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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Incipient fault detection in power distribution systems is crucial to improvethe reliability of the grid. However, the non-stationary nature and theinadequacy of the training dataset due to the self-recovery of the incipientfault signal, make the incipient fault detection in power distribution systemsa great challenge. In this paper, we focus on incipient fault detection inpower distribution systems and address the above challenges. In particular, wepropose an ADaptive Time-Frequency Memory(AD-TFM) cell by embedding wavelettransform into the Long Short-Term Memory (LSTM), to extract features in timeand frequency domain from the non-stationary incipient fault signals.We makescale parameters and translation parameters of wavelet transform learnable toadapt to the dynamic input signals. Based on the stacked AD-TFM cells, wedesign a recurrent neural network with ATtention mechanism, named AD-TFM-ATmodel, to detect incipient fault with multi-resolution and multi-dimensionanalysis. In addition, we propose two data augmentation methods, namely phaseswitching and temporal sliding, to effectively enlarge the training datasets.Experimental results on two open datasets show that our proposed AD-TFM-ATmodel and data augmentation methods achieve state-of-the-art (SOTA) performanceof incipient fault detection in power distribution system. We also disclose oneused dataset logged at State Grid Corporation of China to facilitate futureresearch.

Incipient Fault Detection in Power Distribution System: A Time-Frequency Embedded Deep Learning Based Approach