English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Fault localization in distribution grids represents a crucial aspect in achieving the concept of smart grids within electrical networks. Despite the existence of various approaches to address this issue, it remains an open and challenging topic in real situations and, therefore, complex grids. One of the main challenges stems from the scarcity of labelled real-world examples is due to the inherent chaotic nature of faults (short circuits between a phase and ground). Obtaining sufficient fault examples for neural network training purposes becomes extremely difficult. Efforts have been made to simulate fault signals and apply data augmentation techniques. However, for fault location specifically, classical augmentation techniques are not applicable due to the unique nature of the fault signals. In this paper, we propose a novel approach to address the problem of extracting fault location information from TDR (Time Domain Reflectometry) signals. This kind of signals, involve injecting pulses into the grid and record these pulses as a bounced signal due to the different impedance changes of the grid. Our approach relies on employing a Transformer for anomaly detection. This Transformer-based Siamese network architecture (abbreviated by TransSiamese) is inspired by TranAD model. This Transformer has been modified to be trained in a Siamese way with a few examples (pre-fault signals/normal state and fault signals/abnormal state). After training phase, we can run inference mode by feeding it signals representing faulty grid states (fault signals). The Transformer attempts to predict the evolution of the signal, however, from a certain point to the end, the predicted fault signal deviates from the True signal supplied. Thanks to the intrinsic property of the Siamese network, it dampens the differences between the learned and the current signal when it comes to pre-fault; on the contrary, it enhances these differences when we are immersed in a fault signal.

TransSiamese: A Transformer-Based Siamese Network for Anomaly Detection in Time Series as Approach for Fault Location in Distribution Grids