Hybrid AI Models for Predictive Electric Vehicle Battery Capacity Estimation and Fault Tolerance Management

International Journal of Electrical and Electronics Engineering

© 2025 by SSRG - IJEEE Journal

Volume 12 Issue 4

Year of Publication : 2025

Authors : Bapu Dada Kokare, Sanjay A. Deokar, Mangesh M. Kale

10.14445/23488379/IJEEE-V12I4P123

How to Cite?

Bapu Dada Kokare, Sanjay A. Deokar, Mangesh M. Kale, "Hybrid AI Models for Predictive Electric Vehicle Battery Capacity Estimation and Fault Tolerance Management," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 4, pp. 289-297, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I4P123

Abstract:

The adoption of electric powertrains is rapidly increasing due to their high efficiency and minimal environmental impact. However, ensuring reliable fault detection and accurate battery capacity estimation remains a significant challenge in Electric Vehicles (EVs). This study proposes a hybrid Artificial Intelligence (AI) model that integrates Long Short-Term Memory (LSTM) networks, Feedforward Neural Networks (FNN), and Random Forest (RF) algorithms to estimate EV battery capacity under load conditions. The hybrid model not only predicts the remaining battery capacity with high accuracy but also supports decision-making processes by determining whether the battery requires replacement or a simple recharge. This dual functionality enhances operational efficiency and reduces maintenance costs. Experimental evaluations reveal that the hybrid approach significantly outperforms standalone LSTM, FNN, and RF models in terms of accuracy and reliability. By addressing key challenges in battery performance prediction, this model provides a robust solution for smarter predictive maintenance, improved energy management, and enhanced lifecycle optimization of electric vehicle batteries. This study paves the way for applying advanced machine learning techniques in EV system management, contributing to sustainable transportation and energy solutions.

Keywords:

Electric Vehicle Batteries, Hybrid AI Models, Long Short-Term Memory, Feedforward Neural Networks, Random Forest, Battery Capacity Estimation.

References:

[1] Shengyu Tao et al., “Collaborative and Privacy-Preserving Retired Battery Sorting for Profitable Direct Recycling via Federated Machine Learning,” Nature Communications, vol. 14, no.1, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Wei Li, Liang Gao, and Akhil Garg, “A Framework Based on Big Data for Intelligent Monitoring of Battery Packs,” IOP Conference Series: Earth and Environmental Science, vol. 463, no. 1, pp. 1-6, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Junzhe Shi et al., “Electric Vehicle Battery Remaining Charging Time Estimation Considering Charging Accuracy and Charging Profile Prediction,” Journal of Energy Storage, vol. 49, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Guangxing Bai, and Pingfeng Wang, “A Self-Cognizant Dynamic System Approach for Health Management: Lithium-Ion Battery Case Study,” ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Buffalo, New York, USA, pp. 1-12, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Venkatesan Chandran et al., “State of Charge Estimation of Lithium-Ion Battery for Electric Vehicles using Machine Learning Algorithms,” World Electric Vehicle Journal, vol. 12, no. 1, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jingyuan Zhao et al., “Machine Learning for Predicting Battery Capacity for Electric Vehicles,” eTransportation, vol. 15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Jinpeng Tian et al., “State-of-Charge Estimation of Lifepo4 Batteries in Electric Vehicles: A Deep-Learning Enabled Approach,” Applied Energy, vol. 291, 2021.
[CrossRef] [Google Scholar] [Publisher Link] 
[8] Robert Marlin et al., “Electric Vehicle Next Charge Location Prediction,” IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 10, pp. 14128-14139, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Dawei Zhang et al., “Deep Learning in the State of Charge Estimation for Li-Ion Batteries of Electric Vehicles: A Review,” Machines, vol. 10, no. 10, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Yonggeon Lee et al., “Extending Ev Battery Lifetime: Digital Phenotyping Approach for Departure Time Prediction,” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 8, no. 4, pp. 1-30, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Hui Song et al., “Ensemble Classification Model for Ev Identification from Smart Meter Recordings,” IEEE Transactions on Industrial Informatics, vol. 19, no. 3, pp. 3274-3283, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Sonja Rosenberg et al., “Combining Dynamic Material Flow Analysis and Life Cycle Assessment to Evaluate Environmental Benefits of Recycling- A Case Study for Direct and Hydrometallurgical Closed-Loop Recycling of Electric Vehicle Battery Systems,” Resources, Conservation and Recycling, vol. 198, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Brian Bole, Chetan S. Kulkarni, and Matthew Daigle, “Adaptation of an Electrochemistry-Based Liion Battery Model to Account for Deterioration Observed Under Randomized Use,” Annual Conference of the PHM Society, vol. 6, no. 1, pp. 1-9, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Shahid A. Hasib et al., “A Comprehensive Review of Available Battery Datasets, Rul Prediction Approaches, and Advanced Battery Management,” IEEE Access, vol. 9, pp. 86166-86193, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Shaheer Ansari et al., “Particle Swarm Optimized Data-Driven Model for Remaining Useful Life Prediction of Lithium-Ion Batteries by Systematic Sampling,” Journal of Energy Storage, vol. 56, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Nassr Al-Dahabreh et al., “A Data-Driven Framework for Improving Public EV Charging Infrastructure: Modeling and Forecasting,” IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 6, pp. 5935-5948, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Rachel Lee, Saadallah Yazbeck, and Solomon Brown, “Validation and Application of Agent-Based Electric Vehicle Charging Model,” Energy Reports, vol. 6, pp. 53-62, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Fabian Rücker et al., “Battery Electric Vehicles in Commercial Fleets: Use Profiles, Battery Aging, and Open-Access Data,” Journal of Energy Storage, vol. 86, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Basavaraju Bennehalli et al., “Machine Learning Approach to Battery Management and Balancing Techniques for Enhancing Electric Vehicle Battery Performance,” Journal of Electrical Systems, vol. 20, no. 2s, pp. 885-892, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Haowei He et al., “EVBattery: A Large-Scale Electric Vehicle Dataset for Battery Health and Capacity Estimation,” arXiv, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Matthias Steinstraeter, Johannes Buberger, and Dimitar Trifonov, “Battery and Heating Data in Real Driving Cycles,” IEEE Dataport, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Weiqi Hua et al., “Integrating Artificial Intelligence into Electric Vehicle Energy Systems: A Survey,” Artificial Intelligence for Knowledge Management, Energy and Sustainability, 10th IFIP International Workshop on Artificial Intelligence for Knowledge Management, Krakow, Poland, pp. 92-115, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Linfang Yan et al., “A Cooperative Charging Control Strategy for Electric Vehicles Based on Multiagent Deep Reinforcement Learning,” IEEE Transactions on Industrial Informatics, vol. 18, no. 12, pp. 8765-8775, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Ronald E. Kruse, and Thomas A. Huls, “Development of the Federal Urban Driving Schedule,” SAE Technical Paper, 1973.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Thomas Legg, and Douglas Nelson, “Evaluating Simulation Driver Model Performance Using Dynamometer Test Criteria,” SAE Technical Paper, 2022.
[CrossRef] [Google Scholar] [Publisher Link]