Energy-saving strategies for new energy vehicles based on GA algorithm and fuzzy theory

New energy vehicles have the disadvantage of low driving range, and existing energy-saving optimization methods have high costs with limited improvement potential. The combination of search algorithms and fuzzy inference provides a new approach for energy consumption optimization and management in vehicles. This paper proposes an energy consumption prediction and optimization method for vehicles based on Genetic Algorithm and Fuzzy Theory. The method uses Long Short Term Memory network to extract temporal features of multi-dimensional driving data under complex driving scenarios, optimizes key hyperparameters through sparrow search mechanism, and finds the global optimum using particle position and velocity update mechanism. Fuzzy inference calculates energy consumption results under different driving behaviors, achieving energy-saving optimization for PHEV type new energy vehicle. Experimental results show that the proposed model achieves an energy consumption prediction accuracy of 92.89%, with improvements of 24.58% in brake energy recovery and 8.78% in battery state of charge optimization, significantly outperforming comparison models. These results indicate that the model has high precision, real-time performance, and stability in energy consumption prediction under complex driving scenarios, providing reliable data support for energy-saving strategies in PHEV type new energy vehicle.