A Novel Wavelet Aided Probabilistic Generative Model for Fault Detection and Classification of High Voltage Transmission Line

Abstract

This paper presents a novel discrete wavelet transform (DWT) based probabilistic generative model for fault detection and classification (FDC) of transmission line. The transmission lines frequently experience the number of shunt faults that affects the system stability, damages the load and increases the line restoration cost. Therefore, a robust and precise model is needed to detect and classify the faults for the rapid restoration of faulty phases. In this paper, we propose a deep belief networks (DBN) model for FDC based on discrete wavelet transformation which is made of multiple layers with restricted Boltzmann machine (RBM) that enables the model to learn the probability reconstruction over its inputs. The effectiveness of the proposed DBN is tested by using the number of input signals under various sampling frequencies and obtained results compared with existing methods. Results show that the proposed model is capable to perform precise FDC of transmission line.