Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 20, 2026

Identification and Quantification of Decomposition Mechanisms in Lithium-Ion Batteries; Input to Heat Flow Simulation for Modeling Thermal Runaway
11:25

Identification and Quantification of Decomposition Mechanisms in Lithium-Ion Batteries; Input to Heat Flow Simulation for Modeling Thermal Runaway

Published on: March 7, 2022

Deep learning-based RUL and SOH prediction of lithium-ion batteries using LOCO.

Bisma Ali1, Irum Matloob1, Nuha Alkhalifa2

  • 1Department of Software Engineering, Fatima Jinnah Women University, Rawalpindi, Pakistan.

Scientific Reports
|June 18, 2026
PubMed
Summary

Related Concept Videos

Batteries and Fuel Cells03:12

Batteries and Fuel Cells

A battery is a galvanic cell that is used as a source of electrical power for specific applications. Modern batteries exist in a multitude of forms to accommodate various applications, from tiny button batteries such as those that power wristwatches to the very large batteries used to supply backup energy to municipal power grids. Some batteries are designed for single-use applications and cannot be recharged (primary cells), while others are based on conveniently reversible cell reactions that...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Metabolomic Classification of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome via Explainable Ensemble Learning and Pareto-Guided Feature Selection.

International journal of molecular sciences·2026
Same author

Fecal Extracellular Vesicle Metabolomics as a Non-Invasive Biomarker Source in Colorectal Cancer: TPOT AutoML Superiority over Tree-Based Models with SHAP and LIME Clinical Interpretability.

International journal of molecular sciences·2026
Same author

Explainable Boosting Machine in Sepsis Prediction Using Platelet Metabolomics: An Interpretable Machine Learning Approach.

Diagnostics (Basel, Switzerland)·2026
Same author

Tensor enhanced chest cancer classification via CNN and Vision Transformer models.

PloS one·2026
Same author

Machine learning-driven image encryption using SVM for enhanced security and computational efficiency.

Scientific reports·2026
Same author

Enhancing medical image security with quantum DNA dual encryption.

Scientific reports·2026

Accurate Remaining Useful Life (RUL) prediction for lithium-ion batteries is crucial. This study benchmarks deep learning models (LSTM, TCN, TFT) using rigorous cross-cell validation, revealing degradation complexity impacts performance.

Area of Science:

  • Battery Engineering
  • Data Science
  • Machine Learning

Background:

  • Lithium-ion battery degradation impacts reliability and safety.
  • Accurate Remaining Useful Life (RUL) and State of Health (SOH) prediction are vital for battery prognostics.
  • Deep learning offers potential for advanced battery health monitoring.

Purpose of the Study:

  • To establish a comprehensive benchmarking framework for comparing deep learning models in battery prognostics.
  • To evaluate the performance of Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Temporal Fusion Transformer (TFT) architectures.
  • To assess model generalization capabilities using a strict Leave-One-Cell-Out (LOCO) validation protocol.

Main Methods:

  • Utilized two public datasets: NASA Ames and Oxford Battery Degradation.
Keywords:
Battery degradation modelingLeave-One-Cell-Out (LOCO) cross-validationLithium-ion batteriesLong Short-Term Memory (LSTM)Regression metrics (MAE, RMSE, [Formula: see text])Remaining useful life (RUL)State of health (SOH)Temporal Convolutional Network (TCN)Temporal Fusion Transformer (TFT)

Related Experiment Videos

Last Updated: Jun 20, 2026

Identification and Quantification of Decomposition Mechanisms in Lithium-Ion Batteries; Input to Heat Flow Simulation for Modeling Thermal Runaway
11:25

Identification and Quantification of Decomposition Mechanisms in Lithium-Ion Batteries; Input to Heat Flow Simulation for Modeling Thermal Runaway

Published on: March 7, 2022

  • Employed a sliding-window approach to create time-series sequences of degradation features.
  • Applied identical preprocessing, feature engineering, and normalization across all models.
  • Implemented a Leave-One-Cell-Out (LOCO) cross-cell validation strategy.
  • Evaluated models using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R2 scores.

    • Main Results:

    • Model performance was significantly influenced by degradation complexity and cross-cell heterogeneity.
    • The study identified variations in model performance based on the chosen deep learning architecture.
    • Rigorous statistical analysis was performed to differentiate training effects from validation fold variations.

    Conclusions:

    • Carefully designed evaluation protocols and rigorous cross-cell validation are essential for reliable battery prognostics benchmarking.
    • The findings underscore the need for robust methods to handle degradation complexity and heterogeneity in lithium-ion battery health assessment.
    • This work provides a standardized framework for future research in deep learning-based battery prognostics.