Resumen

NAINIKA, C.; BALAMURUGAN, P.; FEBIN DAYA, J. L.  y  ANANTHA KRISHNAN, V.. Real driving cycle based SoC and battery temperature prediction for electric vehicle using AI models. J. appl. res. technol [online]. 2024, vol.22, n.3, pp.351-361.  Epub 07-Oct-2025. ISSN 2448-6736.  https://doi.org/10.22201/icat.24486736e.2024.22.3.2453.

The increase in electric vehicles has surpassed expectations leading to the eventual replacement of traditional IC (internal combustion) engine vehicles. However, to achieve this, it is crucial to research and develop more efficient and reliable electric batteries to create a sustainable transportation system. The performance of the battery directly impacts the power and range of the vehicle making battery management research imperative. Accurate estimation of battery state of charge (SoC) and temperature is vital for the overall performance, drivability and safety of the vehicle. This paper proposes a comprehensive approach to create an AI-based model to estimate the battery SoC and temperature that matches the performance of conventional vehicles. Various regression models are used as prediction models and the results are presented. These insights offer valuable understandings of battery thermal behavior, aiding in the design of an effective battery management system.

Palabras llave : Electric vehicle; battery; artificial intelligence; SoC estimation; Temperature.

        · texto en Inglés     · Inglés ( pdf )