ItemArticle

An improved LSTM based thermal prediction and control algorithm for battery management system in hybrid electric vehicles

Title
An improved LSTM based thermal prediction and control algorithm for battery management system in hybrid electric vehicles
Creator
Prabu, P.; Ganeshkumar, P.; Krishnan, Prabhakar; Dhanasekaran, S.; Jiang, Weiwei; Logeshwaran, J.
Description
Effective thermal management of lithium-ion batteries is critical for ensuring safety, longevity, and optimal performance in Hybrid Electric Vehicles (HEV). This research proposes an improved Long Short-Term Memory (LSTM) based thermal prediction and control algorithm for Battery Management Systems (BMS) to enhance temperature regulation accuracy and computational efficiency. The proposed model integrates an optimized LSTM network with attention mechanisms to capture long-term dependencies in thermal dynamics while reducing prediction latency. A multi-physics-based thermal model is employed to generate high-fidelity training data, accounting for electrochemical-thermal coupling effects. The algorithm incorporates adaptive learning rates and dropout regularization to mitigate overfitting and improve generalization under varying load conditions. A model predictive control framework is designed to leverage real-time LSTM predictions for proactive cooling strategy optimization, minimizing energy consumption while maintaining safe operating temperatures. The proposed model reached RMSE of Heat generation rate of 1.08 W/mA3, Entropy coefficient Error of 0.024 mV/K, Thermal conductivity of 0.626 w/mK, Latency of 28 ms, Cooling energy Consumption of 314.61 kWh and Temperature deviation of 3.34 AC. The proposed solution offers a computationally efficient, scalable framework for next-generation BMS, enhancing battery reliability and vehicle efficiency. 2025 Elsevier Ltd
Source
International Communications in Heat and Mass Transfer;Volume;169;Issue;;Article No.;109930;
Date
01-01-2025
Publisher
Elsevier Ltd
Subject
Adaptive learning; Battery; Electric vehicles; LSTM; Optimization; Reliability; Thermal management
Coverage
Prabu P., Department of Information Systems, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, 11442, Saudi Arabia; Ganeshkumar P., Department of Computer Science, College of Computer and Information Sciences, Al Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, 11432, Saudi Arabia; Krishnan P., Center for Cyber Security and Networks, Amrita Vishwa Vidyapeetham, Amritapuri Campus, Kollam, India; Dhanasekaran S., Department of Electronics and Communication Engineering, Sri Eshwar College of Engineering, Tamil Nadu, Coimbatore, 641202, India; Jiang W., School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, 100876, China; Logeshwaran J., Department of Computer Science, Christ University, Karnataka, Bengaluru, 560029, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 7351933; CODEN: IHMTD
Format
online
Language
English
Type
Article

Citation

Prabu, P.; Ganeshkumar, P.; Krishnan, Prabhakar; Dhanasekaran, S.; Jiang, Weiwei; Logeshwaran, J., “An improved LSTM based thermal prediction and control algorithm for battery management system in hybrid electric vehicles,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 19, 2026, https://archives.christuniversity.in/items/show/22278.

Output Formats