A review on hybrid wavelet regrouping particle swarm optimization neural networks for characterization of partial discharge acoustic signals

Partial discharges (PD) emit energy in several ways and in the process, electro-magnetic emissions in the form of radio waves, light and heat, audible and ultra-sonic acoustic emissions are produced. These emissions enable the detection, location, measurement and analysis of the PD activity. PD activity is a precursor to failure thus it is construed as fault activity that must be addressed to prevent unplanned power losses. To prevent these unplanned failures that could result in power and revenue losses, an intelligent model that can detect, identify and characterize acoustic signals due to partial discharge activity has been proposed. The model is capable of differentiating abnormal operating conditions from normal ones. This paper highlights some smart techniques which have recently been used to identify the partial discharges on electrical overhead network that will guarantee sustainable and reliable energy savings. Furthermore, the main focus of this review is on a hybrid algorithm combining particle swarm optimization (PSO) with a neural network, referred to as PSO-NN.