Energy Management of Plug-In Hybrid Electric Vehicles for Autonomous Driving in a Following Environment Based on Fuzzy Adaptive PID Control

The traditional energy management model for plug-in hybrid vehicles mainly uses rule-based optimization strategies. This association pattern can determine good results in most cases, but it has drawbacks such as low robustness, poor energy-saving effect, and low safety under complex driving conditions such as the following environments. Therefore, this study is based on a fuzzy adaptive proportional integral differential controller, combined with an improved Cuckoo search algorithm, to perform group optimization on various parameters of the control system. It uses simulation software to design a model for calculating the expected driving torque and ultimately develops a new energy management model for electric hybrid vehicles. The Cuckoo search algorithm is selected for its exceptional global search capability and adaptive optimization characteristics, which facilitate its effective resolution of intricate nonlinear optimization issues, such as the energy management strategy in plug-in hybrid electric vehicles. In terms of software application, this study used LabVIEW software for simulation experiments. The results showed that the average energy consumption of the model in 140 following experiments was about 21.5 KJ. When the improved Cuckoo algorithm iterated to the 51st iteration, the fitness value of the method reached its maximum value and remained stable thereafter, reaching 97.13%. Therefore, the energy management model for electric hybrid vehicles designed in this project has the advantages of high energy efficiency, strong robustness, and strong adaptability, providing a new approach to developing the energy management field.