This paper presents a new application of Power Line Communication (PLC) technologies aimed at detecting abnormal operating temperatures in underground Medium Voltage (MV) cables. The core of this method is the analysis of the signal transmitted from one end of the line to the other. Since the electrical behavior of the cable varies with temperature, the characteristics of the received signal are modified by the presence of an overtemperature. In particular, changes in cable resistance, that affect the attenuation constant of the line, can be modelled using the thermal coefficient of copper. Furthermore, variations in other components, such as the cable capacitance, determine different propagation speeds thus modifying the phase of the transmitted signal with respect to the nominal conditions. Therefore, the main objective of this paper is to propose a classification method based on machine learning techniques capable of recognizing the presence and the extension of overheated cable sections. This monitoring method uses a feed-forward multilayer neural network with multi-valued neurons and guarantees a classification rate of approximately 90%. The classification performance has been compared to that obtained through a Support Vector Machine.

A New Application of Power Line Communication Technologies: Prognosis of Failure in Underground Cables / Bindi, Marco; Grasso, Francesco; Luchetta, Antonio; Piccirilli, Maria Cristina. - ELETTRONICO. - (2022), pp. 1-6. (Intervento presentato al convegno International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022) [10.1109/ICECCME55909.2022.9988118].

A New Application of Power Line Communication Technologies: Prognosis of Failure in Underground Cables

Bindi, Marco;Grasso, Francesco;Luchetta, Antonio;Piccirilli, Maria Cristina
2022

Abstract

This paper presents a new application of Power Line Communication (PLC) technologies aimed at detecting abnormal operating temperatures in underground Medium Voltage (MV) cables. The core of this method is the analysis of the signal transmitted from one end of the line to the other. Since the electrical behavior of the cable varies with temperature, the characteristics of the received signal are modified by the presence of an overtemperature. In particular, changes in cable resistance, that affect the attenuation constant of the line, can be modelled using the thermal coefficient of copper. Furthermore, variations in other components, such as the cable capacitance, determine different propagation speeds thus modifying the phase of the transmitted signal with respect to the nominal conditions. Therefore, the main objective of this paper is to propose a classification method based on machine learning techniques capable of recognizing the presence and the extension of overheated cable sections. This monitoring method uses a feed-forward multilayer neural network with multi-valued neurons and guarantees a classification rate of approximately 90%. The classification performance has been compared to that obtained through a Support Vector Machine.
2022
International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022
International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022
Bindi, Marco; Grasso, Francesco; Luchetta, Antonio; Piccirilli, Maria Cristina
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 identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1300920
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact