Power Quality Measurement in Three-Phase Systems using Neural Networks

F.J. Alcántara, P. Salmerón, J. Prieto, and J.R. Vázquez (Spain)


Power Quality Measurement, Harmonics, Symmetrical Components, Artificial Neural Networks.


In this paper, a new measurement procedure based on neural networks for the estimation of harmonic powers and current/voltage symmetrical components is presented. The theory foundation is the Park Vectors representation for a three-phase voltage/current. The measurement sys tem scheme is built with three neural network blocks. The first block is a feedforward neural network that computes the Park vectors and the zero phase sequence components. The second block is an adaptive linear neuron (ADALINE) that estimates the harmonic complex coeffi cients of the current/voltage Park vectors. A third block is another feedforward neural network that obtains symme trical components of current/voltage harmonics and har monic active/reactive powers. Finally, the digital simula tion results of a practical case to check the measurement method performance are presented.

Important Links:

Go Back