专栏名称: AEii国际应用能源
发布应用能源领域资讯,介绍国际应用能源创新研究院工作,推广应用能源优秀项目,增进应用能源领域合作
目录
相关文章推荐
918云南交通台  ·  突发事故,现场黑烟滚滚!乘客紧急送医!车企回应 ·  10 小时前  
昆明信息港  ·  绝味鸭脖,被立案调查! ·  2 天前  
掌上春城  ·  热搜第一!她突然退出,网友:很心疼 ·  3 天前  
918云南交通台  ·  3·15曝光问题,多地连夜查处! ·  3 天前  
51好读  ›  专栏  ›  AEii国际应用能源

【Applied Energy 最新原创论文】电池老化诊断算法在不同电池间的迁移:从实验室到实际应用的案例研究

AEii国际应用能源  · 公众号  ·  · 2023-08-28 20:01

正文

原文信息:

Transferable data-driven capacity estimation for lithium-ion batteries with deep learning: A case study from laboratory to field applications

原文链接:

https://www.sciencedirect.com/science/article/pii/S030626192301111X

Highlights

Transferable deep learning based capacity estimation from laboratory to field.

Automatic feature extraction and dimension increasing with physical interpretation.

Uncertainty awareness of charging protocols, charging habits, and production quality.

Only using 100 s charging data in determined voltage window.

摘要

老化诊断在锂离子电池系统的健康与安全管理中起着至关重要的作用。本研究旨在开发一种可迁移的数据驱动框架,以准确进行电化学体系相同但容量不同的锂离子电池在实际应用中的老化诊断。所提出的框架可以有效利用大型实验室数据集中的通用性老化信息,针对小容量电池的恒定电流放电特性进行预训练网络的获取。基于该预训练网络,可以进一步在实际驾驶循环下有效地提升大容量电池的老化诊断性能。此外,在不同数据集上分别进行了充电容量增量分析,为老化特征的提取筛选出具有物理可解释性的电压区间,并充分考虑了不同快充策略对电池老化的影响。考虑到实际用户充电行为的不确定性,利用所确定电压区间内的任意100秒充电时间序列进行自动化的维度提升与老化特征提取。结果表明,所提出的方法极大的提高了电池老化诊断的精确性与鲁棒性。与基准方法相比,提出方法在最佳和最差测试结果下的平均均方根误差分别提高了68.40%和65.89%。考虑到实际应用的多种不确定性,基于30次随机老化特征筛选进一步验证了所提方法的鲁棒性。本研究表明了利用可迁移深度学习和通用性老化信息来改善实际应用场景下电池老化诊断的潜力。研究结果强调了在不同容量的锂离子电池之间共享信息的重要性,该信息可有效提高电池老化诊断的效率性和精确性。

更多关于" Capacity estimation "的研究请见:

https://www.sciencedirect.com/search?qs=Capacity%20estimation&pub=Applied%20Energy&cid=271429

Abstr act

Capacity estimation plays a vital role in ensuring the health and safety management of lithium-ion battery-based electric-drive systems. This research focuses on developing a transferable data-driven framework for accurately estimating the capacity of lithium-ion batteries with the same chemistry but different capacities in field applications. The proposed approach leverages universal information from a laboratory dataset and utilizes a pre-trained network designed for small-capacity batteries with constant-current discharging profiles. By applying this framework, capacity estimation for large-capacity batteries under drive cycles can be efficiently achieved with improved performance. In addition, the incremental capacity analysis is employed on two datasets, selecting a robust voltage interval for health indicator extraction with physical interpretations and uncertainty awareness of different fast charging protocols. The feature extraction and dimension increase processes are automated, utilizing the last short charging sequences in wide voltage intervals while considering the uncertainty related to various user charging habits. Results demonstrate that the proposed strategy significantly enhances both robustness and accuracy. When compared to conventional methods, the proposed method exhibits an average root mean square error improvement of 68.40% and 65.89% in the best and worst cases, respectively. The robustness of the proposed strategy is further verified through 30 randomized health indicator verifications. This research showcases the potential of transferable deep learning in improving capacity estimation by leveraging universal information for field applications. The findings emphasize the importance of sharing knowledge across different capacities of lithium-ion batteries, enabling more effective and accurate capacity estimation techniques.

Keywords

Lithium-ion battery;

Capacity estimation;

Transferable deep learning;

Laboratory to field;

Graphics

Fig. 1. Graphical abstract

Fig. 5. Structure of developed flexible DNN in field application.

Fig. 6. Comparative results of the best performance.







请到「今天看啥」查看全文