This research study deals with the heat prediction of the battery in electric vehicles. An all-electric vehicle is considered in this study. The FTP-75, NEDC, and WLTC standard driving cycles are used to assess the performance of the electric vehicle battery. Additionally, the actual Munich driving travel cycle was employed in the simulation. The parameters that determine the performance of the vehicle, such as the battery's state of charge (SOC), energy consumption, and operating temperature, are evaluated. The results indicate that raising the gradients increases the temperature and the heat output from the battery. In addition, Munich's driving cycle increased driving time and rapid accelerations have raised temperatures and increased heat generation. The results showed that an increase in the road slope of 5 % results in an increase in the battery temperature of 3 % and a reduction in the SOC of the battery for 20 %. In addition, results showed that for a travel path with an average road slope of 5°, the battery temperature increases about 7 C which requires more thermal management using hybrid cooling.

中文翻译：

---

基于机器学习的标准驾驶循环中电池发热管理的预测，以避免热失控并提高安全性


这项研究涉及电动汽车电池的热量预测。本研究考虑的是全电动汽车。采用FTP-75、NEDC和WLTC标准行驶循环来评估电动汽车电池的性能。此外，模拟中还采用了实际的慕尼黑驾驶行程周期。对决定车辆性能的参数进行评估，例如电池的充电状态 (SOC)、能耗和工作温度。结果表明，提高梯度会增加电池的温度和热量输出。此外，慕尼黑的驾驶周期增加了驾驶时间，并且快速加速导致温度升高并增加了热量产生。结果表明，道路坡度增加5%，导致电池温度升高3%，电池SOC降低20%。此外，结果显示，对于平均道路坡度为5°的行驶路径，电池温度增加约7℃，这需要使用混合冷却进行更多的热管理。