Particle Swarm optimization of Type-2 fuzzy control for regenerative braking of electric vehicles

Introduction Regenerative braking control technology has been widely implemented in electric vehicles (EVs) to enhance energy recuperation efficiency. However, the distribution of braking force, particularly for the front axle motor, often fails to achieve an optimal balance between high energy recovery and vehicle stability. Methods To address this challenge, a model-based simulation framework integrating Type-2 fuzzy logic and Particle Swarm Optimization (PSO) was developed. The proposed strategy employs a Type-2 fuzzy controller to manage braking force allocation dynamically, while PSO optimizes the fuzzy rule parameters to improve overall system performance. Results Simulation under New European Driving Cycle (NEDC) conditions demonstrated that the optimized control strategy increases the driving range to 396 km on a single battery charge—an improvement of approximately 15.8%. The regenerative braking ratio coefficient exhibited a dynamic range of 0.08–0.63 during a 600-second operational period, indicating a responsive and adaptable control mechanism. Discussion The experimental results confirm that the proposed fuzzy-PSO-based strategy effectively balances braking safety with energy recovery. This approach offers a practical and scalable solution for enhancing the braking performance of EVs and contributes to the broader goal of reducing energy consumption and emissions. The study provides new insights into optimizing EV braking systems for improved environmental and economic outcomes.