Power factor correction using neural network as controller for synchronous motor

Abstract

This study presents a novel technique based on artificial neural networks (ANNs ) to correct the line power factor with variable loads by controlling the excitation current of a synchronous motor. The network is trained using voltage, current, and excitation current input-output pairs, which were collected using a test rig specifically designed for data collection. The desired outputs for training the neural network were assigned based on the experimental setup and requirements. The neural network was trained using the Bayesian regularization learning algorithm, which minimizes the error between the actual and desired output. The training process was conducted using the NN fitting tool in MATLAB, a widely-used software for developing and implementing neural networks.