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 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...
Continuous Charge Distributions01:17

Continuous Charge Distributions

Imagine a bucket of water. It contains many molecules, of the order of 1026 molecules. Thus, although it contains discrete elements (molecules) at the microscopic level, macroscopically, it can be considered continuous. Small volume elements of water, infinitesimal compared to the bulk of the bucket's volume, still contain many molecules. Under this framework, quantized matter is approximated as continuous for practical purposes.
The electric charge can also be subjected to an analogical...
The Electrical Double Layer01:30

The Electrical Double Layer

In the region where two bulk phases meet, an intricate electric charge distribution arises due to charge transfer, ion adsorption, molecular orientation, and charge distortion. This complex distribution is commonly referred to as the electrical double layer.When a solid electrode interfaces with ions in an electrolyte solution, the speed of electron transfer dictates the rates of oxidation and reduction. The electrode acquires a charge through the escape of atoms into the solution as cations or...

You might also read

Related Articles

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

Sort by
Same author

Polymeric microneedles for closed-loop drug delivery: from biosensing to therapy.

RSC advances·2026
Same author

ZIF-8-based chemiresistive CO<sub>2</sub> sensor: fabrication, performance evaluation, and comparison with NDIR and colorimetric methods.

RSC advances·2026
Same author

Light spectrum optimizer and pyramidal dilation attention convolutional neural network for wind energy conversion system using permanent magnet synchronous generator and single-ended primary inductor converter.

Scientific reports·2026
Same author

LiWO-SRDN-based EV charging coordination for stable smart grid systems using a single-switch high step-up zeta converter.

Scientific reports·2026
Same author

Hybrid optimization-based quantum-driven multi-relational graph attention networks for enhanced cyber attack detection in medical IoT networks.

Scientific reports·2026
Same author

Modeling and experimental evaluation of marotti oil biodiesel blends in a diesel engine using response surface methodology and artificial neural networks.

Scientific reports·2026

Related Experiment Videos

Multi-scale temporal convolution attention network for state-of-charge estimation in Li-ion batteries.

S Fouziya Sulthana1, M Sivaramkrishnan2, G Venkatesan3

  • 1Department of Mechatronics Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamil Nadu, 603203, India.

Scientific Reports
|May 23, 2026
PubMed
Summary

This study introduces the Multi-Scale Temporal Convolution Attention Network (MSTCAN) for accurate State of Charge (SOC) estimation in lithium-ion batteries. MSTCAN significantly improves battery management system performance in electric vehicles.

Keywords:
Battery managementDeep learningLithium-ion batteriesMSTCANState of charge

Related Experiment Videos

Area of Science:

  • Electrical Engineering
  • Materials Science
  • Artificial Intelligence

Background:

  • Accurate State of Charge (SOC) estimation is crucial for lithium-ion battery safety, reliability, and efficiency in electric vehicles (EVs) and energy storage.
  • Traditional SOC methods struggle with battery aging, dynamic loads, and temperature variations.
  • Existing deep learning models often fail to capture both short-term transients and long-term SOC evolution simultaneously.

Purpose of the Study:

  • To develop an advanced deep learning model for precise SOC estimation in lithium-ion batteries.
  • To overcome limitations of traditional and current deep learning approaches in SOC prediction.
  • To enhance the performance and reliability of Battery Management Systems (BMS) for EVs.

Main Methods:

  • Proposed a novel Multi-Scale Temporal Convolution Attention Network (MSTCAN).
  • MSTCAN fuses multi-scale temporal convolutions for hierarchical feature extraction and attention mechanisms.
  • Utilized a Tesla Model-3 2170 Li-ion battery dataset, processed with cleaning, normalization, and cycle-based segmentation.

Main Results:

  • MSTCAN achieved a Root Mean Square Error (RMSE) of 1.25% and Mean Absolute Error (MAE) of 0.97%.
  • The model demonstrated a maximum error of 3.12% and a coefficient of determination (R²) of 0.998.
  • MSTCAN significantly outperformed traditional and other deep learning-based SOC estimation methods.

Conclusions:

  • The proposed MSTCAN model offers robust and reliable SOC estimation for lithium-ion batteries.
  • This approach provides a promising solution for upgrading BMS performance and efficiency in practical EV applications.
  • The study highlights the potential of advanced deep learning architectures for battery state monitoring.