Guo, Zhongyi (Jilin University), Chen, Hong (Tongji University), Xu, Fang (Jilin University), Kong, Xiangming (China FAW Corporation Limited), Lin, Jiamei (Jilin University)

Learning-Based Model Predictive Control for Four-Wheel Drive Electric Vehicle Stability under Environmental Disturbance

Scheduled for presentation during the Invited session "Modeling, control and optimization of vehicle and renewable energy system" (FrB4), Friday, November 1, 2024, 10:30−10:50, Room T4

7th IFAC Conference on Engine and Powertrain Control, Simulation and Modeling, Oct 30 - Nov 1, 2024, Dalian, China

This information is tentative and subject to change. Compiled on January 2, 2025

Abstract

This paper presents a learning-based model predictive controller for four-wheel drive electric vehicle stability. The controller can improve the accuracy of the controller and ensure the controller's safety under uncertain environment. To improve the model accuracy, a data-mechanical hybrid model is developed that uses Gaussian process regression to learn the environment uncertainty. Moreover, the variance is added to cost function as a soft constraint to tighten the state constraint and improve the safety of the controller. Finally, the controller is validated in the CarSim/Simulink co-simulation platform. The results show that the controller enhances the vehicle handling stability under environmental disturbance compared to traditional model predictive control.