Stability and Maneuverability Guaranteed Torque Distribution Strategy of DDEV in Handling Limit: A Novel LSTM-LMI Approach

Abstract

Direct yaw moment (DYC) does increase the maneuverability and controllability of distributed driving electric vehicle. However, the additional DYC could also lead to the instability of vehicle in low friction road. Extensive literatures have proposed various methods to tackle this problem. Nevertheless, the conflict between maneuverability and stability in handling limit is difficult to solve. To this end, a novel multimode torque distribution algorithm is developed in this article. The conception of drive stability region is proposed to describe the feasible operations of the driver. Based on the different regions, we define multitorque distribution modes to handle the varying conditions. A linear matrix inequality based mode decision theorem is developed to estimate the boundaries of the drive stability region as well as determine the optimal mode. Considering that the lateral tire force is important for mode decision, a long short-term memory neural network is adopted to make a precise estimation. Finally, we develop multitorque distribution strategies to meet the requirements of each mode. Processor-in-the-loop test is also implemented to verify the real-time performance of the algorithm. Simulation and experiment indicate that, the multimodes torque distribution strategy show a better performance compared with the single mode, which mitigates the conflict of maneuverability and stability as well as ensures the safety of vehicle in handling limit.