Optimal Signal Decomposition-based Multi-Stage Learning for Battery Health Estimation

2025-01-24

AI Summary

Battery aging exhibits strong nonlinearity and capacity self-recovery, leading to significant errors in state-of-health (SOH) estimation. To address this, we propose a multi-stage learning framework based on optimal signal decomposition. We innovatively design an optimized variational mode decomposition (OVMD) algorithm to achieve physically interpretable decoupling of aging signals. Furthermore, we introduce a multi-stage spatiotemporal feature collaboration mechanism to jointly model capacity regeneration and degradation dynamics in the time–frequency domain. Evaluated on public battery aging datasets, our method achieves a mean absolute error of only 0.26% in SOH estimation—substantially outperforming existing approaches. The model is lightweight and computationally efficient, enabling real-time deployment on embedded battery management systems (BMS).

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Battery health estimation is fundamental to ensure battery safety and reduce cost. However, achieving accurate estimation has been challenging due to the batteries' complex nonlinear aging patterns and capacity regeneration phenomena. In this paper, we propose OSL, an optimal signal decomposition-based multi-stage machine learning for battery health estimation. OSL treats battery signals optimally. It uses optimized variational mode decomposition to extract decomposed signals capturing different frequency bands of the original battery signals. It also incorporates a multi-stage learning process to analyze both spatial and temporal battery features effectively. An experimental study is conducted with a public battery aging dataset. OSL demonstrates exceptional performance with a mean error of just 0.26%. It significantly outperforms comparison algorithms, both those without and those with suboptimal signal decomposition and analysis. OSL considers practical battery challenges and can be integrated into real-world battery management systems, offering a good impact on battery monitoring and optimization.

Problem

• Battery Health Assessment
• Aging Process Complexity
• Capacity Self-Recovery

Innovation

• OSL Multistep Learning Method
• Optimal Signal Splitting Technique
• Battery Health Assessment