End-to-End Framework for Predicting the Remaining Useful Life of Lithium-Ion Batteries

2025-05-22

AI Summary

To address the challenges of insufficient prediction accuracy and poor cross-scenario generalization in lithium-ion battery remaining useful life (RUL) estimation, this paper proposes an end-to-end deep learning framework. First, a feature enhancement method is designed that jointly incorporates statistical metrics and delta differencing to effectively extract and denoise degradation-relevant features. Second, a hybrid CNN-A-LSTM-ODE-LSTM architecture is introduced to simultaneously capture local temporal patterns, long-range dependencies, and continuous-time degradation dynamics. Finally, a few-shot cross-scenario transfer learning mechanism is integrated to improve adaptability across diverse operating conditions. Evaluated on two widely used public datasets, the proposed method achieves an RMSE of 101.59, outperforming state-of-the-art deep and conventional models. Experimental results demonstrate its superior accuracy, robustness to domain shifts, and practical deployability for real-world RUL prognostics.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate prediction of the Remaining Useful Life (RUL) is essential for enabling timely maintenance of lithium-ion batteries, impacting the operational efficiency of electric applications that rely on them. This paper proposes a RUL prediction approach that leverages data from recent charge-discharge cycles to estimate the number of remaining usable cycles. The approach introduces both a novel signal processing pipeline and a deep learning prediction model. In the signal preprocessing pipeline, a derived capacity feature is computed based on current and capacity signals. Alongside original capacity, voltage and current, these features are denoised and enhanced using statistical metrics and a delta-based method to capture differences between the current and previous cycles. In the prediction model, the processed features are then fed into a hybrid deep learning architecture composed of 1D Convolutional Neural Networks (CNN), Attentional Long Short-Term Memory (A-LSTM), and Ordinary Differential Equation-based LSTM (ODE-LSTM) modules. This architecture is designed to capture both local signal characteristics and long-range temporal dependencies while modeling the continuous-time dynamics of battery degradation. The model is further evaluated using transfer learning across different learning strategies and target data partitioning scenarios. Results indicate that the model maintains robust performance, even when fine-tuned on limited target data. Experimental results on two publicly available large-scale datasets demonstrate that the proposed method outperforms a baseline deep learning approach and machine learning techniques, achieving an RMSE of 101.59, highlighting its strong potential for real-world RUL prediction applications.

Problem

• Predicts remaining useful life of lithium-ion batteries accurately
• Uses deep learning to analyze charge-discharge cycle data
• Enhances signal processing for better battery degradation modeling

Innovation

• Novel signal processing pipeline for feature enhancement
• Hybrid deep learning with CNN, A-LSTM, ODE-LSTM
• Transfer learning for robust performance on limited data