Using experimental data from a hybrid energy storage system (HESS) composed of two 12V batteries in parallel 60Ah Lead acid (LA) and 8Ah Lithium Iron Phosphate (LFP)–a machine learning approach known as feedforward backpropagation artificial neural network (BPNN) was developed to estimate the state-of-charge (SOC) of both batteries using only one neural network structure. In order to minimize the SOC estimation error the BPNN was trained using a set of five different homologation automotive drive cycles and tested on a sixth drive cycle known as worldwide harmonized light vehicles test cycle (WLTC) to compute the estimation accuracy. A rootmean- squared error (RMSE) of 0.33% and 0.84% is obtained over the test cycle for the LFP and the LA batteries, respectively. The results were then compared to the estimation obtained from a commercially available battery management system (BMS) showing better performance for the proposed approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Hybrid Energy Storage System State-Of-Charge Estimation Using Artificial Neural Network For Micro-Hybrid Applications


    Contributors:


    Publication date :

    2018-06-01


    Size :

    1885117 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Hybrid State Estimation Combining Artificial Neural Network and Physical Model

    Sieberg, Philipp Maximilian / Blume, Sebastian / Harnack, Nele et al. | IEEE | 2019


    Artificial Neural Network Based Energy Storage System Modeling for Hybrid Electric Vehicles

    Wipke, Keith / Mahajan, Roop. L. / Bhatikar, Sanjay. R. et al. | SAE Technical Papers | 2000


    Battery state of charge estimation using an Artificial Neural Network

    Ismail, Mahmoud / Dlyma, Rioch / Elrakaybi, Ahmed et al. | IEEE | 2017


    Artificial neural network based energy storage system modeling for hybrid electric vehicles

    Bhatikar,S.R. / Mahajan,R.L. / Wipke,K. et al. | Automotive engineering | 2000


    Hybrid State Estimation–A Contribution Towards Reliability Enhancement of Artificial Neural Network Estimators

    Sieberg, Philipp M. / Blume, Sebastian / Reicherts, Sebastian et al. | IEEE | 2022