Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{185105,
        author = {G. Amba Prasad Rao and Ganesh Madhusudhanan},
        title = {Lumped thermal analysis of traction motors for effective thermal management with Machine Learning approach},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {575-588},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185105},
        abstract = {The market share of electric vehicles is increasing due to the persistent issues of high harmful emissions due to the combustion of fossil liquid fuels for use in conventional prime movers. Electric motors and batteries are important components of a typical neat electric vehicle. Electric motors, especially Permanent Magnet Motors, are crucial in electric vehicles due to their superior torque-to-inertia ratio, power density, and efficiency. This study explores thermal analysis techniques for Permanent Magnet Synchronous Motors to determine temperature variations and identify areas requiring effective thermal management. Using a lumped thermal network and linear equations in MATLAB, the analysis captures both axial and radial heat transfer in the motor. Temperatures obtained from the lumped model for the winding, rotor, stator, permanent magnet, and casing are 123.76°C, 114.87°C, 120.91°C, 114.87°C, and 87.49°C, respectively. The obtained temperatures align well with Computational Fluid Dynamics (CFD) results and experimental data, highlighting the highest winding temperature during continuous operation at 4500 rpm. The thermal network aids in material selection, insulation, cooling methods, and component design. Additionally, various machine learning algorithms, including Linear Regression, Decision Tree, Random Forest, and Support Vector Machines, predict temperature distributions across different motor geometries. The Linear Regression model yielded the highest R-squared value, closely aligning with the lumped model's predictions for the winding, rotor, casing, permanent magnet, and stator temperatures.},
        keywords = {Electric Vehicle; Thermal network; Lumped Parameter; Permanent Magnet Synchronous Motor; Machine Learning.},
        month = {October},
        }