Sera: Semantic Representation Aggregation for Reliable and Interpretable Battery Health Forecasting

Jiawei Li; Fang Liu; Wei Zhang; Zuming Liu; Man-Fai Ng; Zhi Wei Seh

cs.LGOct 8, 2026

Sera: Semantic Representation Aggregation for Reliable and Interpretable Battery Health Forecasting

Authors: Jiawei Li, Fang Liu, Wei Zhang, Zuming Liu, Man-Fai Ng, Zhi Wei Seh

Organizations: Infocomm Technology Cluster Singapore Institute of Technology Singapore · School of Science and Technology Singapore University of Social Sciences Singapore · College of Smart Energy Shanghai Jiao Tong University Shanghai, China · Institute of Advanced Intelligence and Computing (IAIC), Agency for Science, Technology and Research (A*STAR), Fusionopolis Way, #16–16 Connexis, Singapore 138632, Republic of Singapore · Institute of Materials Research and Engineering (IMRE), Agency for Science, Technology and Research (A*STAR), Fusionopolis Way, Innovis #08-03, Singapore 138634, Republic of Singapore

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.

Figures & tables

Figure 1. Overall architecture of Sera . Given a window of battery time series, semantic features are extracted to construct rule-based and LLM-based degradation semantics. Temporal and semantic information is encoded separately and then aggregated for SoH forecasting.

Rule	Candidate Values	Source Features	Description
Trend	stable , mild_decay , linear_decay , accelerating_fade	SoH slope, SoH acceleration ratio	Overall degradation tendency observed within the input window.
Risk Level	low , medium , high	SoH slope, temperature std. ( $T_{\mathrm{std}}$ ), IR std. ( $\sigma_{\mathrm{IR}}$ )	Estimated level of degradation risk based on evidence from multiple battery indicators.
Mechanism	SEI_growth , lithium_plating , cathode_degradation , thermal_aging , impedance_rise , mixed , stable	SoH slope, $\sigma_{\mathrm{IR}}$ , $T_{\mathrm{std}}$ , charge time slope	Dominant electrochemical or thermal degradation behaviour inferred from the observed feature patterns.
Severity	mild , moderate , severe	Magnitude of SoH slope, mean SoH level	Strength of the degradation evidence observed within the input window.
Change Point	yes , no	SoH acceleration ratio, SoH acceleration flag	Indication of a possible transition in the observed degradation behaviour.
Key Metric	SoH_slope , Tstd , IRstd , CTslp , QDslp	Selected diagnostic indicator	Most informative feature supporting the current degradation interpretation.

Table 1. Structured semantic representation schema for battery degradation. Each semantic component is described by its candidate values, supporting source features, and degradation meaning.

	$H=30$		$H=50$		$H=70$		$H=90$
Model	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE
TS	1.556	2.309	2.317	2.942	3.043	3.818	3.565	4.727
Rule only	11.384	12.904	12.064	13.578	10.962	12.174	11.641	13.172
LLM only	12.157	14.225	12.806	14.755	11.526	13.296	12.150	14.515
TS + Rule	0.912	1.369	1.883	2.463	2.350	3.135	2.593	3.349
TS + LLM	1.408	2.036	2.108	2.744	2.522	3.202	2.946	3.869

Table 2. Comparison of forecasting performance in terms of test MAE and RMSE across different prediction horizons. Lower values indicate better performance, with the best results highlighted in bold. All values are

\times 10^{-3}

Panel of Figure 2 — Figure 2. Semantic contribution and generalization analysis across prediction horizons. Fig. 2(a) : reduction in test MAE relative to the TS baseline. Fig. 2(b) : generalization gap, measured as the difference between test and training MAE.

Model	LSTM		TFM		PatchTST
Model	$H=30$	$H=90$	$H=30$	$H=90$	$H=30$	$H=90$
TS	1.394	3.578	1.599	3.421	1.556	3.565
TS + Rule	1.505	3.097	1.375	2.708	0.912	2.593
TS + LLM	1.535	3.336	2.013	3.246	1.408	2.946
Sera (ours)	1.229	3.098	1.350	2.636	1.015	2.234

Table 3. Comparison of test MAE across temporal encoders at

H=30

and

H=90

. Lower values are better, and the best results are highlighted in bold. All values are

\times 10^{-3}

Panel of Figure 3 — Figure 3. Qualitative comparison of SoH trajectories for representative short- (Fig. 3(a) ) and long-lifespan (Fig. 3(b) ) batteries. The results compare the ground truth trajectories with predictions from the temporal baseline, semantic variants, and models with temporal and semantic representations.

	$H=30$		$H=50$		$H=70$		$H=90$
Semantic Edit	%	$\bar{\Delta}_{H}$	%	$\bar{\Delta}_{H}$	%	$\bar{\Delta}_{H}$	%	$\bar{\Delta}_{H}$
Optimistic Bundle	90.5	$+$ 5.8	69.0	$+$ 7.5	86.5	$+$ 12.9	70.5	$+$ 11.9
Pessimistic Bundle	100.0	$-$ 71.3	100.0	$-$ 116.8	100.0	$-$ 146.1	100.0	$-$ 251.3
Slope $\to$ Mild	75.5	$+$ 5.6	84.5	$+$ 7.5	82.0	$+$ 13.2	71.0	$+$ 12.1
Slope $\to$ Steep	100.0	$-$ 68.9	100.0	$-$ 129.7	100.0	$-$ 142.3	100.0	$-$ 255.1
Trend $\to$ Stable	78.5	$+$ 0.9	93.0	$+$ 2.2	91.0	$+$ 4.2	61.0	$+$ 7.7

Table 4. Counterfactual analysis of different semantic interventions. Higher semantic consistency (%) indicates that more predictions change in the expected direction after interventions. Positive (negative)

\bar{\Delta}_{H}

values indicate an increase (decrease) in predicted SoH, with larger absolute values indicating stronger effects.

\bar{\Delta}_{H}

values are in units of

10^{-3}

Explore similar work

BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting
May 26, 2026Ruifeng Tan, Jintao Dong, Weixiang Hong +3Multivariate Time Series Forecasting RUL Estimation
School of Computer Science and Engineering, Central South University · Material Genome Institute, Shanghai University
Autonomous End-to-End SOH Prediction Services for Battery Systems via Temporal-Contrastive Representation Learning
Jun 15, 2026Junting Wen, Dan Li, Qihao Quan +8Contrastive Learning Self-Supervised Time Series Representation Learning
School of Software Engineering, Sun Yat-sen University, Zhuhai 519082, China · Tianneng Battery Group Co., Ltd, Zhejiang, China · School of Communication Engineering, Hangzhou Dianzi University, China +1
PiDDM: Physics-Informed Differentiable Degradation Modeling for Lithium-Ion Battery State-of-Health Prediction
Jul 31, 2026Zeping Chen, Ruda Jian, Sachin Sigdel +3RUL Estimation Physics-Informed ML
Department of Chemical and Biomolecular Engineering, University of Notre Dame, Notre Dame, IN, USA · Department of Mechanical Engineering, The University of Texas at Dallas, Richardson, TX, USA · Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN, USA +1

May 26, 2026, cs.AIJ/K move · Enter open · S save

BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting

Ruifeng Tan, Jintao Dong, Weixiang Hong, Jia Li+2

School of Computer Science and Engineering, Central South University · Material Genome Institute, Shanghai University

Multivariate Time Series Forecasting RUL Estimation Time Series Transformers

Open paper AskPDF arXiv

Early battery degradation trajectory forecasting (BDTF), which predicts the full-life state-of-health trajectory from early operational data, is critical for battery optimization, manufacturing, and deployment. Battery degradation data exhibit two key characteristics. First, degradation data present a multi-level structure, including regularities shared within aging conditions and trajectory patterns shared across batteries. Second, degradation-related variations in voltage-current profiles are often localized to specific state of charge (SOC) intervals. Existing approaches often fail to explicitly model these characteristics. To bridge this gap, we propose BatteryMFormer, a multi-level Transformer for early BDTF. BatteryMFormer integrates (1) an aging-condition-aware decoder that injects aging-condition priors via aging-condition-informed queries and aging-condition-aware attention, (2) a meta degradation pattern memory that learns and retrieves trajectory prototypes to guide long-horizon forecasting, and (3) a dual-view encoder that jointly captures temporal dynamics and SOC-localized variations from voltage and current time series. Extensive experiments on four battery domains show that BatteryMFormer consistently outperforms state-of-the-art baselines, marking a significant step toward reliable BDTF. Our code is available at https://github.com/Ruifeng-Tan/BatteryMFormer.

Abstract

Explore similar work

BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting

Autonomous End-to-End SOH Prediction Services for Battery Systems via Temporal-Contrastive Representation Learning

PiDDM: Physics-Informed Differentiable Degradation Modeling for Lithium-Ion Battery State-of-Health Prediction