Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jul 11;14(1):16036.
doi: 10.1038/s41598-024-66997-9.

Enhanced SOC estimation of lithium ion batteries with RealTime data using machine learning algorithms

Obuli Pranav D  1 , Preethem S Babu  1 , Indragandhi V  2 , Ashok B  3 , Vedhanayaki S  1 , Kavitha C  4
Affiliations

Enhanced SOC estimation of lithium ion batteries with RealTime data using machine learning algorithms

Obuli Pranav D et al. Sci Rep. .

Abstract

Accurately estimating Battery State of Charge (SOC) is essential for safe and optimal electric vehicle operation. This paper presents a comparative assessment of multiple machine learning regression algorithms including Support Vector Machine, Neural Network, Ensemble Method, and Gaussian Process Regression for modelling the complex relationship between real-time driving data and battery SOC. The models are trained and tested on extensive field data collected from diverse drivers across varying conditions. Statistical performance metrics evaluate the SOC prediction accuracy on the test set. Gaussian process regression demonstrates superior precision surpassing the other techniques with the lowest errors. Case studies analyse model competence in mimicking actual battery charge/discharge characteristics responding to changing drivers, temperatures, and drive cycles. The research provides a reliable data-driven framework leveraging advanced analytics for precise real-time SOC monitoring to enhance battery management.

Keywords: Comparative analysis; Electric vehicle; Gaussian process regression; Lithium-ion battery; Machine learning; State of charge.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Architecture of BMS.
Figure 2
Figure 2
General architecture of SVM.
Figure 3
Figure 3
Neural network structure.
Figure 4
Figure 4
Gaussian process regression model.
Figure 5
Figure 5
Flowchart of the proposed SOC estimation methodology.
Figure 6
Figure 6
Feature scaling of input parameters.
Figure 7
Figure 7
Input parameters. (a) Humidity. (b) Pack voltage. (c) Pack current. (d) Pack cell temperature. (e) Motor temperature. (f) FET temperature. (g) Ambient temperature.
Figure 8
Figure 8
Schematic diagram of the proposed experimental setup.
Figure 9
Figure 9
Comparison of performance indices of different kernels of tree.
Figure 10
Figure 10
Comparison of performance indices of different kernels of linear regression.
Figure 11
Figure 11
Comparison of performance indices of different kernels of SVM.
Figure 12
Figure 12
Comparison of performance indices of different kernels of GPR.
Figure 13
Figure 13
Comparison of performance indices of different layers of neural network.
Figure 14
Figure 14
Comparison of performance indices of different kernels of tree during testing.
Figure 15
Figure 15
Comparison of performance indices of different kernels of linear regression during testing.
Figure 16
Figure 16
Comparison of performance indices of different kernels of SVM testing.
Figure 17
Figure 17
Comparison of performance indices of different kernels of GPR during testing.
Figure 18
Figure 18
Comparison of performance indices of different layers of neural network during testing.
Figure 19
Figure 19
Comparison of performance indices of different ML algorithms.
See this image and copyright information in PMC

References

    1. Xie J, Wu C, Le ADT, Abeywardana IU, Paul B, Hussein A. Battery electric vehicles for modern power systems—A comprehensive review on technological evolutions and integration paradigms. Renew. Energy. 2022;183:459–489.
    1. Liu Z, Zhang Q, Huisingh D, Wang Y. Carbon emissions of electric vehicles based on electricity generation mix: A regional assessment of China. Renew. Energy. 2021;163:1217–1233.
    1. Wang Z, Zhang X, Sun Y, Liu W. A comprehensive overview of hybrid electric vehicles. Appl. Energy. 2020;269:115054.
    1. Zhang X, Sahinoglu Z, Wada T, Hara S, Sakurai J. Recent progress on lithium ion battery performance degradation analysis and state estimation technologies: A review. J. Energy Storage. 2020;28:101230.
    1. Chu S, Majumdar A, Pan J, Chiang YM, Wu Z. Why are commercial lithium ion batteries unstable? An overview of stability issues, consequences, and remedies. J. Power Sources. 2021;493:229562.

LinkOut - more resources