Organizations: Singapore Institute of Technology (SIT), Singapore, 828608 · Singapore University of Social Sciences (SUSS), Singapore, 599494 · Institute of Materials Research and Engineering (IMRE), Agency for Science, Technology and Research (A*STAR), 2 Fusionopolis Way, Innovis #08-03, Singapore 138634, Republic of Singapore
State of health (SoH) is widely used for battery management, but it is a single scalar and offers limited interpretability. Two batteries with similar SoH can exhibit very different degradation behaviors and the lack of interpretability hinders optimal battery operation. In this paper, we propose IBAM for interpretable battery aging modelling with a neural-assisted physics-based framework. IBAM outputs a 2-D aging fingerprint without extra diagnostic tests and uses only routine logs from the battery management system. The fingerprint offers great interpretability by capturing a battery's curve-wide polarization voltage loss and the tail loss near the end-of-discharge. IBAM first creates a physics-based battery model based on a fractional-order equivalent circuit model, and then extracts per-cycle fingerprints from the model using a two-stage least-squares method. IBAM further anchors fingerprints on the SoH axis with physics-guided regression, where the per-cycle SoH is estimated via a bidirectional gated recurrent unit with customized multi-channel voltage features. Across batteries with short-, medium-, and long-lifespans, IBAM consistently yields the best physics model fidelity at different aging stages, and provides clear interpretations of degradation mechanisms and fingerprint patterns about batteries of different lifespans. The resulting fingerprints support interpretable battery health assessment and can inform battery control choices.
Figures & tables
Fig. 1: An illustration of IBAM architecture.
Fig. 2: Illustration of the polarization loss and tail loss for a representative battery cell across different discharge cycles.
Fig. 3: Illustration of the physics-based models for ECM and FOECM.
Fig. 4: IBAM learned degradation fingerprints for representative batteries in the short-life ( Bat039 and Bat025 ), medium-life ( Bat116 ), and long-life ( Bat100 and Bat124 ) categories; each battery’s lifespan (in cycles) is indicated in the legend. Overall, short-life batteries exhibit stronger tail loss.
Optimized Physics Battery Model
100% Lifespan
67% Lifespan
33% Lifespan
0% Lifespan
Short
Medium
Long
Short
Medium
Long
Short
Medium
Long
Short
Medium
Long
ECM
53.067
48.350
46.723
39.073
34.607
29.777
42.073
37.133
32.140
39.813
38.577
32.663
FOECM base (w/t RW)
52.740
48.053
46.053
37.997
33.890
28.350
41.167
36.340
30.763
38.627
37.850
31.293
FOECM ( IBAM , ours)
45.457
43.547
43.303
34.790
31.340
27.400
36.577
33.387
28.310
34.050
34.200
28.727
TABLE I: The performance of different physics-based battery models, including ECM, FOECM base without the tail component RW , and IBAM ’s FOECM in terms of per-cycle voltage-fitting RMSE. Four representative battery operation stages are considered, including 100%, 67%, 33%, and 0% remaining lifespan based on 100% SoH and EoL. A small value indicates a good performance.
BiGRU Input Battery Lifespan
MAE
RMSE
1-Channel
4-Channel
1-Channel
4-Channel
Short
0.0141
0.0039
0.0174
0.0050
Medium
0.0184
0.0053
0.0216
0.0060
Long
0.0111
0.0056
0.0132
0.0066
TABLE II: Impact of 4-channel feature construction on the BiGRU SoH estimator used in IBAM . Results are reported in MAE and RMSE, where small values indicate good performance.
Accurate prediction of lithium-ion battery state of health (SOH) is essential for reliable energy storage operation. However, purely data-driven models may generalize poorly across cycling protocols and produce physically implausible behavior during long-term extrapolation. We developed a physics-informed differentiable degradation modeling framework (PiDDM) for battery SOH prediction. PiDDM incorporates empirical Arrhenius degradation kinetics associated with solid electrolyte interphase growth and loss of lithium inventory into the training objective, encouraging physically consistent capacity fade under diverse operating conditions. The framework was evaluated using a public dataset of 55 batteries cycled under six operating protocols. PiDDM achieved the lowest average prediction error among the evaluated models and substantially reduced mean squared error relative to a multilayer perceptron and a baseline physics-informed neural network. For extrapolation, the models were trained on the first 90% of each battery's cycle life and evaluated on the unseen final 10%. PiDDM captured accelerated end-of-life degradation while avoiding the nonphysical capacity regeneration produced by the baseline models. These results show that incorporating degradation physics into neural network training improves predictive accuracy and physical consistency, providing a promising approach for practical battery health monitoring.
Zeping Chen, Ruda Jian, Sachin Sigdel +3
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
Battery health prognostics is a core function in battery management systems (BMSs), yet long-horizon health forecasting from BMS signals remains challenging due to operating-condition dependency and sensor noise. In this paper, we propose PhyMamba, a two-stage physics-modulated Mamba framework that integrates electrochemical aging into sequence modelling. PhyMamba does not require explicit identification of internal aging parameters, which often relies on intrusive measurements. In stage-1, a lightweight Mamba encoder first processes BMS signals and produces a latent representation that is transformed via an aging parameterization module, into physics-informed aging features. In stage-2, a customized Mamba forecasting backbone performs multi-cycle prediction, where physics is tightly integrated to regulate the model's internal temporal updates toward degradation-consistent evolution. Experiments on three public datasets under multiple forecast horizons show that PhyMamba achieves the best aggregated performance, with an overall mean error reduction of 31.8% compared with a diverse range of baselines. PhyMamba also offers an optimized accuracy-efficiency trade-off, which supports practical deployment for robust battery health prognostics.
Sara Sameer, Yunyi Zhao, Wei Zhang +4
Information and Communications Technology Cluster, Singapore Institute of Technology, Singapore 138683
Accurate battery health prognosis using State of Health (SOH) estimation is essential for the reliability of multi-scale battery energy storage, yet existing methods are limited in generalizability across diverse battery chemistries and operating conditions. The inability of standard neural networks to capture the complex, high-dimensional physics of battery degradation is a major contributor to these limitations. To address this, a physics-informed neural network with the Quantum Feature Mapping(QFM) technique (QPINN) is proposed. QPINN projects raw battery sensor data into a high-dimensional Hilbert space, creating a highly expressive feature set that effectively captures subtle, non-linear degradation patterns using Nyström method. These quantum-enhanced features are then processed by a physics-informed network that enforces physical constraints. The proposed method achieves an average SOH estimation accuracy of 99.46% across different datasets, substantially outperforming state-of-the-art baselines, with reductions in MAPE and RMSE of up to 65% and 62%, respectively. This method was validated on a large-scale, multi-chemistry dataset of 310,705 samples from 387 cells, and further showed notable adaptability in cross-validation settings, successfully transferring from one chemistry to another without relying on target-domain SOH labels.
Muhammad Imran Hossain, Md Fazley Rafy, Sarika Khushalani Solanki +1
Lane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV, USA, 26505.