Thermal monitoring of underground medium voltage cables based on machine learning techniques

In this paper a monitoring system for Medium Voltage (MV) cables is presented and simulated. It consists of a classification tool capable of identifying the working temperature of several sections of underground cables starting from the Frequency Response Analysis (FRA). This means that the monitoring procedure can be applied during normal network operation with a low intrusive level and allows the localization of the cable section in the worst working conditions. Starting from this information it is possible to organize the maintenance operations and avoid the occurrence of catastrophic failures. The monitoring method shown in this paper focuses on the relationship between cable temperature and conductor resistance. The online classification of the working temperature is carried out through two different machine learning techniques: Support Vector Machine (SVM) and Complex Neural Network (CNN). Both the single-fault hypothesis and the multiple-fault hypothesis are studied; in the first case the classification results are always higher than 95%, while in the more complex situation the classification rate decreases slightly. To make the simulation procedure as general as possible, Simulink-Simscape blocks, called "Three-phase AC power cable", are used in this paper.