Deep Learning for High-Impedance Fault Detection and Classification
Abstract
High-Impedance Faults (HIFs) are a hazard to public safety but are difficult to detect because of their low current amplitude and diverse characteristics. Supervised machine learning techniques have shown great success in HIF detection; however, these approaches rely on resource-intensive signal processing techniques and fail in presence of non-HIF disturbances and even for scenarios not included in training data. This thesis leverages unsupervised learning and proposes a Convolutional Autoencoder framework for HIF Detection (CAE-HIFD). In CAE-HIFD, Convolutional Autoencoder learns only from HIF signals by employing cross-correlation; consequently, eliminating the need for diverse non-HIF scenarios in training. Furthermore, this thesis proposes a novel HIF classification approach based on the transformer network stacked with the convolution neural network. To discriminate HIFs from non-fault disturbances, probability distribution-based kurtosis analysis is utilized. The proposed approaches reliably detect HIFs with a 100% success rate in terms of all five metrics of protection system performance, namely accuracy, security, dependability, safety, and sensitivity. The evaluation studies show that proposed approaches outperform the state-of-the-art HIF detection techniques and are robust against noise.