FPGA Implementation of Multilayer Perceptron for Real-Time Detection of Power Quality Disturbances for Electric Vehicle Charger
Information
Resumen
Power quality is one of the most critical fields in the energy sector. The connection of electric vehicles to the electrical grid can cause a degradation of energy quality when charging or discharging the battery. Identifying sudden voltage drops, surges, and network interruptions is essential to avoid network failure. A multiple fault classification/monitoring system has been developed based on artificial neural networks and implemented in an FPGA. The system’s performance has been evaluated using a set of data obtained from MATLAB/Simulink 2024. Different dataset combinations are implemented, trained, validated, and tested on three multilayer perceptron (MLP) models of various configurations. The analysis shows that the MLP designed with 12-bit fixed-point data precision is the most efficient MLP implementation in classification accuracy, compared to 8, 12, 20, and 24-bit fixed-point data. The system achieved 99.95% classification accuracy across various fault conditions, demonstrating its capability for real-time deployment.
Datos de publicación
Cita esta publicación
Comprueba el estilo que requiere tu institución o revista.
Fuentes y trazabilidad
Se conserva la procedencia de los datos y se da prioridad a la revista cuando existe información editorial.
Licencias declaradas por las fuentes
https://creativecommons.org/licenses/by/4.0/