准确预测锂离子电池在早期循环中的寿命对于确保安全性和可靠性以及加快电池开发周期至关重要。然而，由于非线性电池容量的衰减以及早期周期中的变化可忽略不计，因此大多数现有研究对较早的预测都给出了较差的预测结果。在本文中，为了实现对电池寿命的准确的早期周期预测，提出了一个基于综合机器学习（ML）的框架，该框架包含三个模块，即特征提取，特征选择和基于机器学习的预测。首先，通过分析各种信息性参数的演变模式，基于前100个周期的充放电原始数据手动制作了42个特征。其次，要管理功能的不相关性和冗余性，采用四种典型的特征选择方法来生成最优的低维特征子集。最后，将选定的功能输入六个有代表性的ML模型中，以有效预测电池寿命。数值实验与配对
进行t
检验以统计评估所提出框架的性能。结果表明，基于包装的特征选择方法优于其他方法，并显着提高了后续ML模型的预测性能。在包装器特征选择之前和之后，与其他复杂的ML预测模型相比，弹性网，高斯过程回归和支持向量机都具有更好的性能。支持向量机模型与包装器特征选择相结合，从统计学上呈现了最佳的电池寿命预测结果，均方根误差为115个周期，
R
2
为0.90。最后，与现有工作相比，通过使用建议的框架，均方根误差从173个周期显着减少到115个周期。
Accurately predicting the lifetime of lithium-ion batteries in early cycles is crucial for ensuring the safety and reliability, and accelerating the battery development cycle. However, most of existing studies presented poor prediction results for early prediction, due to the nonlinear battery capacity fade with negligible variation in early cycles. In this paper, to achieve an accurate early-cycle prediction of battery lifetime, a comprehensive machine learning (ML) based framework containing three modules, the feature extraction, feature selection, and machine learning based prediction, is proposed. First, by analysing the evolution pattern of various informative parameters, forty-two features are manually crafted based on the first-100-cycle charge-discharge raw data. Second, to manage feature irrelevancy and redundancy, four typical feature selection methods are adopted to generate an optimal lower-dimensional feature subset. Finally, the selected features are fed into six representative ML models to effectively predict the battery lifetime. Numerical experiments and paired
t
-test are conducted to statistically evaluate the performance of the proposed framework. Results show that the wrapper-based feature selection method outperforms other methods, and significantly improves the prediction performance of subsequent ML models. Both before and after wrapper feature selection, the elastic net, Gaussian process regression, and support vector machine present better performance than other complex ML prediction models. The support vector machine model combined with wrapper feature selection statistically presents the best result for battery lifetime prediction, with a root-of-mean-square-error of 115 cycles, and a
R
2
of 0.90. Finally, when compared with an existing work, the root-of-mean-square-error is substantially decreased from 173 to 115 cycles, by using the proposed framework.
