Optimization of the tire ice traction using combined Levenberg–Marquardt (LM) algorithm and neural network
- 31 Downloads
In order to overcome prediction defects of the current tire friction mechanism model on ice surface, this paper puts forward a tire–rubber–ice surface traction prediction model by integrating the Levenberg–Marquardt (LM) optimizing algorithm with the neural network. With 125 groups of experimental data of different influencing factors as training samples, the LM optimizing algorithm is adopted to optimize the network model thus built. Meanwhile, the trained model is tested and compared with the other algorithms. Results suggest that the tire friction coefficient on different ice surfaces obtained by the algorithm proposed in this paper is the closest to the practical value with its overall error below 0.1%. Thus, the algorithm put forward in this paper can be directly applied to efficiently and accurately predict the friction characteristics between the tire and the ice surface and lay a solid foundation for the study of cars driving on the ice surface at a high speed.
KeywordsTire Ice Friction coefficient LM optimizing algorithm Neural network
This paper is sponsored by Chinese National Natural Science Foundation (No. 51605483), National Key Research and Development Program (No. 2017YFB1300900) and Science Foundation of National University of Defense Technology (No. ZK16-03-14, No. ZK17-03-02).
- 1.Sheng D, Feng S, Li H (2012) Research on effect of torque characteristic of friction lining limited slip differential on vehicle handling stability. Automob Technol 295(5553):336–338. https://doi.org/10.3969/j.issn.1000-3703.2012.04.007 CrossRefGoogle Scholar
- 6.Shimizu K, Ikeya C (1989) Indoor test of ice and snow tires on iced drum-development of tester and characteristics of coated ice for test. SAE technical paper 890004. https://doi.org/10.4271/890004
- 7.Nordström O (1993) The VTI flat bed tyre test facility—a new tool for testing commercial tyre characteristics. SAE technical paper 933006. https://doi.org/10.4271/933006
- 8.Peng X, Xie Y, Guo K (2000) A new method for determining tire traction on ice. SAE technical paper 2000-01-1640. https://doi.org/10.4271/2000-01-1640
- 9.Sandu C, Taylor B, Biggans J, Ahmadian M (2008) Building an infrastructure for indoor terramechanics studies: the development of a Terramechanics Rig at Virginia Tech. In: Proceedings of the 16th international conference of the international society for terrain vehicle system (ISTVS), Turin, Italy, vol 30, p 9Google Scholar
- 11.Hunter J (1993) Reconstructing collision involving ice and slippery surfaces. SAE technical paper 930896. https://doi.org/10.4271/930896
- 14.ASTM F1572-08. Standard test methods for tire performance testing on snow and ice surfaces. http://www.astm.org
- 15.ASTM F1572-08. Standard test methods for single wheel driving traction in a straight line on snow and ice-covered surfaces. http://www.astm.org
- 16.Pottinger M, McIntyre J, Kempainen A, Pelz W (2000)Truck tire force and moment in cornering—braking—driving on ice, snow, and dry surfaces. SAE technical paper 2000-01-3431. https://doi.org/10.4271/2000-01-3431
- 24.Ojala N, Valtonen K, Kivikytö-Reponen P (2015) High speed slurry-pot erosion wear testing with large abrasive particles. Tribol Finn J Tribol 33(1):36–44Google Scholar
- 26.Deo RC, Şahin M (2015) Application of the artificial neural network model for prediction of monthly standardized precipitation and evapotranspiration index using hydrometeorological parameters and climate indices in eastern Australia. Atmos Res S161–162:65–81. https://doi.org/10.1016/j.atmosres.2015.03.018 CrossRefGoogle Scholar