Knowledge-Aware Modeling with Frequency Adaptive Learning for Battery Health Prognostics

• URL: http://arxiv.org/abs/2510.02839v1
• Date: Fri, 03 Oct 2025 09:24:38 GMT
• Title: Knowledge-Aware Modeling with Frequency Adaptive Learning for Battery Health Prognostics
• Authors: Vijay Babu Pamshetti, Wei Zhang, Sumei Sun, Jie Zhang, Yonggang Wen, Qingyu Yan,
• Abstract summary: Karma is a knowledge-aware model with frequency-adaptive learning for battery capacity estimation and remaining useful life prediction.<n>A dual-stream deep learning architecture is developed, where one stream captures long-term low-frequency degradation trends and the other models high-frequency short-term dynamics.<n>Experiments show Karma's superior performance, achieving average error reductions of 50.6% and 32.6% over state-of-the-art algorithms for battery health prediction.
• Score: 27.840159692578354
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Battery health prognostics are critical for ensuring safety, efficiency, and sustainability in modern energy systems. However, it has been challenging to achieve accurate and robust prognostics due to complex battery degradation behaviors with nonlinearity, noise, capacity regeneration, etc. Existing data-driven models capture temporal degradation features but often lack knowledge guidance, which leads to unreliable long-term health prognostics. To overcome these limitations, we propose Karma, a knowledge-aware model with frequency-adaptive learning for battery capacity estimation and remaining useful life prediction. The model first performs signal decomposition to derive battery signals in different frequency bands. A dual-stream deep learning architecture is developed, where one stream captures long-term low-frequency degradation trends and the other models high-frequency short-term dynamics. Karma regulates the prognostics with knowledge, where battery degradation is modeled as a double exponential function based on empirical studies. Our dual-stream model is used to optimize the parameters of the knowledge with particle filters to ensure physically consistent and reliable prognostics and uncertainty quantification. Experimental study demonstrates Karma's superior performance, achieving average error reductions of 50.6% and 32.6% over state-of-the-art algorithms for battery health prediction on two mainstream datasets, respectively. These results highlight Karma's robustness, generalizability, and potential for safer and more reliable battery management across diverse applications.

Related papers

• Fixed Point Neural Acceleration and Inverse Surrogate Model for Battery Parameter Identification [5.094264803596951]
  We propose a deep learning-based framework for parameter identification of electrochemical battery models.<n>The proposed framework combines a neural surrogate model of the single particle model with electrolyte (NeuralSPMe) and a deep learning-based fixed-point iteration method.
  arXiv  Detail & Related papers  (2025-10-28T07:20:38Z)
• State of Health Estimation of Batteries Using a Time-Informed Dynamic Sequence-Inverted Transformer [0.0]
  Batteries play a central role in the efficiency and safety of energy storage systems, yet they inevitably degrade over time due to repeated charge-discharge cycles.<n> Accurate estimation of a State of Health (SoH) of battery is therefore essential for ensuring operational reliability and safety.<n>We propose a novel architecture: Time-Informed Dynamic Sequence Inverted Transformer (TIDSIT)<n> Experimental results on the NASA battery degradation dataset show that TIDSIT significantly outperforms existing models, achieving over 50% reduction in prediction error and maintaining an SoH prediction error below 0.58%.
  arXiv  Detail & Related papers  (2025-07-24T11:43:46Z)
• A Hybrid Artificial Intelligence Method for Estimating Flicker in Power Systems [42.76841620787673]
  This paper introduces a novel hybrid AI method combining H filtering and an adaptive linear neuron network for flicker component estimation in power distribution systems.<n>The proposed method leverages the robustness of the H filter to extract the voltage envelope under uncertain and noisy conditions followed by the use of ADALINE to accurately identify flicker frequencies embedded in the envelope.
  arXiv  Detail & Related papers  (2025-06-16T15:38:39Z)
• Survival Analysis with Machine Learning for Predicting Li-ion Battery Remaining Useful Life [4.6033243214188415]
  We propose a hybrid survival analysis framework integrating survival data reconstruction, survival model learning, and survival probability estimation.<n>Our approach transforms battery voltage time series into time-to-failure data using path signatures.<n> Experiments conducted on the Toyota battery and NASA battery datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-03-17T02:49:34Z)
• ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation [43.684035409535696]
  Existing imputation solutions mainly include low-rank models and deep learning models. We demonstrate a low rankness-induced bias balance between strong inductive bias and hightemporal model expressivity. We demonstrate its superiority in terms of accuracy, efficiency, and versatility in heterogeneous datasets, including traffic flow, solar energy, smart meters and air quality.
  arXiv  Detail & Related papers  (2023-12-04T08:35:31Z)
• Deep Ensembles Meets Quantile Regression: Uncertainty-aware Imputation for Time Series [45.76310830281876]
  We propose Quantile Sub-Ensembles, a novel method to estimate uncertainty with ensemble of quantile-regression-based task networks. Our method not only produces accurate imputations that is robust to high missing rates, but also is computationally efficient due to the fast training of its non-generative model.
  arXiv  Detail & Related papers  (2023-12-03T05:52:30Z)
• Improving Diffusion Models for ECG Imputation with an Augmented Template Prior [43.6099225257178]
  noisy and poor-quality recordings are a major issue for signals collected using mobile health systems. Recent studies have explored the imputation of missing values in ECG with probabilistic time-series models. We present a template-guided denoising diffusion probabilistic model (DDPM), PulseDiff, which is conditioned on an informative prior for a range of health conditions.
  arXiv  Detail & Related papers  (2023-10-24T11:34:15Z)
• Enhanced Gaussian Process Dynamical Models with Knowledge Transfer for Long-term Battery Degradation Forecasting [0.9208007322096533]
  Predicting the end-of-life or remaining useful life of batteries in electric vehicles is a critical and challenging problem. A number of algorithms have incorporated features that are available from data collected by battery management systems. We develop a highly-accurate method that can overcome this limitation.
  arXiv  Detail & Related papers  (2022-12-03T12:59:51Z)
• Stabilizing Machine Learning Prediction of Dynamics: Noise and Noise-inspired Regularization [58.720142291102135]
  Recent has shown that machine learning (ML) models can be trained to accurately forecast the dynamics of chaotic dynamical systems. In the absence of mitigating techniques, this technique can result in artificially rapid error growth, leading to inaccurate predictions and/or climate instability. We introduce Linearized Multi-Noise Training (LMNT), a regularization technique that deterministically approximates the effect of many small, independent noise realizations added to the model input during training.
  arXiv  Detail & Related papers  (2022-11-09T23:40:52Z)
• Dynaformer: A Deep Learning Model for Ageing-aware Battery Discharge Prediction [2.670887944566458]
  We introduce a novel Transformer-based deep learning architecture which is able to simultaneously infer the ageing state from a limited number of voltage/current samples. Our experiments show that the trained model is effective for input current profiles of different complexities and is robust to a wide range of degradation levels.
  arXiv  Detail & Related papers  (2022-06-01T15:31:06Z)
• Evaluating feasibility of batteries for second-life applications using machine learning [0.0]
  This paper presents a combination of machine learning techniques to enable prompt evaluation of retired electric vehicle batteries. The proposed algorithm generates features from available battery current and voltage measurements with simple statistics. It selects and ranks the features using correlation analysis, and employs Gaussian Process Regression enhanced with bagging.
  arXiv  Detail & Related papers  (2022-03-08T18:07:33Z)
• Simple statistical models and sequential deep learning for Lithium-ion batteries degradation under dynamic conditions: Fractional Polynomials vs Neural Networks [1.8899300124593648]
  Longevity and safety of Lithium-ion batteries are facilitated by efficient monitoring and adjustment of the battery operating conditions. It is crucial to implement fast and accurate algorithms for State of Health (SoH) monitoring on the Battery Management System. This paper proposes and compares two data-driven approaches: a Long Short-Term Memory neural network, and a Multivariable Fractional Polynomial regression.
  arXiv  Detail & Related papers  (2021-02-16T12:26:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.