The SFRA (Sweep Frequency Response Analysis) is a measurement technique that allows to evaluate the integrity of power transformers. The goal of SFRA is to determine the transfer function (TF) of each winding of the transformer in a certain frequency range. The technique has recently been successfully used for the characterization of rotating machines, such as induction motors, widely found in industry. Promising results have also recently been demonstrated in the use of the technique for the identification and characterization of household appliances. This article illustrates the possibility of using TFs, obtained by applying the SFRA technique, as an input to Deep Learning algorithms, in order to create systems capable of making decisions based on these results. Furthermore, the work reports the results obtained by a Deep Learning system applied to the recognition of household appliances through the use of this analysis.
Deep Learning Applied to SFRA Results: A Preliminary Study
Bucci G.;Ciancetta F.;Fiorucci E.;Mari S.;Fioravanti A.
2021-01-01
Abstract
The SFRA (Sweep Frequency Response Analysis) is a measurement technique that allows to evaluate the integrity of power transformers. The goal of SFRA is to determine the transfer function (TF) of each winding of the transformer in a certain frequency range. The technique has recently been successfully used for the characterization of rotating machines, such as induction motors, widely found in industry. Promising results have also recently been demonstrated in the use of the technique for the identification and characterization of household appliances. This article illustrates the possibility of using TFs, obtained by applying the SFRA technique, as an input to Deep Learning algorithms, in order to create systems capable of making decisions based on these results. Furthermore, the work reports the results obtained by a Deep Learning system applied to the recognition of household appliances through the use of this analysis.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.