计算机科学
电池(电)
随机森林
学习迁移
均方误差
模式识别(心理学)
特征选择
功率(物理)
人工智能
特征(语言学)
还原(数学)
点(几何)
传输(计算)
原始数据
数据挖掘
算法
能量(信号处理)
近似误差
传递函数
软件部署
校准
国家(计算机科学)
离群值
深度学习
控制理论(社会学)
作者
Tianqing Yuan,Chunyu Zhao,Jing Bai
出处
期刊:Journal of Energy Engineering-asce
[American Society of Civil Engineers]
日期:2026-10-02
卷期号:152 (6)
标识
DOI:10.1061/jleed9.eyeng-7053
摘要
Abstract With the widespread deployment of large-scale energy storage systems, this paper proposes a state of health (SOH) estimation method for lithium-ion batteries operating under fluctuating renewable power conditions. First, a random forest algorithm is employed to eliminate false data from the raw dataset. Then, the maximum mean discrepancy method is introduced to efficiently identify aging domains and detect knee points, thereby reducing the distribution discrepancy between the source and aging domains and enhancing model robustness. Subsequently, a wrapper-based feature selection approach is utilized to extract highly correlated features and establish mapping relationships with the prediction model. Finally, a hybrid model integrating the horned lizard optimization algorithm, bidirectional temporal convolutional network, and bidirectional gated recurrent unit is developed for SOH prediction. Experimental results demonstrate that the proposed method achieves mean absolute percentage error and root mean square error within 0.6% and 1.4% on the Oxford dataset, respectively, and exhibits strong performance on the National Aeronautics and Space Administration dataset, confirming its high accuracy and robustness.
科研通智能强力驱动
Strongly Powered by AbleSci AI