Controlador Instantâneo Adaptativo Baseado em Rede Neural aplicado a um Conversor Boost

Carlúcio Pereira da Silva; Luiz Fernando Marquez Arruda; Diego Santos Greff

doi:10.20906/sbai.v1i1.2773

Carlúcio Pereira da Silva GREEN - Grupo de Energias Renováveis, Universidade Federal de Santa Catarina, SC
Luiz Fernando Marquez Arruda GREEN - Grupo de Energias Renováveis, Universidade Federal de Santa Catarina, SC
Diego Santos Greff GREEN - Grupo de Energias Renováveis, Universidade Federal de Santa Catarina, SC

DOI: https://doi.org/10.20906/sbai.v1i1.2773

Keywords: DC-DC Converter, Neural Controller, Predictive Controller, Artificial Neural Network, Boost Converter

Abstract

The proposal for this work deals with a technique for controlling a Boost-type DC-DC converter, called Instantaneous Adaptative Neural Network Controller (IANNC). The proposed control method uses a Perceptron neural network that seeks to maintain the voltage converter output. Through IANNC it is possible to establish the appropriate working cycle for the Pulse Width Modulation (PWM) control signal. The proposed method was confronted with a typical Proportional Integral (PI) controller aiming to validate the model. The results were obtained using the PSIM simulator, where, in particular, the stability of the converter?s output voltage against an R load was considered.