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
Ultrasonic welding creates lithium-garnet interface in seconds
image:
Cross-sectional Li-LLZO interfacial morphologies obtained by ultrasonic welding in seconds at room temperature.
view moreCredit: ©Eric Jianfeng Cheng et al.
Bonding lithium metal to a ceramic surface should be a dream team combination for creating solid-state lithium metal batteries. However, getting them to bond is the hard part. Impurity layers tend to form on the surface, which hinders a process called wetting that is crucial to the adherence of metals and ceramics. To get these two materials with very different characteristics to bond, a different strategy was needed. Researchers at Tohoku University's Advanced Institute for Materials Research (WPI-AIMR) thought outside the box, finding that ultrasonic welding brought these two materials together.
"This is an underexplored method in our field. Applying ultrasonic welding to bond lithium metal directly to a garnet-type oxide electrolyte is, to our knowledge, unprecedented in this context," remarks Eric Jianfeng Cheng (WPI-AIMR).
The research describing this exciting new implementation strategy - which may help create more efficient and practical solid-state energy storage technology than conventional lithium-ion batteries - was published in Small Structures on March 19, 2026.
Solid-state lithium metal batteries are widely regarded as a promising next-generation energy storage technology. Among solid electrolytes, the garnet-type oxide Li₇La₃Zr₂O₁₂ (LLZO) has attracted particular attention because of its high ionic conductivity and chemical stability. However, establishing intimate physical contact between lithium metal and the ceramic electrolyte (Li₇La₃Zr₂O₁₂ or LLZO) is difficult. The stiff, irregular shapes of a marble slab and a metal sheet interface are challenging to bond mainly because both surfaces readily form insulating Li₂CO₃ layers when exposed to air. This occurs for the Li metal surface in particular, and creates a barrier of sorts that blocks Li-ion transport and hinders wetting.
Ultrasonic welding (USW), a mature industrial technique widely used for joining metallic components, offers a solution that is fundamentally different from conventional strategies (which are costly and process-intensive). The results of this study demonstrate that USW can form intimate lithium-LLZO interfaces within seconds at room temperature. The ultrasonic vibration disrupts insulating surface layers such as Li₂CO₃, while controlled pressure and high-frequency oscillation enable lithium metal to plastically deform and conform to the rigid LLZO surface, eliminating interfacial voids and establishing direct solid-state contact without melting or thermal activation.
Using USW alone, the interfacial resistance was reduced to approximately 225 Ω·cm². When combined with a thin sputtered Au interlayer, the resistance further decreased to about 1.5 Ω·cm², placing it among the lowest values reported for room-temperature processed Li-LLZO interfaces. Symmetric cell testing confirmed its practical feasibility as well.
This rapid, room-temperature bonding strategy provides a manufacturing-friendly and efficient pathway for oxide-based solid-state batteries. This work contributes to the development of safer and higher-energy batteries for electric vehicles, renewable energy storage, and portable electronics.
About the World Premier International Research Center Initiative (WPI)
The WPI program was launched in 2007 by Japan's Ministry of Education, Culture, Sports, Science and Technology (MEXT) to foster globally visible research centers boasting the highest standards and outstanding research environments. Numbering more than a dozen and operating at institutions throughout the country, these centers are given a high degree of autonomy, allowing them to engage in innovative modes of management and research. The program is administered by the Japan Society for the Promotion of Science (JSPS).
See the latest research news from the centers at the WPI News Portal: https://www.eurekalert.org/newsportal/WPI
Main WPI program site: www.jsps.go.jp/english/e-toplevel
Advanced Institute for Materials Research (AIMR)
Tohoku University
Establishing a World-Leading Research Center for Materials Science
AIMR aims to contribute to society through its actions as a world-leading research center for materials science and push the boundaries of research frontiers. To this end, the institute gathers excellent researchers in the fields of physics, chemistry, materials science, engineering, and mathematics and provides a world-class research environment.
AIMR site: https://www.wpi-aimr.tohoku.ac.jp/en/
Journal
Small Structures
Article Title
Ultrasonic Welding of Garnet Solid Electrolytes to Lithium Metal: Achieving Intimate Interfacial Contact in Seconds
Article Publication Date
19-Mar-2026
New lithium-ion battery design could power longer-lasting electric vehicles and portable devices
University of Surrey
A new battery design that could significantly extend the range of electric vehicles and the lifespan of portable electronics has been developed by researchers at the University of Surrey’s Advanced Technology Institute (ATI).
In a study published in ACS Applied Energy Materials, researchers introduce a novel lithium-ion battery anode that delivers some of the highest energy storage capacities reported for silicon–carbon nanotube systems, while maintaining stability over hundreds of charge cycles.
Lithium-ion batteries power much of modern technology – from smartphones and wearables to electric vehicles. Graphite, the most commonly used anode material, is stable but limited in the amount of energy it can store. Silicon, on the other hand, offers far greater capacity, but it expands during charging, causing it to crack and degrade over time.
To overcome this, the research team developed a new “Vertically Integrated Silicon–Carbon Nanotube” (VISiCNT) structure. The design grows dense forests of carbon nanotubes directly onto copper foil and coats them with a thin layer of silicon, creating a flexible, conductive scaffold that can absorb expansion while maintaining performance.
The resulting anode can store a very large amount of energy for its weight. In laboratory tests, it stored more than 3500 milliampere-hours per gram – close to the maximum possible for silicon and far higher than the graphite (370 mAh/g) used in today’s batteries. It also demonstrated improved stability and performance over repeated charge cycles.
Dr Muhammad Ahmad, Research Fellow at the University of Surrey’s ATI and lead author of the study, said:
“There’s been a growing push for battery innovation, as many of today’s technologies are limited by how much energy batteries can store. Our VISiCNT design offers a practical route to harness silicon’s huge storage capability without sacrificing cycle life.
“This is a much-needed breakthrough, delivering very high capacity, fast charging and long-term durability, while bringing us closer to batteries that can power electric vehicles and everyday devices for much longer on a single charge.”
A key advantage of the new approach is that the carbon nanotubes are grown directly onto copper – the material already used in commercial batteries – using a scalable manufacturing process. This could make it easier to integrate the technology into existing industrial production lines.
Professor Ravi Silva, Principal Investigator and Director of the ATI, said:
“This work is an important step towards bringing CNT-silicon anodes out of the lab and into real-world manufacturing. We can grow carbon nanotube structures directly onto copper foil at speed and tailor the silicon layer for stability, meaning this approach could be integrated into existing battery production lines with minimal disruption. The technology has clear potential not just for electric vehicles, but also for grid storage and smaller batteries used in microelectronics.
“We are very proud to present yet another CNT technology following our initial research in delivering the world’s darkest material, VANTA-Black via the university spin-out Surrey NanoSystems Ltd., which is showing real-world impact of fundamental research funded by UKRI.”
As demand for energy storage grows, batteries will need to store more energy, charge faster and last longer to support the UK’s transition to Net Zero. The VISiCNT design offers a promising route to meeting these challenges and could be key to powering next-generation electric vehicles and phones.
[ENDS]
Notes to editors
Dr Muhammad Ahmad and Professor Ravi Silva are available for interview; please contact mediarelations@surrey.ac.uk to arrange.
The full paper can be found here: https://doi.org/10.1021/acsaem.5c03862
Journal
ACS Applied Energy Materials
Article Title
Vertically Integrated Silicon–Carbon Nanotube Architectures for High-Capacity and Robust Lithium-Ion Battery Anodes
Article Publication Date
23-Mar-2026
No comments:
Post a Comment