arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.10792cs.LGcs.AIstat.AP
收藏

通过基于注意力的模型解读时间模式与循环变异性以提升锂离子电池寿命预测的数据效率与特征识别能力

Enhancing Data Efficiency and Feature Identification for Lithium-Ion Battery Lifespan Prediction by Deciphering Interpretation of Temporal Patterns and Cyclic Variability Using Attention-Based Models

Korea Advanced Institute of Science and Technology(韩国科学技术院);University of Southern California(南加州大学)

Jaewook Lee, Seongmin Heo, Jay H. Lee

AI总结:

本研究针对锂离子电池寿命预测模型可解释性不足的问题,提出结合时间与循环注意力的改进模型,可识别关键时间步和循环,将输入从100个循环减至30个,仅用前30个循环数据就能以58个循环的平均偏差预测容量快速衰减起始点,提升了预测效率与准确性。

摘要:

准确预测锂离子电池寿命对于优化运行策略、降低风险至关重要。尽管已有大量研究致力于电池寿命预测,但极少有研究探讨其模型的可解释性,或这类洞见如何能改善预测效果。针对这一空白,我们提出三种创新模型,将浅层注意力层整合到我们前期工作的基础模型中,该基础模型结合了循环神经网络与卷积神经网络的元素。利用一个知名公开数据集,我们验证了所提方法的有效性。我们应用时间注意力机制识别关键时间步,并凸显不同测试电池批次间的差异,尤其强调了“静置”阶段的重要性。此外,通过对上下文向量施加基于自注意力的循环注意力,我们的方法能有效识别关键循环,从而可以策略性地减小输入规模以实现更快的预测。我们采用单头和多头注意力机制,系统性地将所需输入从100个循环逐步减少到50个,再减少到30个,并根据循环注意力分数优化这一过程。我们的优化模型展现出强大的回归能力,仅通过分析易于获取的前30个循环的输入数据,就能准确预测容量快速衰减的起始点,平均偏差仅为58个循环。

英文摘要:

Accurately predicting the lifespan of lithium-ion batteries is crucial for optimizing operational strategies and mitigating risks. While numerous studies have aimed at predicting battery lifespan, few have examined the interpretability of their models or how such insights could improve predictions. Addressing this gap, we introduce three innovative models that integrate shallow attention layers into a foundational model from our previous work, which combined elements of recurrent and convolutional neural networks. Utilizing a well-known public dataset, we showcase our methodology's effectiveness. Temporal attention is applied to identify critical timesteps and highlight differences among test cell batches, particularly underscoring the significance of the "rest" phase. Furthermore, by applying cyclic attention via self-attention to context vectors, our approach effectively identifies key cycles, enabling us to strategically decrease the input size for quicker predictions. Employing both single- and multi-head attention mechanisms, we have systematically minimized the required input from 100 to 50 and then to 30 cycles, refining this process based on cyclic attention scores. Our refined model exhibits strong regression capabilities, accurately forecasting the initiation of rapid capacity fade with an average deviation of only 58 cycles by analyzing just the initial 30 cycles of easily accessible input data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑