In order to ensure the continuous and reliable supply of electrical energy to the power grid, it is necessary to evaluate and monitor the degree of impairment of the insulation of electrical cables, as throughout its service life, insulation around cables suffers degradation due to numerous stress factors, which can arise from both environmental and operational causes. This aspect has aroused deep interest among energy professionals, as well as the industrial sector, with focus mainly placed on the undesirable effect caused by unexpected and sudden process stoppages, as well as their consequent financial and social impacts. That said, this article presents a methodology for evaluating the degree of insulation aging using the partial discharge progression curve. For this purpose, a thermal oven was duly constructed, in accordance with the technical premises presented in the literature, capable of homogeneously heating conductor samples. After thermal cycles, these conductors were aptly handled and tested in a controlled laboratory environment to determine the partial discharge progression curve. Through accurate data processing, a correlation was obtained between the degradation of the insulation and the rate of increase in partial discharge. The results are promising, as they provide support for maintenance agents’ ability to monitor and intervene regarding conductors.

In this article, an unsupervised learning method is presented with the objective of modeling, in real-time, the main operating modes (OM) of distribution transformers. This model is then used to assess the operational condition through use of two tools: the operation map and the health index. This approach allows, mainly, for a reduction in the need for the interpretation of results by specialists. The method used the concepts of k-nearest neighbors (k-NN) and Gaussian mixture model (GMM) clustering to identify and update the main OMs and characterize these through operating mode clusters (OMC). The evaluation of the method was performed using data from a case study of almost one year in duration, along with five in-service distribution transformers. The model was able to synthesize 11 magnitudes measured directly in the transformer into two latent variables using the principal component analysis technique, while preserving on average more than 86% of the information present. The operation map was able to categorize the transformer operation into previously parameterized levels (appropriate, precarious, critical) with errors below 0.26 of standard deviation. In addition, the health index opened the possibility of identifying and quantifying the main abnormal variations in the operating pattern of the transformers.