EntroLnn: Entropy-Guided Liquid Neural Networks for Operando Refinement of Battery Capacity Fade Trajectories

2026-01-08

arXiv.org

AI Summary

This study addresses the disconnect between state-of-health (SoH) estimation and end-of-life (EoL) prediction in battery capacity fade trajectory (CFT) modeling by proposing EntroLnn, a novel framework that unifies online CFT refinement as a single task. The approach innovatively integrates entropy-based features derived from real-time temperature fields with a deformable Liquid Neural Network (LNN) to enable lightweight, adaptive modeling of dynamic battery degradation behavior. Experimental results demonstrate that EntroLnn achieves superior performance across diverse battery chemistries and operating conditions, yielding a remarkably low mean absolute error of 0.004577 in CFT prediction and an EoL prediction error of merely 18 cycles. The framework thus offers high accuracy, strong generalization capability, and enhanced interpretability.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Battery capacity degradation prediction has long been a central topic in battery health analytics, and most studies focus on state of health (SoH) estimation and end of life (EoL) prediction. This study extends the scope to online refinement of the entire capacity fade trajectory (CFT) through EntroLnn, a framework based on entropy-guided transformable liquid neural networks (LNNs). EntroLnn treats CFT refinement as an integrated process rather than two independent tasks for pointwise SoH and EoL. We introduce entropy-based features derived from online temperature fields, applied for the first time in battery analytics, and combine them with customized LNNs that model temporal battery dynamics effectively. The framework enhances both static and dynamic adaptability of LNNs and achieves robust and generalizable CFT refinement across different batteries and operating conditions. The approach provides a high fidelity battery health model with lightweight computation, achieving mean absolute errors of only 0.004577 for CFT and 18 cycles for EoL prediction. This work establishes a foundation for entropy-informed learning in battery analytics and enables self-adaptive, lightweight, and interpretable battery health prediction in practical battery management systems.

Problem

• battery capacity fade trajectory
• online refinement
• state of health
• end of life prediction
• battery health analytics

Innovation

• Entropy-guided learning
• Liquid Neural Networks
• Capacity fade trajectory
• Online battery health prediction
• Temperature-field entropy features