arXiv cs.AI· Jiawei Li, Fang Liu, Wei Zhang, Zuming Liu, Man-Fai Ng, Zhi Wei Seh·· 9 天前AI 评分18
Sera：融合知识与 LLM 的语义表示聚合框架，实现可靠可解释的电池健康预测
Sera: Semantic Representation Aggregation with Knowledge and LLM for Reliable and Interpretable Battery Health Forecasting
AI 导读
Sera 是一个语义表示聚合框架，通过规则知识与 LLM 解读从电池时序中提取退化语义，与时间模型表示经门控聚合，在主流基准上预测误差最高降低 37.3%。反事实分析显示预测响应与关键退化描述符含义一致，验证了其可解释性。
正文 · 原文
Abstract: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.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11567 [cs.LG] |
| (or arXiv:2610.11567v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11567 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fang Liu [view email]
[v1]
Thu, 8 Oct 2026 09:25:01 UTC (251 KB)
来源：arXiv cs.AI · arxiv.org