Radial Basis Function Application in Noise Reduction of Power Transformers

The noise interferes with the measuring equipment installed in transformer stations and results in technical challenges for utility engineers. Sensors are mounted on transformers, to measure partial discharge (PD) signals, but the noise deforms the PD signals. In this paper, the noise removal from PD signal of power transformers is performed by a radial basis function (RBF) neural network. The CST software is used to simulate a transformer, PD and noise. Also, a laboratory model is used to generate the PD and noise signals. The simulation and measurement results are presented and discussed. It is shown that the proposed method is a good technique for noise removal from PD signals.