Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development, ICSETPSD 2023, 17th-18th November 2023, Coimbatore, Tamilnadu, India

Research Article

Artificial Neural Network based Bidirectional Converter Control for Electric Vehicle Charging

Download51 downloads
  • @INPROCEEDINGS{10.4108/eai.17-11-2023.2342838,
        author={Latha  Ramasamy and Navaneethan  Soundirarajan and Varsha  R J},
        title={Artificial Neural Network based Bidirectional Converter Control for Electric Vehicle Charging},
        proceedings={Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development, ICSETPSD 2023, 17th-18th November 2023, Coimbatore, Tamilnadu, India},
        publisher={EAI},
        proceedings_a={ICSETPSD},
        year={2024},
        month={1},
        keywords={artificial neural network (ann) electric vehicle (ev) grid to vehicle (g2v) vehicle to grid(v2g) pi controller dc-dc converter},
        doi={10.4108/eai.17-11-2023.2342838}
    }
    
  • Latha Ramasamy
    Navaneethan Soundirarajan
    Varsha R J
    Year: 2024
    Artificial Neural Network based Bidirectional Converter Control for Electric Vehicle Charging
    ICSETPSD
    EAI
    DOI: 10.4108/eai.17-11-2023.2342838
Latha Ramasamy1,*, Navaneethan Soundirarajan1, Varsha R J1
  • 1: PSG College of Technology
*Contact email: rla.ee@psgtech.ac.in

Abstract

Extensive research has been ongoing in the field of Electric Vehicle (EV) chargers. This article addresses transfer of electric power from the grid to EV and from an EV to grid, a configuration of a single-phase charger system consists of bidirectional AC-DC converter integrated with bidirectional DC-DC converter. An artificial neural network (ANN) controller is employed for controlling the charging current and voltage. ANN model produces the required duty cycle to feed the maximum power under both Grid to Vehicle(G2V) mode and Vehicle to Grid (V2G) mode. The ANN is trained for the measured battery voltages and battery current to estimate the bidirectional converter’s duty cycle. The implementation of the neural network is presented in this study, and simulation results are accomplished using Matlab/Simulink. The simulation findings support the effectiveness of the suggested control technique as well as its practicality. A comparative study is made to show the enhanced performance of the proposed controller than the conventional Proportional-Integral (PI) controller