The automotive industry is currently investing heavily to pivot from conventional internal combustion engines to electric powertrains. The battery pack still makes up a large portion of each electric vehicle’s cost, making management and control of the battery crucial for this transition. With improved state of charge estimation an increased amount of energy can safely be extracted from each battery pack, therefore increasing the range, or allowing smaller packs to be utilized. For this study, traditional equivalent circuit models and machine learning methods are compared for battery state of charge estimation across a temperature range of -10°C to 25°C. The machine learning models explored include support vector regression, feedforward neural networks and recurrent neural networks. The dataset used was derived from various tests and drive cycles performed on a Panasonic 18650PF NMC Cell in a temperature chamber. Based upon the results, it is evident that equivalent circuit models perform very well at higher temperatures, but struggle to capture the highly nonlinear characteristics of batteries at lower temperatures. On the other hand, when properly trained and parameterized, machine learning models can be much more effective at capturing the battery’s characteristics at low temperatures while maintaining their computational requirements low.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Comparing Traditional and Machine Learning Models for Battery SOC Calculation


    Beteiligte:
    Barrios, Fernando Andre (Autor:in) / Di Donato, James (Autor:in) / Vidal, Carlos (Autor:in) / Chemmanoor, Nithin (Autor:in) / Ahmed, Ryan (Autor:in) / Emadi, Ali (Autor:in) / Habibi, Saeid (Autor:in)


    Erscheinungsdatum :

    15.06.2022


    Format / Umfang :

    442895 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Comparing discrete choice and machine learning models in predicting destination choice

    Ilona Rahnasto / Martijn Hollestelle | DOAJ | 2024

    Freier Zugriff

    Comparing discrete choice and machine learning models in predicting destination choice

    Rahnasto, Ilona / Hollestelle, Martijn | Springer Verlag | 2024

    Freier Zugriff

    Public transport priority schemes: comparing microsimulation with traditional TRANSYT and LINSIG models

    Ahuja, S. / van Vuren, T. / MacDonald, M. et al. | British Library Conference Proceedings | 2003



    Flexible oneanchor retaining building models calculation results comparing with experimental data

    Anёdriy Grishin / Olaksandr Siplivets | DOAJ | 2019

    Freier Zugriff