Aging, degradation, or damage to internal insulation materials often contribute to transformer failures. Furthermore, combustible gases can be produced when these insulation materials experience thermal or electrical stresses. This paper presents an artificial neural network for pattern recognition (PRN) to classify the operating conditions of power transformers (normal, thermal faults, and electrical faults) depending on the combustible gases present in them. Two network configurations were presented, one with five and the other with ten neurons in the hidden layer. The main advantage of applying this model through artificial neural networks is its ability to capture the nonlinear characteristics of the samples under study, thus avoiding the need for iterative procedures. The effectiveness and applicability of the proposed methodology were evaluated on 815 real data samples. Based on the results, the PRN performed well in both training and validation (for samples that were not part of the training), with a mean squared error (MSE) close to expected (0.001). The network was able to classify the samples with a 98% accuracy rate of the 815 samples presented and with 100% accuracy in validation, showing that the methodology developed is capable of acting as a tool for diagnosing the operability of power transformers.

Transformers can produce gases dissolved in oil that can cause damage to their structures, and preventing failures caused by these gases is a goal to be reached. There is a demand for wireless sensors to monitor those gases. Alongside its development, there is a growing interest in new energy sources enabling these technologies. Triboelectric nanogenerators can gather energy from the environment, such as mechanical energy from vibrations, and convert it into electricity from the contact of two dielectric materials. In this work, the authors propose the study of a low-cost and straightforward triboelectric nanogenerator (TENG) based on ZnO nanorods as a positive dielectric material, with PDMS:GO composites at different concentrations as the negative dielectric material. All the studies were carried out in a wide frequency range varying from 45 to 250 Hz. Additionally, an analysis of the addition of a steel spring into the TENG to improve the device’s generating output is shown. A power density of 246 mV m${}^{-2}$ and 4 V of the output voltage was obtained using a PDMS:GO 4% (w/w) composite and a steel spring. A correlation between the “mass-spring” system and the better performance of the triboelectric device is presented. Further, vibration frequencies in several external points of the transformer walls and the device’s performance in these frequencies are shown, and the results gathered from this data are discussed.

With the growth of smart grids, consumers now have access to new technologies that enable improvements in the quality of service provided and allow new levels of energy efficiency. Much of this increase in energy efficiency is directly related to changes in consumption habits due to the quantity and quality of information made available by new technologies. At this point, short-term consumption forecasting can be considered an effective information tool in the search for better consumption patterns and energy efficiency. This paper presents prediction tests combining the result obtained from an artificial neural network and regression methods. The artificial neural network used was the Multilayer Perceptron (MLP), and its results were compared with polynomial regression techniques (first, second, and third degree), demonstrating the superiority of the network. The neural network has proven to be a highly effective tool for forecasting future data, demonstrating its ability to capture complex patterns in input data and produce accurate estimates. Additionally, the flexibility of neural networks in handling large volumes of data and their continuous adjustment capability further enhance their suitability as a robust tool for future predictions. The results corroborate the capacity of the methodology presented for short-term consumption forecasting.

Technical power losses in power systems are unavoidable, caused by factors such as transformer impedance, conductor resistance, equipment inefficiencies, line reactance, and phase imbalances. Reducing these losses is essential for improving system efficiency. This study introduces an innovative approach using Artificial Neural Networks (ANN) combined with the graphical interface to predict complete curves of real and reactive power losses in power systems under various contingencies. The key advantage of this methodology is its speed, allowing quick estimation of power loss curves both in normal and contingency conditions, whether mild or severe. ANN models excel at capturing the nonlinear behavior of power systems, eliminating the need for iterative methods commonly used in traditional approaches. The results showed that the ANN performed effectively, with a mean squared error during training below the specified threshold. For samples not included in the training set, the network accurately estimated 99% of the real and reactive power losses within the specified range, with residuals around 10⁻³ and an overall accuracy rate of 99% between the desired and obtained outputs. Additionally, a Graphical User Interface (GUI) was implemented to facilitate user interaction, allowing for easy visualization of power-loss predictions and real-time adjustments.

Na busca de uma matriz elétrica limpa de baixo carbono o país está diante de um novo arranjo elétrico, devido a inserção das energias renováveis, a micro e minigeração distribuída fotovoltaica cresce exponencialmente. Gerando novos desafios ao setor e as políticas públicas, provocando novos serviços as concessionárias de distribuição, gerando possíveis impactos no custo operacional, esse artigo apresenta tais situações, que devem ser entendidas e mitigadas para equilibrar esses novos cenários.