A multivariate multiple regression analysis of tire-road contact peak triaxial stress by using machine learning methods

Abstract

Predicting the tire-road contact triaxial stress is significant in assessing performance of vehicle and road surface material. However, both the Finite Element Method and the direct measurement method can only obtain contact stresses under several specific conditions, which is difficult to generalize. In this paper, a chain regression model is proposed, which hybridizes εSVR and ANN to improve forecasting accuracy in all directions by predicting uniaxial and triaxial stresses step by step. Meanwhile, the specific type of tire (185/65R15) under different conditions are simulated by using the 3 D finite element method for the dataset, and the factors affecting triaxial stress are analyzed by correlation analysis. Numerical examples from the above dataset reveal that the proposed εSVR-ANN chain model outperforms other multi-output regression models in all five directions in terms of forecasting accuracy. In addition, statistical tests verify the efficacy of the proposed method. This study provides a reference for the design of tire-road contact stress measurement and statistical scheme.

Keywords:

• Contact stress
• driving conditions
• machine learning
• multi-output regression
• regressor chains
• Tire model

Additional information

Funding

The research presented in this paper was financially supported by the 2018 National Key Scientific Instrument and Equipment Development Projects of China (No. 51827812), National Natural Science Foundation of China (No. 51578430 and No. 51778509) and Natural Science Foundation of Hubei Province (No. 2018CFB293).