Deep Learning Ensemble-based Robust Intelligent Fault Detection and Classification Strategy for Power Transmission Line

This paper introduces a novel architecture for anomaly detection and classification of high-voltage transmission line using the self-attention convolutional neural network enhanced with wavelet transform (WSATCNN). The transmission lines repeatedly face an aggregation of shunt-faults and its impact in the real time system increases the vulnerability, damage in load, and line restoration cost. In this paper, we propose a WSAT-CNN model for enhanced noise immunity and to pay more attention to the fault features. The proposed model consists of number of layers with self-attention mechanism that allows the model to recognize the fault more accurately. The resilience of the presented framework is validated by reckoning the noises to the input data. The results indicate that the proposed approach is capable of accurately classifying and detecting faults in transmission line with high precision