New fusion model boosts lithium-ion battery remaining useful life prediction accuracy and reliability for safer electric mobility
image:
Lithium-ion battery remaining useful life prediction based on data-driven and particle filter fusion model
view moreCredit: GREEN ENERGY AND INTELLIGENT TRANSPORTATION
Lithium-ion batteries power everything from electric vehicles and portable electronics to grid-scale energy storage, thanks to their high energy density, lack of memory effect, and adaptability across temperature ranges. However, repeated charge-discharge cycles cause gradual capacity fade, eventually rendering the battery unusable when it drops below a critical threshold. Accurate prediction of remaining useful life (RUL)—the number of cycles left before this failure point—is essential for proactive battery management, preventing unexpected failures, optimizing replacement schedules, and reducing costs and safety risks in real-world applications.
Traditional RUL prediction methods fall into three categories: physics-based models that simulate internal degradation processes, data-driven approaches that learn patterns from historical data, and hybrid fusions that combine their strengths. While physics-based models offer interpretability, they demand extensive prior knowledge and struggle with complex nonlinear dynamics. Pure data-driven techniques, such as convolutional neural networks (CNNs) for feature extraction or gated recurrent units (GRUs) for time-series forecasting, excel in accuracy when ample high-quality data is available but can accumulate errors over long horizons and lack robustness to noise or limited samples. Hybrid methods address these gaps by integrating probabilistic state estimation, like particle filters (PF), to correct predictions and enhance stability.
A recent study introduces an advanced hybrid framework, the CNN-GRU-PF fusion model, to overcome these limitations. The approach begins by preprocessing battery capacity data using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) combined with Pearson correlation analysis, effectively decomposing the series into components, reconstructing them to suppress noise, and preserving essential degradation trends. A one-dimensional CNN then extracts high-dimensional spatial features from the processed capacity sequences, while the GRU captures long-term temporal dependencies to generate initial capacity predictions. These predictions serve as observations for the PF, which leverages its strong state estimation capabilities to correct errors and produce optimized outputs. A moving window mechanism iteratively updates the training set by incorporating PF-refined values back into the CNN-GRU model, enabling dynamic adaptation and significantly boosting long-term forecasting performance.
Experimental validation on benchmark NASA datasets, including battery B5, alongside CALCE and custom experimental data, demonstrates the model's superior performance. For battery B5, the CNN-GRU-PF achieves remarkable improvements in prediction accuracy of 87.27% over standalone GRU, 82.88% over PF alone, and 55.43% over the simpler GRU-PF combination. Similar gains appear across other batteries, with enhanced stability even when trained on limited data samples. The iterative updating with the moving window, despite modestly increasing computation time, delivers substantial accuracy gains compared to static versions, underscoring the value of continuous learning in handling evolving degradation patterns.
These advancements promise substantial benefits for battery-dependent technologies. More precise RUL estimates enable better state-of-health monitoring in electric vehicles, extending operational range confidence and preventing abrupt failures that could compromise safety. In energy storage systems, reliable predictions optimize maintenance, reduce downtime, and support efficient integration of renewables. The model's robustness to noise and small datasets makes it practical for diverse operating conditions.
Looking ahead, the CNN-GRU-PF framework holds strong potential for real-time implementation in battery management systems of electric vehicles and grid applications. Future work could validate it on field data from actual vehicles, explore performance under extreme temperatures or abusive conditions, and incorporate additional health indicators like voltage or temperature curves for even greater precision. Extensions to multi-cell packs or different chemistries would broaden applicability, accelerating safer, more sustainable battery utilization.
In essence, this innovative fusion model represents a major stride in battery prognostics by synergistically blending deep learning's pattern recognition with probabilistic filtering's error correction and adaptive training. It delivers unprecedented accuracy and robustness, laying a foundation for smarter battery health management that enhances reliability, longevity, and safety across electrified systems.
Reference
Author: Chunling Wu a b, Chenfeng Xu a b, Liding Wang a b, Juncheng Fu a b, Jinhao Meng c
Title of original paper: Lithium-ion battery remaining useful life prediction based on data-driven and particle filter fusion model
Article link: https://www.sciencedirect.com/science/article/pii/S2773153725000179
Journal: Green Energy and Intelligent Transportation
DOI: 10.1016/j.geits.2025.100267
Affiliations:
a School of Energy and Electrical Engineering, Chang'an University, Xi'an 710064, China
b Shaanxi Key Laboratory of Transportation New Energy Development, Application and Vehicle Energy Saving Technology, Xi'an 710064, China
c School of Electrical Engineering, Xi'an Jiaotong University, Xi'an 710049, China
Journal
Green Energy and Intelligent Transportation
Article Title
Lithium-ion battery remaining useful life prediction based on data-driven and particle filter fusion model
Pioneering detection of lithium plating in lithium-ion capacitors enables safer ultra-fast charging for next-generation energy storage
Beijing Institute of Technology Press Co., Ltd
image:
Lithium plating accurate detection of lithium-ion capacitors upon high-rate charging
view moreCredit: GREEN ENERGY AND INTELLIGENT TRANSPORTATION
Lithium-ion capacitors (LICs) bridge the performance gap between traditional lithium-ion batteries and supercapacitors, delivering superior power density, extended cycle life, and significantly higher energy density than conventional double-layer capacitors. These attributes position LICs as a compelling solution for demanding applications such as electric vehicle acceleration, regenerative braking in urban rail systems, wind power smoothing, smart grid stabilization, and uninterruptible power supplies. Their ability to charge in seconds makes them particularly attractive for high-power scenarios, yet rapid charging introduces a serious risk: lithium plating on the anode. This unwanted deposition of metallic lithium can lead to reduced efficiency, capacity fade, increased internal resistance, and in severe cases, dendrite formation that risks short circuits and thermal runaway. Until recently, no direct or precise method existed to monitor lithium plating specifically in LICs during high-rate charging, limiting the safe exploitation of their full potential.
In a groundbreaking study, researchers developed the first accurate detection approach for lithium plating in LICs by employing 3-electrode pouch-type cells and focusing on differential analysis of the anode potential, moving beyond conventional terminal voltage monitoring. This innovative setup allowed precise tracking of plating onset through multiple complementary techniques: differential charging voltage (DCV) during charging, Coulombic efficiency (CE) assessment, and voltage relaxation profile (VRP) analysis post-charge. These methods revealed that lithium plating initiates at a charging rate of 20 C. Below 50 C, the deposited lithium remains largely reversible, stripping back during discharge without significant harm to performance. Above 50 C, however, irreversible "dead" lithium accumulates, confirmed by scanning electron microscopy showing dendritic agglomerates on the anode after cycling. The study also uncovered two distinct reverse reactions following deposition—lithium stripping and lithium intercalation—with potential differences of approximately 20 mV under relaxation and 45 mV under constant-voltage conditions on soft carbon anodes. In constant-current-constant-voltage protocols, the cutoff current in the voltage hold phase critically influences plating behavior, with lower cutoffs exacerbating intercalation and stripping dynamics.
To demonstrate broader applicability, the CE and VRP methods were successfully extended to high-capacity 1,100 F commercial LIC pouch cells, where irreversible plating was detected starting at 70 C. This validation confirms the techniques' reliability for indirect, non-destructive detection in practical, two-electrode systems, offering a pathway to monitor plating without specialized hardware.
These findings carry substantial benefits for energy storage safety and efficiency. By pinpointing safe charging thresholds and distinguishing reversible from irreversible plating, the approach prevents capacity loss and enhances cycle life, while mitigating risks of thermal events in high-power devices. The methods provide actionable data for real-time battery management systems, enabling dynamic adjustment of charging protocols to maintain performance under demanding conditions.
Looking forward, this research opens avenues for optimized LIC charging strategies that maximize power delivery while preserving longevity, such as adaptive multi-stage protocols or integration with advanced thermal management. Future efforts could refine these detection techniques for in-situ application in full systems, explore plating behavior under varied temperatures or aging, and extend insights to hybrid configurations combining LICs with other storage types. Such advancements would accelerate adoption in electric mobility, renewable integration, and high-reliability power backup.
Ultimately, this work represents a pivotal advancement in LIC technology by delivering the first robust framework for lithium plating detection during ultra-fast charging. It equips engineers with essential tools to harness LICs' hybrid strengths safely and effectively, paving the way for more reliable, high-performance energy solutions that support the transition to sustainable, electrified infrastructures.
Reference
Author: Shasha Zhao a b, Xianzhong Sun a b c d, Yabin An a b c, Zhang Guo a e, Chen Li a b d, Yanan Xu a b d, Yi Li f, Zhao Li g, Xiong Zhang a b c d, Kai Wang a b c d, Yanwei Ma a b c d
Title of original paper: Lithium plating accurate detection of lithium-ion capacitors upon high-rate charging
Article link: https://www.sciencedirect.com/science/article/pii/S2773153725000180
Journal: Green Energy and Intelligent Transportation
DOI: 10.1016/j.geits.2025.100268
Affiliations:
a Institute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, China
b University of Chinese Academy of Sciences, Beijing 100049, China
c Key Laboratory of High Density Electromagnetic Power and Systems (Chinese Academy of Sciences), Haidian District, Beijing 100190, China
d Shandong Key Laboratory of Advanced Electromagnetic Conversion Technology, Institute of Electrical Engineering and Advanced Electromagnetic Drive Technology, Qilu Zhongke, Jinan 250013, China
e Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, China
f Department of Materials Engineering, KU Leuven, Leuven 3001, Belgium
g Department of Chemistry, University of Liverpool, Liverpool L69 7ZD, United Kingdom
Journal
Green Energy and Intelligent Transportation
Method of Research
Experimental study
Subject of Research
Not applicable
Article Title
Lithium plating accurate detection of lithium-ion capacitors upon high-rate charging
No comments:
Post a Comment