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

2025-10-03

AI Summary

Battery health prognosis faces challenges including nonlinear degradation, measurement noise, and capacity regeneration. Existing data-driven models lack physics-informed guidance, resulting in unreliable long-term predictions. To address this, we propose Karma, a knowledge-aware and frequency-adaptive learning framework. Karma employs a dual-stream deep architecture to separately model high- and low-frequency degradation dynamics; integrates a bi-exponential physical prior with signal decomposition; and leverages particle filtering for physics-consistent parameter estimation. Furthermore, it enables principled uncertainty quantification. Evaluated on two benchmark datasets, Karma reduces mean prediction error by 50.6% and 32.6% compared to state-of-the-art methods. It significantly improves prediction accuracy, robustness, interpretability, and generalizability—demonstrating superior performance across diverse aging conditions and battery chemistries.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Probabilistic Circuits and Graphical Models
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Modeling complex battery degradation with nonlinearity and noise
• Improving long-term health prognostics through knowledge guidance
• Enhancing prediction accuracy and uncertainty quantification for battery management

Innovation

• Knowledge-aware model with frequency-adaptive learning
• Dual-stream architecture capturing long-term and short-term dynamics
• Particle filter optimization for physically consistent prognostics