未明确提及

本研究旨在通过模拟电池模型生成数据集，以训练数据驱动的电池健康状态(SOH)模型。数据集通过模拟电池模型生成，可以覆盖几乎无限的数据点，提供了一种在时间和成本上更高效的替代实验测量数据的方法。这种方法允许在不同的电流和温度工作负载下生成大量数据点，用于训练更轻量级和灵活的数据驱动模型。数据集的创建过程涉及使用可模拟的电池模型来评估各种工作负载，从而生成用于训练的数据。该数据集主要应用于电池管理系统(BMS)中，用于提高电池健康状态估计的准确性和效率。

This study aims to generate datasets using simulated battery models for training data-driven battery State of Health (SOH) models. Generated via simulated battery models, these datasets can cover nearly unlimited data points, providing a time- and cost-efficient alternative to experimentally measured data. This approach enables the production of large volumes of data points under various current and temperature operating workloads, which supports the training of more lightweight and flexible data-driven models. The dataset creation process involves utilizing simulatable battery models to evaluate diverse operating conditions, thus generating data suitable for model training. This dataset is primarily applied in Battery Management Systems (BMS) to improve the accuracy and efficiency of battery State of Health estimation.