Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Informatika dan Teknik Elektro Terapan
Dylan Adriansyah Effendi
Politeknik Negeri Sriwijaya
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Transformer and Support Vector Regression for LiPo Battery Charging Time Prediction Dylan Adriansyah Effendi; Johansyah Al Rasyid
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 3 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i3.10813

Abstract

This study aims to estimate the charging time of Lithium Polymer (LiPo) batteries using a machine learning-based approach. The parameters used in this study include voltage, current, temperature, and State of Charge (SoC), which are obtained through a microcontroller-based monitoring system. Two algorithms, namely Transformer and Support Vector Regression (SVR), are implemented and compared for battery charging time prediction. Data are collected directly during the charging process and processed for model training and testing. The performance of both models is evaluated using regression metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R²). The experimental results show that the SVR model outperforms the Transformer model, achieving an MAE of 14.67 seconds, an RMSE of 20.16 seconds, a MAPE of 11.83%, and an R² value of 0.9991. Meanwhile, the Transformer model achieves an MAE of 22.54 seconds, an RMSE of 29.61 seconds, a MAPE of 16.83%, and an R² value of 0.9981. These results indicate that both models are capable of accurately predicting battery charging time; however, the SVR model provides better overall prediction performance for the experimental dataset used in this study. This research is expected to contribute to the development of more intelligent and accurate battery management systems.
Co-Authors Johansyah Al Rasyid