A novel meta-learning network for partial discharge source localization in gas-insulated switchgear via digital twin

Abstract

Due to the requirement for highly precise synchronous sampling and the substantial reliance on time difference calculations, the current partial discharge (PD) localization based on the time difference of arrival is only applicable in certain situations. As digital twin technology has advanced, it is possible to employ virtual models to support gas-insulated switchgear (GIS) PD localization. To do this, we propose a meta-learning (ML) network with the aid of digital twin for actual GIS PD localization. Firstly, a GIS digital twin model was established to acquire an auxiliary simulated sample library. Then, a temporal convolutional network is established to extract the discriminable features, effectively obtain the time dependence between features, and improve the accuracy of localization. Next, ML is adopted to quickly learn meta-knowledge that can be applied across tasks, and the model's sensitivity to task changes is improved. Finally, the model is fine-tuned through a limited number of samples from the target task, and high precise PD localization is achieved. The experimental results demonstrate that the ML has an average localization error of only 9.25 cm and a probability density rose to 93% within 20 cm, which is clearly superior to previous methods.