Open Access

ARTICLE

Deep Learning Approaches for Battery Capacity and State of Charge Estimation with the NASA B0005 Dataset

Zeyang Zhou^1,*, Zachary James Ryan¹, Utkarsh Sharma², Tran Tien Anh³, Shashi Mehrotra⁴, Angelo Greco⁵, Jason West⁶, Mukesh Prasad^1,*

1 School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
2 School of Data Science and Engineering, Indian Institute of Science Education and Research, Bhopal, 462066, India
3 Research Institute of Marine Systems Engineering, Seoul National University, Seoul, 08826, Republic of Korea
4 Department of Computer Science and Engineering, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Delhi NCR Campus, Ghaziabad, 201204, India
5 Battery System Modelling Department, CLARIOS VARTA Hannover GmbH, Hanover, 30419, Germany
6 Science and Innovation Group, Bureau of Meteorology, Brisbane, 4000, Australia

* Corresponding Authors: Zeyang Zhou. Email: ; Mukesh Prasad. Email:

Computers, Materials & Continua 2025, 83(3), 4795-4813. https://doi.org/10.32604/cmc.2025.060291

Received 29 October 2024; Accepted 07 March 2025; Issue published 19 May 2025

Abstract

Accurate capacity and State of Charge (SOC) estimation are crucial for ensuring the safety and longevity of lithium-ion batteries in electric vehicles. This study examines ten machine learning architectures, Including Deep Belief Network (DBN), Bidirectional Recurrent Neural Network (BiDirRNN), Gated Recurrent Unit (GRU), and others using the NASA B0005 dataset of 591,458 instances. Results indicate that DBN excels in capacity estimation, achieving orders-of-magnitude lower error values and explaining over 99.97% of the predicted variable’s variance. When computational efficiency is paramount, the Deep Neural Network (DNN) offers a strong alternative, delivering near-competitive accuracy with significantly reduced prediction times. The GRU achieves the best overall performance for SOC estimation, attaining an of 0.9999, while the BiDirRNN provides a marginally lower error at a slightly higher computational speed. In contrast, Convolutional Neural Networks (CNN) and Radial Basis Function Networks (RBFN) exhibit relatively high error rates, making them less viable for real-world battery management. Analyses of error distributions reveal that the top-performing models cluster most predictions within tight bounds, limiting the risk of overcharging or deep discharging. These findings highlight the trade-off between accuracy and computational overhead, offering valuable guidance for battery management system (BMS) designers seeking optimal performance under constrained resources. Future work may further explore advanced data augmentation and domain adaptation techniques to enhance these models’ robustness in diverse operating conditions.

---

Keywords

---