This paper presents an analysis method capable of monitoring the thermal behavior of medium voltage lines. The main theoretical concept on which this method is based is the analysis of the frequency response. Line admittance measurements are used to identify the operating temperature of underground cables. Several factors affect the conductor temperature, such as overload currents, variations in environmental conditions, the health status of the insulating materials. All these situations increase the cable temperature and, consequently, the resistance of the conductor. When the electrical parameters of the cable change, the frequency response also changes and, in this work, a monitoring system based on a machine learning technique is used to classify its magnitude and phase. The monitoring method here proposed uses a feed-forward multilayer neural network with multivalued neurons in order to classify the working temperature of the cable allowing the prevention of catastrophic failures.

Assessment of the health status of Medium Voltage lines through a complex neural network / Bindi M.; Luchetta A.; Scarpino P.A.; Piccirilli M.C.; Grasso F.; Sturchio A.. - ELETTRONICO. - (2021), pp. 1-6. ((Intervento presentato al convegno 2021 AEIT International Annual Conference (AEIT) [10.23919/AEIT53387.2021.9627068].

Assessment of the health status of Medium Voltage lines through a complex neural network

Bindi M.;Luchetta A.;Scarpino P. A.;Piccirilli M. C.;Grasso F.;
2021

Abstract

This paper presents an analysis method capable of monitoring the thermal behavior of medium voltage lines. The main theoretical concept on which this method is based is the analysis of the frequency response. Line admittance measurements are used to identify the operating temperature of underground cables. Several factors affect the conductor temperature, such as overload currents, variations in environmental conditions, the health status of the insulating materials. All these situations increase the cable temperature and, consequently, the resistance of the conductor. When the electrical parameters of the cable change, the frequency response also changes and, in this work, a monitoring system based on a machine learning technique is used to classify its magnitude and phase. The monitoring method here proposed uses a feed-forward multilayer neural network with multivalued neurons in order to classify the working temperature of the cable allowing the prevention of catastrophic failures.
2021 AEIT International Annual Conference (AEIT)
2021 AEIT International Annual Conference (AEIT)
Bindi M.; Luchetta A.; Scarpino P.A.; Piccirilli M.C.; Grasso F.; Sturchio A.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2158/1282904
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact