Application of Convolutional Neural Networks for Advanced Classification of Power Quality Signals

Resumo

In this work, we explore the classification of power quality signals using a simulated database incorporating both unique and combined disturbances in accordance with IEEE 1159 standards. The primary focus is on employing convolutional neural networks (CNNs) for the detection and classification of these anomalies. To assess the effectiveness of our approach, we conducted a comprehensive comparison between the outcomes from CNNs and traditional machine learning techniques, as well as with recent literature findings. Preliminary results indicate that CNNs exhibit a remarkable ability to capture distinctive features of power quality signals, surpassing traditional methodologies in terms of accuracy and robustness. This study not only reaffirms the potential of convolutional neural networks in the field of power quality monitoring but also paves the way for future investigations that might explore more complex deep learning approaches to further enhance the accuracy of anomaly classification in electrical systems.