Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon openaccess Secure and communications-efficient collaborative prognosis

Collaborative prognosis is a technique that is used to enable assets to improve their ability to predict failures by learning from the failures of similar other assets. This is typically made possible by enabling the assets to communicate with each other. The key enabler of current collaborative prognosis techniques is that they require assets to share their sensor data and failure information between each other, which might be a major constraint due to commercial sensitivities, especially when the assets belong to different companies. This study uses federated learning to address this issue and examines whether this technique will enable collaborative prognosis while ensuring sensitive operational data is not shared between organisational boundaries. An example implementation is demonstrated for the prognosis of a simulated turbofan fleet, where federated averaging algorithm is used as an alternative for the data exchange step. Its performance is compared with a conventional collaborative prognosis that involves failure data exchange. The results confirm that federated averaging retains the performance of conventional collaborative prognosis while eliminating the exchange of failure data within assets. This removes a critical hindrance in industrial adoption of collaborative prognosis, thus enhancing the potential of predictive maintenance.

References

    1. 1)
      • 16. Leitão, P., Karnouskos, S.: ‘Industrial agents: emerging applications of software agents in industry’ (Elsevier Inc., Netherlands, 2015).
    2. 2)
      • 24. Ranasinghe, G.D., Lindgren, T., Girolami, M., et al: ‘A methodology for prognostics under the conditions of limited failure data availability’, IEEE Access, 2019, 7, pp. 183996184007.
    3. 3)
      • 32. Saxena, A., Goebel, K.: ‘Turbofan engine degradation simulation data set’, Tech. Rep., NASA Ames Research Center, Moffett Field, CA, 2008.
    4. 4)
      • 3. Schwabacher, M., Goebel, K.: ‘A survey of artificial intelligence for prognostics’. AAAI Fall Symp.: Artificial Intelligence for Prognostics, Virginia, USA, 2007.
    5. 5)
      • 4. Jain, A.K., Lad, B.K.: ‘Data driven models for prognostics of high speed milling cutters’, Int. J. Performability Eng., 2016, 12, (1), pp. 311.
    6. 6)
      • 11. Salvador Palau, A., Dhada, M.H., Parlikad, A.K.: ‘Multi-agent system architectures for collaborative prognostics’, J. Intell. Manuf., 2019, 30, pp. 29993013.
    7. 7)
      • 34. Herrera, M., Pérez-Hernández, M., Kumar Parlikad, A., et al: ‘Multi-agent systems and complex networks: review and applications in systems engineering’, Processes, 2020, 8, p.312.
    8. 8)
      • 2. Neely, A.: ‘Exploring the financial consequences of the servitization of manufacturing’, Oper. Manage. Res., 2008, 1, pp. 103118.
    9. 9)
      • 35. Yong, B.X., Brintrup, A.: ‘Multi agent system for machine learning under uncertainty in cyber physical manufacturing system’. Int. Workshop on Service Orientation in Holonic and Multi-agent Manufacturing, Germany, 2019, pp. 244257.
    10. 10)
      • 33. Saxena, A., Goebel, K., Simon, D., et al: ‘Damage propagation modeling for aircraft engine run-to-failure simulation’. 2008 Int. Conf. on Prognostics and Health Management, PHM 2008, Denver, USA, 2008.
    11. 11)
      • 20. Siemieniuch, C.E., Sinclair, M.A.: ‘On complexity, process ownership and organisational learning in manufacturing organisations, from an ergonomics perspective’, Appl. Ergon., 2002, 33, pp. 449462.
    12. 12)
      • 5. Lee, J., Jin, C., Liu, Z., et al: ‘Introduction to data-driven methodologies for prognostics and health management’ InEkwaro Osire, S., Carlos Gonçalves, A., Alemayehu, F., et al (Eds.): ‘Probabilistic prognostics and health management of energy systems’ (Springer, Switzerland, 2017), pp. 932.
    13. 13)
      • 6. Jain, A.K., Lad, B.K.: ‘Dynamic optimization of process quality control and maintenance planning’, IEEE Trans. Reliab., 2017, 66, pp. 502517.
    14. 14)
      • 9. Salvador Palau, A., Dhada, M.H., Bakliwal, K., et al: ‘An industrial multi agent system for real-time distributed collaborative prognostics’, Eng. Appl. Artif. Intell., 2019, 85, pp. 590606.
    15. 15)
      • 26. Bonawitz, K., Eichner, H., Grieskamp, W., et al: ‘Towards federated learning at scale: system design’, arXiv preprint arXiv:1902.01046, February 2019.
    16. 16)
      • 31. McMahan, H.B., Moore, E., Ramage, D., et al: ‘Communication-efficient learning of deep networks from decentralized data’. Proc. 20th Int. Conf. on Artificial Intelligence and Statistics, AISTATS 2017, Florida, USA, February 2016.
    17. 17)
      • 40. Ambrosio, J.K., Brentan, B.M., Herrera, M., et al: ‘Committee machines for hourly water demand forecasting in water supply systems’, Math. Probl. Eng., 2019, 2019, p. 9765468.
    18. 18)
      • 18. Gilchrist, A., Gilchrist, A.: ‘IIoT reference architecture’ in Gilchrist, A. (Ed.): ‘Industry 4.0’ (Apress, United States, 2016), pp. 6586.
    19. 19)
      • 25. Bekkerman, R., Bilenko, M., Langford, J.: ‘Scaling up machine learning: parallel and distributed approaches’ (Cambridge University Press, United Kingdom, 2011).
    20. 20)
      • 10. Palau, A.S., Bakliwal, K., Dhada, M.H., et al: ‘Recurrent neural networks for real-time distributed collaborative prognostics’. 2018 IEEE Int. Conf. on Prognostics and Health Management, ICPHM 2018, Institute of Electrical and Electronics Engineers Inc., August 2018.
    21. 21)
      • 13. Lin, Y., Liu, S., Huang, S.: ‘Selective sensing of a heterogeneous population of units with dynamic health conditions’, IISE Trans., 2018, 50, pp. 10761088.
    22. 22)
      • 21. Konečný, J., McMahan, H.B., Yu, F.X., et al: ‘Federated learning: strategies for improving communication efficiency’, arXiv preprint arXiv:1610.05492, October 2016.
    23. 23)
      • 19. Sadeghi, A.R., Wachsmann, C., Waidner, M.: ‘Security and privacy challenges in industrial internet of things’. Proc. – Design Automation Conf., vol. 2015-July, Institute of Electrical and Electronics Engineers Inc., San Francisco, USA, July 2015.
    24. 24)
      • 8. Bakliwal, K., Dhada, M.H., Palau, A.S., et al: ‘A multi agent system architecture to implement collaborative learning for social industrial assets’, IFAC-PapersOnLine, 2018, 51, pp. 12371242.
    25. 25)
      • 30. Lecun, Y., Bengio, Y., Hinton, G.: ‘Deep learning’, Nature, 2015, 521, pp. 436444.
    26. 26)
      • 27. Huang, L., Yin, Y., Fu, Z., et al: ‘Loadaboost:loss-based AdaBoost federated machine learning on medical data’, arXiv preprint arXiv:1811.12629, November 2018.
    27. 27)
      • 15. Mcfarlane, D.: ‘Industrial internet of things applying IoT in the industrial context’, Tech. Rep., Institute for Manufacturing, University of Cambridge, 2019.
    28. 28)
      • 7. Salvador Palau, A., Liang, Z., Lütgehetmann, D., et al: ‘Collaborative prognostics in social asset networks’, Future Gener. Comput. Syst., 2019, 92, pp. 987995.
    29. 29)
      • 14. Eker, O.F., Camci, F., Jennions, I.K.: ‘A similarity-based prognostics approach for remaining useful life prediction’. Second European Conf. of the Prognostics and Health Management Society, Nantes, France, May 2014.
    30. 30)
      • 17. Saha, B., Saha, S., Goebel, K.: ‘A distributed prognostic health management architecture’. Sixth Int. Conf. on Condition Monitoring and Machinery Failure Prevention Technologies – CM/MFPT, Dublin, Ireland, 2009.
    31. 31)
      • 36. Wooldridge, M.: ‘An introduction to multiagent systems’ (John Wiley & Sons, Ltd, 2009).
    32. 32)
      • 37. Kingma, D.P., Ba, J.L.: ‘Adam: A method for stochastic optimization’. 3rd Int. Conf. on Learning Representations, ICLR 2015 – Conf. Track Proc., Int. Conf. on Learning Representations, ICLR, San Diego, USA, December 2015.
    33. 33)
      • 29. Li, T., Sahu, A.K., Zaheer, M., et al: ‘Federated optimization in heterogeneous networks’, arXiv preprint arXiv:1812.06127, December 2018.
    34. 34)
      • 28. Hard, A., Rao, K., Mathews, R., et al: ‘Federated learning for Mobile keyboard prediction’, arXiv preprint arXiv:1811.03604, November 2018.
    35. 35)
      • 39. Pearce, T., Zaki, M., Brintrup, A., et al: ‘High-quality prediction intervals for deep learning: a distribution-free, ensembled approach’. 35th Int. Conf. on Machine Learning, ICML 2018, Int. Machine Learning Society (IMLS), Stockholm, Sweden, February 2018, vol. 9, pp. 64736482.
    36. 36)
      • 1. Goyal, D., Pabla, B.S.: ‘Condition based maintenance of machine tools – a review’, CIRP J. Manuf. Sci. Technol., 2015, 10, pp. 2435.
    37. 37)
      • 12. Wang, T., Yu, J., Siegel, D., et al: ‘A similarity-based prognostics approach for remaining useful life estimation of engineered systems’. 2008 Int. Conf. on Prognostics and Health Management, PHM 2008, Denver, USA, 2008.
    38. 38)
      • 38. Dhada, M.H., Palau, A.S., Parlikad, A.K.: ‘Federated learning for collaborative prognosis’. Int. Conf. on Precision, Meso, Micro, and Nano Engineering, IIT Indore, India, 2019.
    39. 39)
      • 22. Yang, Q., Liu, Y., Chen, T., et al: ‘Federated machine learning: concept and applications’, ACM Trans. Intell. Syst. Technol., 2019, 10, pp. 119.
    40. 40)
      • 23. Li, T., Sahu, A.K., Talwalkar, A., et al: ‘Federated learning: challenges, methods, and future directions’, arXiv preprint arXiv:1908.07873, August 2019.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cim.2020.0035
Loading

Related content

content/journals/10.1049/iet-cim.2020.0035
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address