Issue |
E3S Web Conf.
Volume 619, 2025
3rd International Conference on Sustainable Green Energy Technologies (ICSGET 2025)
|
|
---|---|---|
Article Number | 03020 | |
Number of page(s) | 9 | |
Section | Smart Electronics for Sustainable Solutions | |
DOI | https://doi.org/10.1051/e3sconf/202561903020 | |
Published online | 12 March 2025 |
MLA-Machine Learning Approach for Dependable Battery Condition Monitoring in Electric Vehicles
1 Department of Pharmacology, School of Pharmacy, RK University, Rajkot -360020, Gujarat, India
2 Department of Electrical and Electronics Engineering, Saveetha Engineering College, Chennai, India
3 Department of Electrical Engineering, National Institute of Technology, Aizawl, Mizoram, India
4 Lovely Professional University, Phagwara, India
5 Department of Mechanical Engineering, New Horizon College of Engineering, Bangalore, India
6 Department of Electrical and Electronics Engineering, Vel Tech Rangrajan Dr. Sagunthala R & D Institute of Science and Technology, Chennai, Tamil Nadu, India
* Corresponding author: pravin.tirgar@rku.ac.in
The paper introduces smart battery monitoring to address the growing demand in the automotive market for efficient and reliable battery solutions. It uses a machine learning framework that runs a Gated Recurrent Unit (GRU) network with an attention mechanism grow the accuracy and lifespan of battery health predictions. The GRU model study real-time variables such as voltage, current, and temperature to identify physical patterns. The monitoring process help out the model focus on the most important data, leading to more accurate predictions. By giving more weight to key particulars that influence battery health and performance, the system reduces uncertainty improves the accuracy of battery testing. The system can also be adjusted for different tasks. By focusing on relevant data at each moment, the monitoring process enhances the model’s ability to track long- term changes in battery life. This leads to more accurate predictions of critical parameters like State of Charge (SOC), State of Health (SOH), and Remaining Useful Life (RUL). The mixture of the listening and GRU models discharge better by offering the advantages of traditional methods, reducing noise, and boosting the system’s power. Experimental results show that this approach surpasses traditional models in accuracy and reliability, supporting the development of high-quality systems. Stable electronic products, especially in the electric vehicle industry.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.