Antonio Francisco Leite Neto

This paper proposes an integrated framework for predictive asset management in electric power distribution systems by combining machine learning with the Analytic Hierarchy Process (AHP). Distinct utility datasets were used according to the characteristics of each prediction task. Annual preventive- and corrective-maintenance records, including maintenance cost and frequency, covered the period from 2016 to 2023, whereas the SAIDI and SAIFI annual time series covered the period from 2014 to 2023. Remaining Useful Life (RUL) estimation was based on static asset-level records from the entire available equipment stock and therefore was not associated with a single time-series interval. Multiple machine learning algorithms were evaluated independently for each Type of Utility Component (TUC), and the best-performing models were selected according to their validation errors. The resulting predictions were incorporated into a two-level AHP hierarchy that integrates technical, economic, operational, and regulatory criteria for portfolio-level asset-renewal prioritization. For RUL estimation, the selected TUC-specific models reduced the mean MAE from 11.33 years for the historical-mean baseline to 2.70 years, corresponding to an absolute improvement of 8.63 years and a relative reduction of 76.15%. The resulting priority ranking was evaluated retrospectively using moving-average, cumulative-gain, and lift analyses. The top 20% of ranked assets captured 29.61% of the observed corrective-maintenance occurrences, corresponding to a lift of 1.4806 relative to random selection. The cumulative-gain curve yielded an area under the curve of 0.6337 and a ranking Gini coefficient of 0.2674, indicating moderate positive discrimination across the asset portfolio. These results show that the proposed ML–AHP framework can support the allocation of inspection, engineering-assessment, and renewal resources toward assets with comparatively greater maintenance demand and operational relevance. The framework provides a structured, data-driven decision-support approach for utility asset-renewal planning, while prospective field implementation remains necessary to quantify reductions in failures, corrective maintenance, continuity penalties, and total expenditure.

The climatic conditions of an environment and its unpredictable changes can be a major problem in the sizing of long transmission lines, due to the constant exposure of its components to the various types of weather present in the environment. The accumulation of pollutants on the surface of insulators is one of the main factors contributing to insulation failures in transmission lines. This wear occurs because when it comes into contact with moisture, a thin conductive layer forms, changing the distribution of the electric potential and increasing the concentration of the electric field. Thus, it is relevant to analyze insulators in operation when they are subjected to adverse conditions imposed by the environment, which can lead to failures, damaging equipment, causing inconvenience and losses due to eventual shutdowns in the electrical power system. This work analyzes two topologies of pin-type polymeric insulators, voltage class of 15 kV, with the objective of analyzing the electrical behavior when the insulator is subjected to pollution. The analysis of the electric potential, electric field and current density in polymeric insulators is performed using computer simulation. A pollution layer is modeled on the surface of the insulators in order to investigate the influence of pollution on the operation of the insulators, with the variation of the conductivity and permittivity parameters it is possible to simulate pollution at different levels of criticality. From the results obtained, it was possible to observe the electrical characteristics of the two different topologies of polymeric insulators and to verify which is the best topology for the different levels of pollution.

This paper presents a study of the electric field in pin type insulators under the influence of an internal cavity. Polymeric insulators 15 kV were modeled with the aid of technical design software. Computational simulations to obtain the electric field were performed using COMSOL Multiphysics. The simulated cavity inside the insulator has spherical and elliptical geometry, with different values for its diameter. The position of the internal defect was varied from a region near the cable to a region near the hardware. For each simulated case, three levels of pollution were applied to the surface of the insulator, also considering the case in which it is intact. The results obtained for the case in which the insulator is intact does not present large variations in the electric field in the internal region. With the presence of a cavity, the electric field distortions in the cavity region assumed high values, surpassing in some cases the value of the dielectric strength of atmospheric air. The most critical defect detected was for elliptical geometry, whose electric field values were higher than the spherical case.

Lightning strikes are a leading cause of outages on overhead transmission lines, significantly compromising power system reliability. Consequently, monitoring lightning activity is critical to mitigate its impact on lines with high outage rates. This study presents an autonomous lightning strike counter system utilizing a split-core Rogowski coil for non-invasive current measurement on transmission towers. The system combines the Rogowski coil with an active integrator circuit to reconstruct the incident current waveform from the coil voltage signal. A microcontroller-based processing unit records strike occurrences and classifies them by amplitude using predefined thresholds. Laboratory tests were carried out to evaluate the performance of the Rogowski coil and integrator circuit, validating the system accuracy in detecting current pulses associated with lightning strikes. Underway field tests will assess the sensor’s reliability during long-term autonomous operation on 345-kV transmission towers. The results demonstrate that the proposed system represents a practical and cost-effective solution for lightning monitoring in remote areas, contributing to enhanced data collection for engineering studies and improved reliability of electrical infrastructure.

This work proposes a methodology for noise removal, separation, and classification of partial discharges in electrical system assets. Partial discharge analysis is an essential method for fault detection and evaluation of the operational conditions of high-voltage equipment. However, it faces several limitations in field measurements due to interference from radio signals, television transmissions, WiFi, corona signals, and multiple sources of partial discharges. To address these challenges, we propose the development of a clustering model to identify partial discharge sources and a classification model to identify the types of discharges. New features extracted from pulses are introduced to model the clustering and classification of discharge sources. The methodology is tested in the laboratory with controlled partial discharge sources, and field tests are conducted in substations to assess its practical applicability. The results of laboratory tests achieved an accuracy of 85% in classifying discharge sources. Field tests were performed in a substation of the Eletrobras group, allowing the identification of at least three potentially defective current transformers.

This work presents a methodology for the generation and classification of phase-resolved partial discharge (PRPD) patterns based on the use of a printed UHF monopole antenna and signal conditioning circuit to reduce hardware requirements. For this purpose, the envelope detection technique was applied. In addition, test objects such as a hydrogenerator bar, dielectric discs with internal cavities in an oil cell, a potential transformer and tip–tip electrodes immersed in oil were used to generate partial discharge (PD) signals. To detect and classify partial discharges, the standard IEC 60270 (2000) method was used as a reference. After the acquisition of conditioned UHF signals, a digital signal filtering threshold technique was used, and peaks of partial discharge envelope pulses were extracted. Feature selection techniques were used to classify the discharges and choose the best features to train machine learning algorithms, such as multilayer perceptron, support vector machine and decision tree algorithms. Accuracies greater than 84% were met, revealing the classification potential of the methodology proposed in this work.

This work presents a methodology for the generation and classification of phase resolved partial discharges (PRPD) patterns based on the use of a printed UHF monopole antenna and signal con-ditioning circuit to reduce hardware requirements. For this purpose, envelope detection technique was applied. In addition, test objects such as a hydrogenerator bar, dielectric disks with internal cavities in an oil cell, potential transformer, and tip-tip electrodes immersed in oil were used to generate partial discharge (PD) signals. To detect and classify partial discharges, the standard IEC 60270 (2000) method was used as reference. After acquisition of conditioned UHF signals, digital signal filtering threshold technique was used, and peaks of partial discharges envelopes pulses were extracted. Feature selection techniques were used to classify the discharges and choose the best features to train machine learning algorithms, such as multilayer perceptron, support vector ma-chine and decision tree. Accuracies greater than 84% were met, revealing the classification potential of the methodology proposed in this work.

This paper presents a methodology capable of measuring, processing, and extracting contact resistance parameters that enable the identification of the contact degradation level inside arc extinction chambers in medium- and high-voltage circuit breakers (CB). To determine the contact degradation level, an algorithm was developed to extract the characteristic parameters from the results of dynamic resistance measurement (DRM). To analyze the dataset parameters, this work employs the combination of different statistical tools, such as boxplots and fuzzy logic, enabling the evaluation to be conducted without the subjectivity inherent in human decision. Therefore, a more objective and reliable diagnosis could be achieved. The DRM tests were performed on two types of minimum-oil CB (MOCB), 800 A/15 kV/12.5 kA (CB-A) and 2000 A/72.5 kV/31.5 kA (CB-B and CB-C). For CB-A and CB-B, three contacts were utilized for each CB, with significant contact degradation. For CB-C, a single contact was employed without significant degradation. The DRM curves of the CB-C contact were used as the reference for evaluation of the CB-B contacts. For this purpose, a new DRM system was developed. The proposed methodology can be defined as a complement for other diagnostic techniques, serving as a non-subjective asset management tool, supporting decisions regarding equipment interventions.