Structural optimization and battery temperature prediction of battery thermal management system based on machine learning

Abstract

Lithium-ion batteries significantly extend the driving range for electric motorcycles. The battery thermal management system (BTMS) is critical for achieving optimal battery performance. Moreover, precise battery temperature prediction is essential for efficient thermal management. Therefore, a battery thermal management system integrating air and phase change material (PCM) cooling is proposed. Initially, the impact of PCM height, PCM thickness, and air velocity on battery temperature is analyzed. Subsequently, with cost minimization as the objective and ensuring that the maximum battery temperature remains below a threshold, the Black Kite Algorithm (BKA) is employed to optimize the BTMS structure. Finally, a BKA-Convolutional Neural Network (CNN)-Self Attention (SA) model is introduced for battery temperature prediction. The results indicate that increasing the thickness of the PCM and air velocity facilitates battery heat dissipation but with diminishing marginal effects. An increase in PCM height enhances battery cooling at low air velocities but becomes detrimental at high air velocities. The optimized PCM height is 35 mm, resulting in a cost of 0.073 USD for the BTMS per battery. Additionally, the BKA-CNN-SA model achieved a maximum error of 0.45 °C on the validation set and accurately predicted battery temperature changes before and after PCM melting.