Design of Neural Network Based Controller for Switching Regulator in DC-DC Boost Converters

The primary objective of switching regulators is to efficiently convert, regulate, and manage electrical power, guaranteeing stable and effective operation of electronic systems in diverse applications. In this research work a Conventional DC-DC Boost Converter (CBC) and a two-phase Interleaved DC-DC Boost Converter (IBC) were employed in a Switching Regulator. A cascade controller based on Artificial Neural Network (ANN) was implemented on both the CBC and IBC, where the networks were trained using algorithms such as Levenberg Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG). Consequently, the implementation of ANN resulted in reduced time domain parameters such as settling time, rise time, and peak time compared to the Conventional Proportional Integral (PI) Controller.