南京信息工程大学学报2026，Vol.18Issue(3)：352-361,10.DOI:10.13878/j.cnki.jnuist.20241225002
基于HHO-LSTM-KAN模型的锂电池寿命预测
RUL prediction of lithium batteries based on an HHO-LSTM-KAN model
摘要
Abstract
Accurately predicting the long-term Remaining Useful Life(RUL)of lithium batteries is critical for en-suring the reliability of lithium battery-powerd systems.This study constructs an LSTM-KAN prediction model by in-tegrating the sequential data processing capability of Long Short-Term Memory(LSTM)network with the superior nonlinear fitting ability of Kolmogorov-Arnold Network(KAN).To enhance model performance,the Harris Hawk Optimization(HHO)algorithm is employed to determine its optimal hyperparameters.Using datasets from the Uni-versity of Maryland(batteries CS2_35 and CS2_36)and NASA(battery B0007),features correlated with battery capacity are first extracted from operational data such as voltage,current,and temperature.Features with a Spearman correlation coefficient greater than 0.9 are then selected as model inputs to reduce data complexity.Subsequently,the HHO algorithm optimizes the hyperparameters of the LSTM-KAN model,and the processed data are fed into the optimized model for RUL prediction.Experimental results demonstrate that the proposed HHO-LSTM-KAN model ef-fectively predicts the long-term degradation trend of lithium batteries.Its performance,in terms of mean squared er-ror and the required number of prediction samples,is superior to that of other benchmark battery life prediction models.关键词
锂电池/长短时记忆网络/Kolmogor-ov-Arnold网络/哈里斯鹰优化算法/特征提取/电池寿命Key words
lithium battery/long short-term memory(LSTM)/Kolmogorov-Arnold network(KAN)/Harris hawks optimization(HHO)/feature extraction/battery life分类
信息技术与安全科学引用本文复制引用
焦鑫航,杨立清,李忠虎..基于HHO-LSTM-KAN模型的锂电池寿命预测[J].南京信息工程大学学报,2026,18(3):352-361,10.基金项目
国家自然科学基金(62161042) （62161042）
