Intelligent Driving Decision-Making Strategy for New Energy Vehicles Based on Lightweight Reinforcement Learning Model

Intelligent Driving Decision-Making Strategy for New Energy Vehicles Based on Lightweight Reinforcement Learning Model

The explosive growth of new energy vehicles requires optimization of the automotive processing process. This article focuses on the processing of the rear panel in automotive panels. Firstly, the mesh optimization of the stamping die surface of the rear panel is carried out, and the adaptive mesh method of the die surface is used to improve the calculation accuracy of finite element calculations in these local areas. Then, in order to predict the forming performance of the stamping model for automotive panels, Dynaform software was used to numerically simulate the stamping process, analyze the forming effect of the parts under certain process conditions, and provide direction for the optimization of the model. Through experimental settings with different processing parameters, different forming effects of the rear panel were obtained. Then, through orthogonal experiments, the optimal processing scheme was determined. Finally, based on the optimal processing scheme, simulation analysis was conducted to optimize the thickness of the thin plate in the automotive forming process, and further optimize the stamping model structure.