发表机构
Singapore Institute of Technology; Singapore University of Social Sciences; Shanghai Jiao Tong University; Agency for Science, Technology and Research (A*STAR); Institute of Advanced Intelligence and Computing (IAIC), Agency for Science, Technology and Research (A*STAR); Institute of Materials Research and Engineering (IMRE), Agency for Science, Technology and Research (A*STAR)（新加坡理工学院; 新加坡社科大学; 上海交通大学; 新加坡科技研究局; 新加坡科技研究局高级智能与计算研究所; 新加坡科技研究局材料研究与工程研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Sera框架，结合退化语义与时序建模，在主流基准数据集上使电池健康预测误差最高降37.3%，提升了精度、泛化性与可解释性。
AI 中文摘要
电池健康状态（SoH）预测对电池管理至关重要，但由于电池的非线性退化特性及各电池间的异质性，该任务仍具挑战性。现有数据驱动方法主要采用时序模型从电池数值时间序列中学习，却往往未明确表征更高层次的退化特征；而这些特征可提供退化指导，以支持可靠预测并使退化影响更具可解释性。本文提出Sera（语义表示聚合框架），该框架将退化语义与时序建模相结合。在电池领域专业知识的指导下，Sera从时间序列中提取退化语义，并基于规则知识和大语言模型（LLM）的解释构建两种互补表示；这些表示经独立编码后，通过门控聚合与时序模型学习到的表示进行融合。在主流基准数据集上针对多个预测 horizon 及不同时序模型开展的实验表明，Sera可持续提升预测性能，较时序基线的预测误差降低幅度最高达37.3%，且泛化能力得到增强。反事实分析检验了预测对退化语义变化的响应以评估可解释性，结果显示，在所有测试的预测 horizon 下，预测响应均与关键退化描述符的含义一致。综上，这些发现表明，结构化的退化语义与有效聚合可提升预测精度，并为高级电池管理提供可靠且可解释的电池健康预测支持。
英文摘要
Battery state of health (SoH) forecasting is important for battery management, but remains challenging due to nonlinear degradation and heterogeneity across batteries. Existing data-driven approaches primarily use temporal models to learn from numerical battery time series, and higher-level degradation characteristics are often not explicitly represented. These characteristics, however, can provide degradation guidance to support reliable forecasting and make the influence of degradation more interpretable. In this paper, we propose \textsc{Sera}, a \underline{se}mantic \underline{r}epresentation \underline{a}ggregation framework that complements temporal modelling with degradation semantics. Guided by battery domain expertise, \textsc{Sera} extracts degradation semantics from time series and constructs two complementary representations using rule-based knowledge and LLM-based interpretation. The representations are independently encoded and integrated with the representation learned by temporal models through gated aggregations. Experiments on the mainstream benchmark across multiple prediction horizons and different temporal models show that \textsc{Sera} consistently improves forecasting performance, achieving up to a 37.3\% reduction in prediction error over the temporal baseline and enhanced generalizability. Counterfactual analysis examines how forecasts respond to changes in degradation semantics to assess interpretability. The results show that prediction responses are consistent with the meanings of key degradation descriptors across tested horizons. Together, these findings demonstrate that structured degradation semantics and effective aggregation can improve forecasting accuracy and support reliable and interpretable battery health forecasting for advanced battery management.
