Pace: Physics-Aware Attentive Temporal Convolutional Network for Battery Health Estimation

• URL: http://arxiv.org/abs/2512.11332v2
• Date: Tue, 16 Dec 2025 09:17:10 GMT
• Title: Pace: Physics-Aware Attentive Temporal Convolutional Network for Battery Health Estimation
• Abstract summary: Pace is a physics-aware attentive temporal convolutional network for battery health estimation.<n>We develop three battery-specific modules, including dilated temporal blocks for efficient temporal encoding, chunked attention blocks for context modeling, and a dual-head output block for fusing short- and long-term battery degradation patterns.
• Score: 5.570789346088817
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Batteries are critical components in modern energy systems such as electric vehicles and power grid energy storage. Effective battery health management is essential for battery system safety, cost-efficiency, and sustainability. In this paper, we propose Pace, a physics-aware attentive temporal convolutional network for battery health estimation. Pace integrates raw sensor measurements with battery physics features derived from the equivalent circuit model. We develop three battery-specific modules, including dilated temporal blocks for efficient temporal encoding, chunked attention blocks for context modeling, and a dual-head output block for fusing short- and long-term battery degradation patterns. Together, the modules enable Pace to predict battery health accurately and efficiently in various battery usage conditions. In a large public dataset, Pace performs much better than existing models, achieving an average performance improvement of 6.5 and 2.0x compared to two best-performing baseline models. We further demonstrate its practical viability with a real-time edge deployment on a Raspberry Pi. These results establish Pace as a practical and high-performance solution for battery health analytics.

Related papers

• AI-Driven Surrogate Models for Predicting Electrode-Scale Discharge Behavior in Lithium-Ion Batteries [47.27974914502511]
  We introduce a deep learning surrogate pipeline based on the Swin3D Transformer to predict discharge dynamics directly from data.<n>The proposed method reduces the computational overhead by orders of magnitude, providing a scalable and efficient framework for high- throughput battery design and optimization.
  arXiv  Detail & Related papers  (2026-07-22T09:10:48Z)
• Motion-Specific Battery Health Assessment for Quadrotors Using High-Fidelity Battery Models [8.332702331786317]
  This work presents an end to end framework for motion aware battery health assessment in quadrotors.<n>We first design a wide range current sensing module to capture motion specific current profiles during real flights.<n>High fidelity battery model is calibrated using reference performance tests and a metaheuristic based on a degradation coupled electrochemical model.
  arXiv  Detail & Related papers  (2026-03-13T08:52:51Z)
• Enhanced Evolutionary Multi-Objective Deep Reinforcement Learning for Reliable and Efficient Wireless Rechargeable Sensor Networks [44.91945854166524]
  Wireless rechargeable sensor networks (WRSNs) with mobile charging capabilities offer a promising solution to extend network lifetime.<n>WRSNs face critical challenges from the inherent trade-off between maximizing the node survival rates and maximizing charging energy efficiency.
  arXiv  Detail & Related papers  (2025-10-24T03:30:00Z)
• PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching [51.98089287914147]
  textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.<n>Inspired by the two-stage decision-making process in humans, we propose a textbfPick-and-textbflay textbfMemory (PM) construction module for dynamic bfStereo matching, dubbed as bftextPPMStereo.
  arXiv  Detail & Related papers  (2025-10-23T03:52:39Z)
• Knowledge-Aware Modeling with Frequency Adaptive Learning for Battery Health Prognostics [27.840159692578354]
  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.
  arXiv  Detail & Related papers  (2025-10-03T09:24:38Z)
• Joint Resource Management for Energy-efficient UAV-assisted SWIPT-MEC: A Deep Reinforcement Learning Approach [50.52139512096988]
  6G Internet of Things (IoT) networks face challenges in remote areas and disaster scenarios where ground infrastructure is unavailable.<n>This paper proposes a novel aerial unmanned vehicle (UAV)-assisted computing (MEC) system enhanced by directional antennas to provide both computational and energy support for ground edge terminals.
  arXiv  Detail & Related papers  (2025-05-06T06:46:19Z)
• State-of-Health Prediction for EV Lithium-Ion Batteries via DLinear and Robust Explainable Feature Selection [14.672460390509334]
  We propose an explainable, data-driven state-of-health (SOH) prediction framework tailored for electric vehicles (EVs)<n>We extract twenty meaningful features from voltage, current, temperature, and time profiles, and select key features using Pearson correlation and Shapley additive explanations (SHAP)<n>The SHAP-based selection yields consistent feature importance across multiple cells, effectively capturing cell-to-cell variability (CtCV)
  arXiv  Detail & Related papers  (2025-01-20T15:28:20Z)
• Prognosis of Multivariate Battery State of Performance and Health via Transformers [0.0]
  Batteries are an essential component in a deeply decarbonized future. Understanding battery performance and "useful life" as a function of design and use is of paramount importance. We present a first step in that direction via deep transformer networks for the prediction of 28 battery state of health descriptors.
  arXiv  Detail & Related papers  (2023-09-18T15:04:40Z)
• A Mapping Study of Machine Learning Methods for Remaining Useful Life Estimation of Lead-Acid Batteries [0.0]
  State of Health (SoH) and Remaining Useful Life (RUL) contribute to enhancing predictive maintenance, reliability, and longevity of battery systems. This paper presents a mapping study of the state-of-the-art in machine learning methods for estimating the SoH and RUL of lead-acid batteries.
  arXiv  Detail & Related papers  (2023-07-11T10:41:41Z)
• 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)
• A Machine Learning-based Digital Twin for Electric Vehicle Battery Modeling [10.290868910435153]
  Electric Vehicles (EVs) are subject to aging and performance deterioration over time. This work proposes a battery digital twin structure designed to accurately reflect battery dynamics at the run time.
  arXiv  Detail & Related papers  (2022-06-16T10:47:41Z)
• Optimizing a domestic battery and solar photovoltaic system with deep reinforcement learning [69.68068088508505]
  A lowering in the cost of batteries and solar PV systems has led to a high uptake of solar battery home systems. In this work, we use the deep deterministic policy algorithm to optimise the charging and discharging behaviour of a battery within such a system.
  arXiv  Detail & Related papers  (2021-09-10T10:59:14Z)
• Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraints [44.311278843238675]
  We consider an over-the-air FEEL system with analog gradient aggregation. We propose an energy-aware dynamic device scheduling algorithm to optimize the training performance. Under a highly unbalanced local data distribution, the proposed algorithm can increase the accuracy by 4.9%.
  arXiv  Detail & Related papers  (2021-05-31T08:55:02Z)
• Universal Battery Performance and Degradation Model for Electric Aircraft [52.77024349608834]
  Design, analysis, and operation of electric vertical takeoff and landing aircraft (eVTOLs) requires fast and accurate prediction of Li-ion battery performance. We generate a battery performance and thermal behavior dataset specific to eVTOL duty cycles. We use this dataset to develop a battery performance and degradation model (Cellfit) which employs physics-informed machine learning.
  arXiv  Detail & Related papers  (2020-07-06T16:10:54Z)

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.