ANN-GA-based optimization of a hybrid battery thermal regulation system with helical liquid cooling, PCM, and copper foam
Abstract
Effective thermal management is essential for ensuring the safety, performance, and longevity of Lithium-ion batteries (LIBs). In this study, an optimized hybrid Battery Thermal Regulation System (BTRS) is proposed, integrating helical liquid cooling mini-channels and phase change material (PCM) embedded in a copper foam matrix (CPCM) to enhance heat dissipation. To efficiently explore the complex design space, a coupled framework integrating numerical simulations, a Genetic Algorithm (GA), and Artificial Neural Networks (ANN) was developed. The approach successfully identified an ideal configuration (OCD1) characterized by a 10 mm PCM thickness, a 0.08 m/s inlet velocity, and a 65∘ helical angle. Under a severe 3C discharge condition, this optimal design achieved a maximum temperature reduction of 21.27 K, representing an 82.25% improvement over a standalone cell. Furthermore, the optimized hybrid system demonstrated superior cooling efficacy compared to individual strategies, outperforming case A (liquid cooling) by 33.67%, case B (pure PCM) by 69.35%, and case C (CPCM) by 45%. The developed ANN model exhibited high predictive accuracy, with R2 values exceeding 0.99 for both thermal responses. These findings provide a high fidelity and scalable framework for advanced thermal management of next-generation electric vehicle battery systems.
Related
- Experimental evaluation of the thermal performance of a parallel microchannel cooling system for thermal management of multicore processors under low computational loads
- Multi-objective optimization of a hybrid photovoltaic–thermal energy system under load demand uncertainties using Bat algorithm
- Optimization of a thermal shaker-aided quaking-induced conversion platform for the rapid detection of prion seeding activity in human samples
- Predictive multi-energy management and optimization of renewable-integrated smart buildings with coupled electrical–thermal loads and hybrid energy storage
- Radiation-Induced Xerostomia in Patients With Head and Neck Cancer Treated With Comprehensive Salivary Gland-Sparing Helical Tomotherapy Technique Based on a Back Propagation Artificial Neural Network
BibTeX
@article{mahjoub2026anngabased,
title = {{ANN-GA-based optimization of a hybrid battery thermal regulation system with helical liquid cooling, PCM, and copper foam}},
author = {Sonia Naghizadeh Mahjoub and Mohammad Vajdi and Kourosh Vaferi and Farhad Sadegh Moghanlou and Ebrahim Abdi Aghdam},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-75647-1},
url = {https://www.nature.com/articles/s41598-026-75647-1},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - ANN-GA-based optimization of a hybrid battery thermal regulation system with helical liquid cooling, PCM, and copper foam
AU - Sonia Naghizadeh Mahjoub
AU - Mohammad Vajdi
AU - Kourosh Vaferi
AU - Farhad Sadegh Moghanlou
AU - Ebrahim Abdi Aghdam
PY - 2026
DA - 2026/10/14
JO - Scientific Reports
DO - 10.1038/s41598-026-75647-1
UR - https://www.nature.com/articles/s41598-026-75647-1
AB - Effective thermal management is essential for ensuring the safety, performance, and longevity of Lithium-ion batteries (LIBs). In this study, an optimized hybrid Battery Thermal Regulation System (BTRS) is proposed, integrating helical liquid cooling mini-channels and phase change material (PCM) embedded in a copper foam matrix (CPCM) to enhance heat dissipation. To efficiently explore the complex design space, a coupled framework integrating numerical simulations, a Genetic Algorithm (GA), and Artificial Neural Networks (ANN) was developed. The approach successfully identified an ideal configuration (OCD1) characterized by a 10 mm PCM thickness, a 0.08 m/s inlet velocity, and a 65^∘ helical angle. Under a severe 3C discharge condition, this optimal design achieved a maximum temperature reduction of 21.27 K, representing an 82.25% improvement over a standalone cell. Furthermore, the optimized hybrid system demonstrated superior cooling efficacy compared to individual strategies, outperforming case A (liquid cooling) by 33.67%, case B (pure PCM) by 69.35%, and case C (CPCM) by 45%. The developed ANN model exhibited high predictive accuracy, with R2 values exceeding 0.99 for both thermal responses. These findings provide a high fidelity and scalable framework for advanced thermal management of next-generation electric vehicle battery systems.
SN - 2045-2322
ER -