An Algorithm for Power System Fault Analysis ...

An Algorithm for Power System Fault Analysis based on Convolutional Deep Learning Neural Networks

Author Name : Florian Rudin, Guo-Jie Li, Keyou Wang

ABSTRACT:   This paper discusses the possibility of using deep learning architecture using convolutional neural networks (CNN) for real-time power system fault classification. This work is about fault classification only and not about localization. It aims to classify power system voltage signal samples in real time and determine whether they belong to a faulted or non-faulted state. The data is produced by simulating a simple two-bus power system with a three -phase balanced load. The voltage signal is measured at the beginning of the line between the two buses while the fault occurs at half of the line length between the two buses. In a first step, Wavelet transform is used to extract fault harmonics using db4 Daubechies mother wavelets. A sample window of fixed size is slid over the wavelet detail at decomposition level 4 which seems to be a suitable choice. After normalization, the generated training samples are fed into the CNN for learning procedure. The CNN learns fault features of the power system through training by faulted and non-faulted samples to finally classify samples from a test set.1