Hybrid Deep Learning with Temporal Data Augmentation for Accurate Remaining Useful Life Prediction of Lithium-Ion Batteries

2026-03-28

AI Summary

This study addresses the limited robustness and generalization capability of existing methods for predicting the remaining useful life (RUL) of lithium-ion batteries under complex operating conditions and data scarcity. To overcome these challenges, the authors propose CDFormer, a hybrid deep learning model that integrates convolutional neural networks, deep residual shrinkage networks, and Transformer encoders to jointly capture both local and global temporal dynamics of battery degradation. The approach further introduces a composite time-series data augmentation strategy—combining Gaussian noise injection, time warping, and resampling—to enhance robustness against measurement noise and temporal variations. Experimental results on two real-world datasets demonstrate that CDFormer significantly outperforms baseline models such as RNNs and Transformers, achieving superior prediction accuracy and generalization performance on key evaluation metrics.

Abstract

Accurate prediction of lithium-ion battery remaining useful life (RUL) is essential for reliable health monitoring and data-driven analysis of battery degradation. However, the robustness and generalization capabilities of existing RUL prediction models are significantly challenged by complex operating conditions and limited data availability. To address these limitations, this study proposes a hybrid deep learning model, CDFormer, which integrates convolutional neural networks, deep residual shrinkage networks, and Transformer encoders extract multiscale temporal features from battery measurement signals, including voltage, current, and capacity. This architecture enables the joint modeling of local and global degradation dynamics, effectively improving the accuracy of RUL prediction.To enhance predictive reliability, a composite temporal data augmentation strategy is proposed, incorporating Gaussian noise, time warping, and time resampling, explicitly accounting for measurement noise and variability. CDFormer is evaluated on two real-world datasets, with experimental results demonstrating its consistent superiority over conventional recurrent neural network-based and Transformer-based baselines across key metrics. By improving the reliability and predictive performance of RUL prediction from measurement data, CDFormer provides accurate and reliable forecasts, supporting effective battery health monitoring and data-driven maintenance strategies.

Problem

• Remaining Useful Life
• Lithium-Ion Batteries
• Data Scarcity
• Complex Operating Conditions
• Prediction Robustness

Innovation

• hybrid deep learning
• temporal data augmentation
• remaining useful life prediction
• multiscale temporal features
• battery degradation modeling