This content is not included in your SAE MOBILUS subscription, or you are not logged in.
A Novel Prediction Algorithm for Heavy Vehicles System Rollover Risk Based on Failure Probability Analysis and SVM Empirical Model
- Dong Wang - Suzhou Zijing Qingyuan Automotive Co.Ltd ,
- Tianjun Zhu - Hebei University of Engineering ,
- Xiaoxuan Yin - Hebei University of Engineering ,
- Wei Ma - Hebei University of Engineering ,
- Zhenfeng Wang - China Automotive Technology and Reseach Center Co.,Ltd ,
- Fei Li - China Automotive Technology and Reseach Center Co.,Ltd ,
- Xinyu Wang - China Automotive Technology and Reseach Center Co.,Ltd ,
- Zheng Wang - Harbin Institute of Technology
ISSN: 2641-9637, e-ISSN: 2641-9645
Published April 14, 2020 by SAE International in United States
Citation: Zhu, T., Yin, X., Wang, Z., Wang, D. et al., "A Novel Prediction Algorithm for Heavy Vehicles System Rollover Risk Based on Failure Probability Analysis and SVM Empirical Model," SAE Int. J. Adv. & Curr. Prac. in Mobility 2(3):1516-1527, 2020, https://doi.org/10.4271/2020-01-0701.
The study of heavy vehicles rollover prediction, especially in algorithm-based heavy vehicles active safety control for improving road handling, is a challenging task for the heavy vehicle industry. Due to the high fatality rate caused by vehicle rollover, how to precisely and effectively predict the rollover of heavy vehicles became a hot topic in both academia and industry. Because of the strong non-linear characteristics of Human-Vehicle-Road interaction and the uncertainty of modeling, the traditional deterministic method cannot predict the rollover hazard of heavy vehicles accurately. To deal with the above issues, this paper applies a probability method of uncertainty to the design of a dynamic rollover prediction algorithm for heavy vehicles and proposes a novel algorithm for predicting the rollover hazard based on the combined empirical model of reliability index and failure probability. Moreover, the paper establishes a classification model of heavy vehicles based on the support vector machine (SVM) and uses the Monte Carlo method to calculate the failure probability of rollover limit state of heavy vehicles. The fishhook, double lane change, and slalom maneuver tests of heavy vehicles are used to predict and validate the proposed algorithm in real-time. The simulation results show that the rollover prediction method based on failure probability is accurate and real-time, and can effectively improve the rollover prediction accuracy. Meanwhile, the proposed approach reduces the external interference of strong non-linear characteristics of Human-Vehicle-Road interaction and the uncertainty of the modeling to the system, thus significantly improving the prediction accuracy of active safety performance of heavy vehicles.