Useful Lifetime (RUL) of woodworking machines. The effectiveness of the proposed method is showed by testing an independent sample of additional woodworking machines without presenting machine down. The Gradient Boosting model achieved accuracy, recall, and precision of 98.9%, 99.6%, and 99.1%. Our predictive maintenance approach deployed on a Big Data framework allows screening simultaneously multiple connected machines by learning from terabytes of log data. The target prediction provides salient information which can be adopted within the maintenance management practice.

Từ khóa


Tài liệu tham khảo

Fowler, 2011, A survey of problems, solution techniques, and future challenges in scheduling semiconductor manufacturing operations, J. Sched., 14, 583, 10.1007/s10951-010-0222-9

Susto, G.A., Schirru, A., Pampuri, S., Pagano, D., McLoone, S., and Beghi, A. (2013, January 17–21). A predictive maintenance system for integral type faults based on support vector machines: An application to ion implantation. Proceedings of the 2013 IEEE International Conference on Automation Science and Engineering (CASE), Madison, WI, USA.

Paolanti, M., Romeo, L., Felicetti, A., Mancini, A., Frontoni, E., and Loncarski, J. (2018, January 2–4). Machine learning approach for predictive maintenance in industry 4.0. Proceedings of the 2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), Oulu, Finland.

Susto, 2015, Multi-step virtual metrology for semiconductor manufacturing: A multilevel and regularization methods-based approach, Comput. Oper. Res., 53, 328, 10.1016/j.cor.2014.05.008

Romeo, 2020, Machine learning-based design support system for the prediction of heterogeneous machine parameters in industry 4.0, Expert Syst. Appl., 140, 112869, 10.1016/j.eswa.2019.112869

Romeo, L., Paolanti, M., Bocchini, G., Loncarski, J., and Frontoni, E. (2018, January 24–26). An Innovative Design Support System for Industry 4.0 Based on Machine Learning Approaches. Proceedings of the 2018 5th International Symposium on Environment-Friendly Energies and Applications (EFEA), Rome, Italy.

Susto, 2012, A predictive maintenance system for epitaxy processes based on filtering and prediction techniques, IEEE Trans. Semicond. Manuf., 25, 638, 10.1109/TSM.2012.2209131

Coleman, C., Coleman, C., Damodaran, S., Chandramouli, M., and Deuel, E. (2017). Making Maintenance Smarter: Predictive Maintenance and the Digital Supply Network, Deloitte University Press.

Fraser, 2011, A review of the three most popular maintenance systems: How well is the energy sector represented?, Int. J. Glob. Energy Issues, 35, 287, 10.1504/IJGEI.2011.045024

Chen, 1997, Issues in the continuous improvement process for preventive maintenance: Observations from Honda, Nippondenso and Toyota, Prod. Inventory Manag. J., 38, 13

Lei, 2016, A model-based method for remaining useful life prediction of machinery, IEEE Trans. Reliab., 65, 1314, 10.1109/TR.2016.2570568

Yoon, 2019, Life-cycle maintenance cost analysis framework considering time-dependent false and missed alarms for fault diagnosis, Reliab. Eng. Syst. Saf., 184, 181, 10.1016/j.ress.2018.06.006

Sakib, 2018, Challenges and Opportunities of Condition-based Predictive Maintenance: A Review, Procedia CIRP, 78, 267, 10.1016/j.procir.2018.08.318

Lei, 2018, Machinery health prognostics: A systematic review from data acquisition to RUL prediction, Mech. Syst. Signal Process., 104, 799, 10.1016/j.ymssp.2017.11.016

Sipos, R., Fradkin, D., Moerchen, F., and Wang, Z. (2014, January 24–27). Log-based predictive maintenance. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.

Wang, 2017, Predictive maintenance based on event-log analysis: A case study, IBM J. Res. Dev., 61, 11, 10.1147/JRD.2017.2648298

Jardine, 2006, A review on machinery diagnostics and prognostics implementing condition-based maintenance, Mech. Syst. Signal Process., 20, 1483, 10.1016/j.ymssp.2005.09.012

Heng, 2009, Intelligent condition-based prediction of machinery reliability, Mech. Syst. Signal Process., 23, 1600, 10.1016/j.ymssp.2008.12.006

Khan, 2018, A review on the application of deep learning in system health management, Mech. Syst. Signal Process., 107, 241, 10.1016/j.ymssp.2017.11.024

Xia, 2018, Recent advances in prognostics and health management for advanced manufacturing paradigms, Reliab. Eng. Syst. Saf., 178, 255, 10.1016/j.ress.2018.06.021

Goldszmidt, M. (2010). Bayesian network classifiers. Wiley Encyclopedia of Operations Research and Management Science, John Wiley & Sons, Inc.

Cavalieri, 2016, A BBN-based Method to Manage Adaptive Behavior of a Smart User Interface, Procedia CIRP, 50, 535, 10.1016/j.procir.2016.04.162

Ghahramani, Z. (1997). Learning dynamic Bayesian networks. International School on Neural Networks, Initiated by IIASS and EMFCSC, Springer.

Arroyo-Figueroa, G., and Sucar, L.E. (2013). A temporal Bayesian network for diagnosis and prediction. arXiv.

Salfner, F. (2005, January 20–22). Predicting Failures with Hidden Markov Models. Proceedings of the 5th European Dependable Computing Conference (EDCC-5), Budapest, Hungary.

Vrignat, 2015, Failure event prediction using hidden markov model approaches, IEEE Trans. Reliab., 64, 1038, 10.1109/TR.2015.2423191

Zhou, 2010, A model for real-time failure prognosis based on hidden Markov model and belief rule base, Eur. J. Oper. Res., 207, 269, 10.1016/j.ejor.2010.03.032

Canizo, M., Onieva, E., Conde, A., Charramendieta, S., and Trujillo, S. (2017, January 19–21). Real-time predictive maintenance for wind turbines using Big Data frameworks. Proceedings of the 2017 IEEE International Conference on Prognostics and Health Management (ICPHM), Dallas, TX, USA.

Bousdekis, A., Hribernik, K., Lewandowski, M., von Stietencron, M., and Thoben, K.D. (2019). A Unified Architecture for Proactive Maintenance in Manufacturing Enterprises. Enterprise Interoperability VIII, Springer.

Liu, Z., Jin, C., Jin, W., Lee, J., Zhang, Z., Peng, C., and Xu, G. (2018, January 11–13). Industrial AI Enabled Prognostics for High-speed Railway Systems. Proceedings of the 2018 IEEE International Conference on Prognostics and Health Management (ICPHM), Seattle, WA, USA.

Pedregosa, 2011, Scikit-learn: Machine learning in Python, J. Mach. Learn. Res., 12, 2825

Breiman, 2001, Random forests, Mach. Learn., 45, 5, 10.1023/A:1010933404324

Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.

Lipton, 2018, The mythos of model interpretability, Queue, 16, 31, 10.1145/3236386.3241340

Friedman, 2001, Greedy function approximation: A gradient boosting machine, Ann. Stat., 29, 1189, 10.1214/aos/1013203451

Shahzad, 2015, Failure prediction methodology for improved proactive maintenance using Bayesian approach, IFAC-PapersOnLine, 48, 844

Xu, 2019, A digital-twin-assisted fault diagnosis using deep transfer learning, IEEE Access, 7, 19990, 10.1109/ACCESS.2018.2890566

Gan, C.L. (2020). Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things, John Wiley & Sons, Inc.

Sun, B., Feng, J., and Saenko, K. (2016, January 12–17). Return of frustratingly easy domain adaptation. Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.

Thông tin
Thông tin xuất bản

Information (Switzerland)

Tập 11 Số 4

202

Thông tin tác giả