基于容量增量变化量曲线的锂电池健康状态估计

提出了基于容量增量变化量曲线的电池健康状态估计新方法，该曲线具有随电池老化平移不明显的特点，并有利于特征参数的确定和提取。利用随机森林方法分析该曲线上各个函数值的重要性，根据重要性筛选出曲线上可以作为表征参数的函数值，并使用神经网络建立起表征参数与健康状态的映射关系。利用马里兰大学老化数据验证该方法的平均绝对百分比误差为0.77%，健康状态估计值误差基本控制在2%以内，具有较高的精度。

State of Health Estimation for Lithium-Ion Batteries Based on the Changes of Incremental Capacity

The paper proposes a novel method to estimate the state of health of batteries based on the curves of changes in incremental capacity, which does not vary with the battery aging and is conducive to extracting feature parameters. The random forest method is used to analyze the importance of each value on the curve for selecting the feature parameters. The mapping relationship between the feature parameters and the state of health is established by using neural network. The aging data from the Center for Advanced Life Cycle Engineering (CALCE) at the University of Maryland is used to verify the proposed method. The results of high accuracy are obtained including the mean absolute percentage error (MAPE) of 0.77%, and the error of estimation within 2%.