Multi-Objective Optimization of Structural Parameters of Air-Cooled System for Lithium Battery Pack Based on Surrogate Model

The new energy electric vehicle, which takes clean electric energy as the main driving force, has no pollutants and exhaust emissions during its operation and has a higher energy utilization ratio than the fuel locomotive. Therefore, electric vehicles have been widely developed in recent years. The maximum temperature and temperature consistency of the battery pack in the electric vehicle have a great influence on the life and safety of the battery. In this paper, the thermal management system of the lithium battery pack was taken as the research object. The temperature distribution and uniformity of the battery pack under different heat dissipation conditions were analyzed based on computational fluid dynamics (CFD). The multi-objective optimization method of the battery pack thermal management system was carried out by combining the surrogate model with fast non-dominated sorting genetic algorithm (NSGA-II). The maximum temperature of the battery pack obtained from candidate point 1 is 310.72 K, which is 4.99 K lower than the initial model temperature, and the temperature standard deviation is 0.76 K, with a reduction rate of 51.9%. Experiment results showed that maximum difference between the optimized and experimental value of the maximum temperature is 0.8 K, and the error was within 1 K. Therefore, the multi-objective optimization method proposed in this paper has high accuracy.