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.

Partial discharge (PD) source-type classification is essential for condition-based maintenance of high-voltage apparatus. Existing approaches based on grid discretizations of phase-resolved partial discharge (PRPD) patterns suffer from performance degradation under stochastic interference and multi-source conditions. This paper proposes a graph-based framework that integrates the morphological characterization of raw high-frequency PD waveforms with the phase-amplitude position of individual discharge events to enable multi-label classification, identifying multiple PD sources coexisting within a single test. The framework operates through three stages: a multi-task neural network extracts per-pulse embeddings and confidence scores; a construction procedure establishes selective graph connectivity based on spatial proximity and morphological similarity; and an edge-conditioned graph neural network performs classification via message passing weighted by multimodal edge attributes. Experimental evaluation on PD measurements acquired in accordance with IEC 60270 shows that the proposed framework achieves a Matthews correlation coefficient (MCC) of 0.98 and an exact match ratio of 0.97 across single-source, noisy, and multi-source conditions, substantially outperforming histogram- and set-based baselines. The framework maintains an MCC of 0.97 in multi-source scenarios, where its advantage over existing methods is most pronounced. Cross-domain evaluation on an independent dataset acquired with different laboratory equipment confirms the approach’s robustness, achieving an MCC of 0.93 without retraining. Finally, an ablation study demonstrates that the joint removal of morphological similarity filtering and confidence-based node filtering and edge gating reduces the MCC by 0.25, confirming the critical role of the waveform-informed relational structure.