Artificial Neural Network for monitoring the asymmetric half bridge DC–DC converter

This paper investigates the effectiveness of an Artificial Neural Network (ANN) while training as an asymmetric half bridge DC–DC converter circuit used in sensitive applications. The ANN is trained to form a mapping between the inputs and outputs of converter circuit using back propagation algorithm. After training the Artificial Neural Network monitor the asymmetric half bridge converter in order to detect the performance deviations. The ultimate objective of the designed Neural network is to perform like the trained converter circuit when the circuit is changed from its original conditions. Such information can be valuable for many sensitive power electronic applications. Typical simulation results are provided that indicates the effectiveness of the proposed scheme.