Advertisement

Connected Vehicle Prognostics Framework for Dynamic Systems

  • Omar Makke
  • Oleg Gusikhin
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 874)

Abstract

Connected vehicle analytics has a promise to substantially advance vehicle prognostics and health management. However, the practical implementation of connected vehicle prognostics faces a number of challenges, such as the limitation of communication bandwidth resulting in potential loss of data that is critical for adequate prognostics models. The paper discusses a modelling framework for connected vehicle prognostics for dynamic systems that allows addressing connectivity limitations and memory constraints. The framework is based on a hybrid prognostics approach combining in-vehicle physics-based data aggregation model and cloud-based data-driven prognostics leveraging cross-vehicle and external data sources. The application of the framework is illustrated by models for brake pads wear and cabin air filter prognostics.

Keywords

Prognostics Connected vehicles Machine learning Big data analytics 

References

  1. 1.
    Gusikhin, O., Rychtyckyj, N., Filev, D.: Intelligent systems in the automotive industry: applications and trends. Knowl. Inf. Syst. 12, 147–168 (2007)CrossRefGoogle Scholar
  2. 2.
    Siegel, J., Erb, D., Sarma, S.: A survey of the connected vehicle landscape–architectures, enabling technologies, applications, and development areas. IEEE Trans. Intell. Transp. Syst. 19, 2391–2406 (2017)CrossRefGoogle Scholar
  3. 3.
    Zhang, Y., Gantt Jr., G., Rychlinski, M., Edwards, R., Correia, J., Wolf, C.: Connected vehicle diagnostics and prognostics, concept and initial practice. IEEE: Trans. Reliab. 58, 286–294 (2009)Google Scholar
  4. 4.
    Zagajac, J., Chopra, A., Krivtsov, V., Gusikhin, O.: Method and apparatus for connected vehicle system wear estimation and maintenance scheduling. US Patent Application US2016/0163130 A1 (2016)Google Scholar
  5. 5.
    Pecht, M.: Prognostics and Health Management of Electronics. Wiley-Interscience, New York (2008)Google Scholar
  6. 6.
    Zhang, S., Chen, W., Li, Y.: Wear of friction material during vehicle braking. In: SAE Technical Paper 2009-01-1032 (2009)Google Scholar
  7. 7.
    Bakar, A.R.A., Ouyang, H., Khai, L.C., Abdullah, M.S.: Thermal analysis of a disc brake model considering a real brake pad surface and wear. Int. J. Veh. Struct. Syst. 2(1), 20–27 (2010)Google Scholar
  8. 8.
    Kambhampati, C., Graces, F., Warwick, K.: Approximation of non-autonomous dynamic systems by continuous time recurrent neural networks. In: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (2000)Google Scholar
  9. 9.
    Billings, E.C.: Effects of particle accumulation in aerosol filtration. Ph.D. dissertation, California Institute of Technology. http://resolver.caltech.edu/CaltechETD:etd-09172002-113217. Accessed 14 May 2018

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Research and Advanced Engineering, Ford Motor CompanyDearbornUSA

Personalised recommendations