Trabalho de Conclusão de Curso - TCC https://repositorio.ifpe.edu.br/xmlui/handle/123456789/474 2026-07-13T16:20:47Z 2026-07-13T16:20:47Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/2226 2026-07-07T06:01:25Z 2026-06-09T00:00:00Z

Aplicação de redes neurais convolucionais na identificação de pontos quentes em redes de distribuição This work proposes the application of Convolutional Neural Networks for the automated detection of hotspots in electrical power distribution networks using thermographic images. The methodology adopts a two-stage processing architecture (Two-Stage Framework): in the first stage, the YOLOv8 algorithm performs the detection and spatial location of electrical assets—poles, switches, and cable terminations—; in the second stage, the U-Net network performs pixel-by-pixel semantic segmentation of the thermal anomalies identified in the segmented components. The dataset consisted of 500 thermographic images, obtained by a FLIR camera in a distribution network in the municipality of Belo Jardim (PE), with the application of data augmentation techniques to increase the sample variability. The

2026-06-09T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/1978 2026-01-30T06:00:48Z 2025-12-19T00:00:00Z

Análise paramêtrica da energização de uma linha de transmissão de 500kV utilizando o software ATPDraw This work analyzes the behavior of transient overvoltages during the energization switching of a 500 kV transmission line (TL) between the Bom Nome II and Campo Formoso II substations, motivated by the expansion of renewable generation and the need to ensure reliability in the Brazilian Interconnected Power System. The objective is to evaluate the influence of the line length and the mitigation of overvoltages at remote terminals through surge arresters, using simulations in the ATP (Alternative Transients Program) software based on a benchmark case validated by the Brazilian Electricity Regulatory Agency (ANEEL). The results show that increasing the line length intensifies overvoltage levels due to wave reflections. It is concluded that the energization of long transmission lines requires special attention, as they produce the highest overvoltages at remote terminals, reinforcing the importance of transient studies to ensure system safety, insulation coordination, and overall reliability. Keywords: Energization, Overvoltages, ATPDraw, Transmission Line.

2025-12-19T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/1977 2026-01-30T06:00:41Z 2025-12-18T00:00:00Z

Avaliação de sobretensões transitórias em linhas de transmissão com a variação do comprimento da linha utilizando o software ATP This work presents an analysis of the effects of electromagnetic transients in a 500 kV transmission line during the automatic reclosing process, using the Alternative Transient Program (ATP) as the simulation tool. The 500 kV Bom Nome II – Campo Formoso II transmission line was adopted as the study case. This line was part of ANEEL Transmission Auction No. 001/2024, and the ATP base case for Electromagnetic Transient studies for the Basic Design (PB) was made available on the official website. Based on this case, the behavior of transient overvoltages during the three-pole line reclosing maneuver was evaluated by varying the line length. Different line lengths were simulated (50 km, 100 km, 200 km, 300 km, and 373 km). The results showed that increasing the line length leads to higher magnitude and longer duration of overvoltages, due to the greater amount of energy stored in the electric and magnetic fields. It is concluded that a detailed understanding of these parameters is essential for accurately predicting operating conditions and ensuring the reliability of electric power systems.

2025-12-18T00:00:00Z https://repositorio.ifpe.edu.br/xmlui/handle/123456789/1959 2026-01-06T06:01:40Z 2025-12-04T00:00:00Z

Metodologia para automatizar a detecção do efeito borda de nuvem utilizando Python This work provides a comprehensive investigation of the cloud enhancement effect, an atmospheric phenomenon in which solar irradiance exceeds expected values due to the interaction of sunlight with cloud edges, resulting in radiative focusing and an increase in the diffuse component. The study begins with an introduction to solar radiation, highlighting the attenuation of energy from the top of the atmosphere to the surface, as well as the composition of global irradiance into direct and diffuse components. It then discusses the importance of clear-sky models, with emphasis on Gueymard’s method and its contributions to improving irradiance estimates, particularly in studies addressing extreme deviations such as the peaks associated with cloud enhancement. The literature review shows that rapid and intense irradiance fluctuations can compromise the reliability of measurement instruments, affect sensor calibration, influence weather forecasting, and require greater rigor in solarimetric analyses due to the sudden and short-lived nature of these events. Based on these foundations, the present study applies measured data processing to analyze the occurrence of such peaks, identifying characteristic patterns and comparing them with clear-sky reference irradiance limits. Data from the Cedro-PE station (2022) were processed in Python, replacing the manual Excel-based workflow. The implemented algorithm enabled more precise and efficient filtering, grouping, and duration estimation of events. Validation confirmed equivalence with manual results, demonstrating the reliability of the automated approach and its applicability to large- scale solarimetric analyses, reinforcing the relevance of this study for improving solar energy monitoring, diagnostics, and forecasting methods. Keywords: Cloud enhancement. Solar irradiance. Clear-sky model. Gueymard method. Data processing.

2025-12-04T00:00:00Z