Optimization Investigation on Air Phase Change Material Based Battery Thermal Management System

To ensure the normal operation of a battery pack, a battery thermal management system (BTMS) is required to control the temperature of batteries. Herein, the method using an artificial neural network (ANN) combined with a genetic algorithm (GA) is proposed to optimize the thermal performance of air phase change material (PCM) cooling based BTMS. The ANN is applied to describe the relationship between BTMS parameters (inlet air velocity, inlet air temperature, PCM thickness, battery unit spacing, and discharge rate) and battery pack thermal characteristics. The results show that the PCM thickness and battery unit spacing have little effect on the battery temperature. Then, the optimal parameter combinations of BTMS are solved by GA with the goal of minimizing the maximum temperature. The maximum relative error between simulation and prediction is 0.484 °C, which is only 1.3835% of the simulated value. The optimal parameter combinations help to slow down the temperature rise of the battery pack and delay the phase transition of PCM. The results indicate that the developed model can accurately describe the relationship between the BTMS parameters and battery temperature, which provides a time-saving and efficient method for the optimal design of BTMS.