<?xml version="1.1" encoding="utf-8"?>
<article xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><front><journal-meta><journal-id journal-id-type="publisher-id">ASDS</journal-id><journal-title-group><journal-title>Applied Statistics and Data Science</journal-title></journal-title-group><issn>3066-8433</issn><eissn>3066-8441</eissn><publisher><publisher-name>Art and Design</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.61369/ASDS.2025100011</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>基于生成对抗- 元迁移协同的锂离子电池剩余使用寿命动态预测</title><url>https://artdesignp.com/journal/ASDS/1/10/10.61369/ASDS.2025100011</url><author>孟昌皓,刘奕彤,文佳睿,王国强</author><pub-date pub-type="publication-year"><year>2025</year></pub-date><volume>1</volume><issue>10</issue><history><date date-type="pub"><published-time>2025-12-20</published-time></date></history><abstract>锂离子电池剩余使用寿命（Remaining Useful Life, RUL）预测是保障设备运行安全与实现智能运维的关键技术挑战。然而，现有方法仍面临小样本数据稀缺、特征提取高度依赖人工经验以及模型泛化能力不足等挑战。为此，本文提出一种融合数据增强与深度学习的RUL 预测框架，旨在提升预测精度与模型鲁棒性。首先，基于电池容量退化曲线的演化趋势，采用模糊C 均值聚类对退化模式进行划分，并结合Wasserstein 梯度惩罚生成对抗网络实现条件式数据增强，生成与真实退化趋势一致的合成样本，有效缓解小样本问题。其次，设计基于元学习优化的自编码器，通过动态调整学习率与动量参数，提升特征提取的稳定性与鲁棒性，克服传统自编码器收敛不稳定的问题。接着，构建融合自适应注意力机制的双向长短期记忆网络，利用层次化注意力机制聚焦关键时间步特征以增强时序建模能力。最后，在HNEI 和CALCE 公开锂离子电池数据集上对所提方法进行验证。实验结果表明，本文所提方法在提升锂离子电池RUL 预测精度方面具有显著优势。</abstract><keywords>剩余使用寿命预测,智能运维,WGAN-GP,BiLSTM,元自编码器</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[1]陈立泉.锂离子电池改变世界&amp;mdash;&amp;mdash;2019年诺贝尔化学奖成果简析[J].科技导报, 2019, 37(24): 36-40.[2]陈建安,陈曦,POTAPENKO Hanna,等.锂硫电池的电解质安全性的研究进展及军事化前景[J].兵器材料科学与工程, 2025,48(01):145-154.[3]杜志明,陈佳炜.锂离子电池热失控危险性研究进展[J].安全与环境学报,2021,21(04):1523-1532.[4]李炳金,韩晓霞,张文杰,等.锂离子电池剩余使用寿命预测方法综述[J].储能科学与技术, 2024, 13(04):1266-1276.[5]秦琪, 赵帅, 陈绍炜, 等. 基于粒子群优化粒子滤波的电容剩余寿命预测[J]. 计算机工程与应用, 2018, 54(20): 237-241+258.[6]王志福,杨忠义,罗崴,等. 基于数据驱动的锂离子动力电池剩余使用寿命预测方法综述[J].科学技术与工程,2023,23(15):6279-6289.[7]简献忠,张博,王如志.一种改进RAO算法与多核SVM的锂离子电池寿命预测模型[J].小型微型计算机系统,2022,43(11):2314-2320.[8]Li L, Wang P, Chao K H, et al. Remaining Useful Life Prediction for Lithium-ion Batteries Based on Gaussian Processes Mixture [J]. PloS One, 2016, 11(9): e0163004.[9]Chaoui H, Ibe-Ekeocha C C. State of Charge and State of Health Estimation for Lithium Batteries Using Recurrent Neural Networks[J]. IEEE Transactions on Vehicular Technology, 2017, 66(10): 8773-8783.[10]Zheng S, Ristovski K, Farahat A, et al. Long Short-Term Memory Network for Remaining Useful Life Estimation[C]//2017 IEEE International Conference on Prognostics and Health Management (ICPHM). IEEE, 2017: 88-95.[11]Chen C, Pecht M. Prognostics of Lithium-ion Batteries Using Model-based and Data-driven Methods[C]//Proceedings of the IEEE 2012 Prognostics and System Health Management Conference. IEEE, 2012: 1-6.[12]贺宁,张思媛,李若夏,等.粒子滤波和GRU神经网络融合的锂电池RUL预测[J].哈尔滨工业大学学报,2024,56(05):142-151.[13]李梦蝶,赵光,罗灵鲲,等.基于改进CNN-LSTM的飞控系统剩余寿命预测[J].计算机工程与应用,2022,58(16):274-283.[14]Li X, Zhang L, Wang Z, et al. Remaining Useful Life Prediction for Lithium-ion Batteries Based on a Hybrid Model Combining the Long Short-Term Memory and Elman Neural Networks[J]. Journal of Energy Storage, 2019, 21: 510-518.[15]Liu Y, Wen J, Wang G. A Comprehensive Overview of Remaining Useful Life Prediction: From Traditional Literature Review to Scientometric Analysis. Machine Learning with Application. 2025:100704.[16]裴洪,胡昌华,司小胜,等.基于机器学习的设备剩余寿命预测方法综述[J].机械工程学报,2019,55(08):1-13.[17]S. Siami-Namini, N. Tavakoli and A. S. Namin, The Performance of LSTM and BiLSTM in Forecasting Time Series, 2019 IEEE International Conference on Big Data, Los Angeles, CA, USA, 2019, pp. 3285-3292.[18]董作林,宋金岩,孟子迪.基于模态分解和深度学习的锂离子电池寿命预测[J/OL].储能科学与技术,1-12[2025-01-20].[19]吴美君,杨新,潘超凡,等.自编码器结合持续学习：现状、挑战与展望[J/OL].计算机学报,1-37[2025-01-20].[20]李凡长,刘洋,吴鹏翔,等.元学习研究综述[J].计算机学报,2021,44(02):422-446.[21]鲁南,欧阳权,黄俍卉,等.基于注意力机制和多任务LSTM的锂电池容量预测方法[J].电气工程学报,2022,17(04):41-50.[22]王永,李行健,邓江洲.融合注意力机制的残差神经协同过滤推荐模型[J].运筹与管理,2024,33(10):201-208.[23]Smagulova K, James A P. Overview of Long Short-Term Memory Neural Networks[J]. Deep Learning Classifiers with Memristive Networks: Theory and Applications, 2020: 139-153.[24]刘大同,周建宝,郭力萌,等.锂离子电池健康评估和寿命预测综述[J].仪器仪表学报,2015,36(01):1-16.[25]林娅,陈则王.锂离子电池剩余寿命预测研究综述[J].电子测量技术,2018,41(04):29-35.
[26]Li X ,Yu D ,Byg S V , et al.The development of machine learning-based remaining useful life prediction for lithium-ion batteries[J].Journal of Energy Chemistry,2023,82(07):103-121.[27]Ge M F, Liu Y, Jiang X, et al. A Review on State of Health Estimations and Remaining Useful Life Prognostics of Lithium-ion Batteries[J]. Measurement, 2021, 174: 109057.[28]王健雁,廖成龙,凌泽.锂离子电池的循环寿命影响因素研究进展[J].化工新型材料,2019,47(S1):33-35.[29]Gulrajani I, Ahmed F, Arjovsky M, et al. Improved Training of Wasserstein Gans[J]. Advances in Neural Information Processing Systems, 2017, 30.[30]李超,汪伟,安斯光,等.基于数据扩展的锂离子电池早期寿命在线预测[J].现代电子技术,2024,47(10):171-176.[31]黄煜峰,梁焕超,许磊.基于卡尔曼滤波算法优化Transformer模型的锂离子电池健康状态预测方法[J].储能科学与技术,2024,13(08):2791-2802.[32]王海瑞,侯晓建,朱贵富,等.基于MsDCNN-Informer模型的设备剩余寿命预测[J/OL].控制工程,1-12[2025-03-14].</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
