Advertisement

A Grey Box Model Approach for the Prediction of Tire Energy Loss

  • Michael Burger
  • Stefan SteidelEmail author
Conference paper
  • 8 Downloads
Part of the Lecture Notes in Mechanical Engineering book series (LNME)

Abstract

The maintenance costs of vehicles, and particularly commercial vehicles, are influenced by rolling resistance and tread wear of tires. In this context, the tire label is established in Europe for indicating the energy efficiency of a tire, although the respective test procedures do not reflect realistic application scenarios in daily use. Therefore, we propose a grey box model approach for predicting rolling resistance and tread wear of tires, i.e., tire energy losses, as a function of route, vehicle, driver and traffic parameters by means of physical models for the vehicle and tire dynamics in combination with machine learning techniques. This enables the prediction of tire energy loss for different customer groups in arbitrary regions around the world under realistic conditions.

Keywords

Tire simulation Tire energy loss Machine learning Neural networks Support vector machines 

Notes

Acknowledgement

The authors thank Amrut Pisolkar and the CDTire-Team for supporting the generation of the training data via CDTire/Driver. Moreover, we thank Simon Gottschalk for assisting the analysis of the present validation data.

References

  1. 1.
    Barber, D.: Bayesian Reasoning and Machine Learning. Cambridge University Press, New York (2012)zbMATHGoogle Scholar
  2. 2.
    Bishop, C.: Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, Heidelberg (2006)Google Scholar
  3. 3.
    Gallrein, A., Bäcker, M., Gizatullin, A.: Structural MBD tire models: closing the gap to structural analysis - history and future of parameter identification. SAE Technical Paper 2013-01-0630 (2013)Google Scholar
  4. 4.
    Calabrese, F., Bäcker, M., Galbally, C., Gallrein, A.: A detailed thermo-mechanical tire model for advanced handling applications. SAE Int. J. Passeng. Cars – Mech. Syst. 8(2), 501–511 (2015)CrossRefGoogle Scholar
  5. 5.
    Halfmann, T., Steidel, S., Gallrein, A., Dreßler, K., Pasalkar, V.: Extrapolation of rolling resistance for truck tires from specific load cases to vehicle usage in the field. In: Berns, K. et al. (eds.): Commercial Vehicle Technology 2016, Shaker, pp. 470–478 (2016)Google Scholar
  6. 6.
    Murphy, K.: Machine Learning. The MIT Press, Cambridge (2012)zbMATHGoogle Scholar
  7. 7.
    Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Steidel, S., Halfmann, T., Bäcker, M., Gallrein, A.: Prediction of rolling resistance and tread wear of tires in realistic commercial vehicle application scenarios. SAE Technical Paper 2016-01-8027 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department Dynamics, Loads and Environmental Data DLU, Division Mathematics for Vehicle Engineering MFFraunhofer Institute for Industrial Mathematics ITWMKaiserslauternGermany

Personalised recommendations