Abstract
This paper aims to develop a practical tire model that keeps the balance between generalization ability and accuracy for Formula Student application. Up to now, the advantages of Artificial Neural Networks for tire modelling have been investigated by some studies, which are briefly introduced in this paper. However, tire models based on Artificial Neural Networks were likely to over-fit the given data, or were sensitive to the noise. And far too title attention has been paid for the generalization ability, which is essential for a tire model. In this paper, a Bayesian regularization method based on the Bayes’ theorem is proposed to solve the major problems described above by improving the generalization ability. And a large number of measured data were used for testing the trained models with different configurations. The results show that the tire models based on the Bayesian regularized artificial neural networks can achieve better generalization ability, and are practical for racing applications such as Formula Student.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Xiong G, Li B, Chai X (2001) Virtual prototyping technology. J Syst Simul 13(1):114–117 (in Chinese)
Harsh D, Shyrokau B (2019) Tire model with temperature effects for formula SAE vehicle. Appl Sci 9(24)
Guo K (2016) UniTire: unified tire model. J Mech Eng 52(12):90–99 (in Chinese)
Zhao Q, Wang W, Luo L, Zheng L, Li J (2016) Modeling and simulation of automotive handling and stability based on laternal model of UniTtire. Sci Technol Eng 16(32):127–131 (in Chinese)
Li J, Gao X, Wang W, Zhang C (2018) A collaborative study on ride comfort and handling stability based on UniTire models. Automot Eng 40(2):127–132 (in Chinese)
Rumelhart D, Hinton G, Williams R (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536
Cybenko G (1989) Approximation by superposition of a sigmoidal function. Math Control Signals Syst 2(4):303–314
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
Cotter NE (1990) The Stone-Weierstrass theorem and its application to neural networks. IEEE Trans Neural Netw 1(4):290–295
Ito Y (1991) Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Netw 4(3):385–394
Chen T, Chen H, Liu RW (1995) Approximation capability in C(Rn) by multilayer feedforward networks and related problems. IEEE Trans Neural Netw 6(1):25–30
Palkovics L, El-Gindy M, Pacejka HB (1996) Application of neural networks to tyre modelling for vehicle simulation. Heavy Vehicle Systems, Special Series. Int J Veh Des 3(1–4):323–345
Long C, Chen H (2010) Comparative study between the magic formula and the neural network tire model based on genetic algorithm. In: Third international symposium on intelligent information technology & security informatics. IEEE Computer Society
Wang J, Liu Y, Ding L et al (2018) Neural network identification of a racing car tire model. J Eng 2018:1–11
Mao X, Mao J, Wang D (2019) Research on tire rolling resistance modeling based on RBF neural network. China Rubber Ind 66(10):739–743 (in Chinese)
Li D (2008) Study on integrated vehicle dynamics control based on optimal tire force distribution. Shanghai Jiao Tong University (in Chinese)
Wei H, Xu S, Song W (2001) Generalization theory and generalization methods for neural networks. Acta Autom Sin (06):806–815 (in Chinese)
Song L, Huang T, Fang J, Zhou X (2008) Conversion of GPS height based on Bayesian regularization BP neural network. J Southwest Jiaotong Univ 43(6):724–728 (in Chinese)
Bain LJ, Engelhardt M (1991) Introduction to probability and mathematical statistics, 2nd edn. Duxbury Press, California, p 382
MacKay DJC (1992) Bayesian interpolation. Neural Comput 4(3):415–447
Burden F, Winkler D (2009) Bayesian regularization of neural networks. Methods Mol Biol 458:23–42
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Huang, H., Chen, T., Huang, J., Feng, Z., Mo, Z., Wu, T. (2022). The Generalization Ability of the Tire Model Based on Bayesian Regularized Artificial Neural Network. In: Proceedings of China SAE Congress 2020: Selected Papers. Lecture Notes in Electrical Engineering, vol 769. Springer, Singapore. https://doi.org/10.1007/978-981-16-2090-4_16
Download citation
DOI: https://doi.org/10.1007/978-981-16-2090-4_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2089-8
Online ISBN: 978-981-16-2090-4
eBook Packages: EngineeringEngineering (R0)