Evaluation of AI-based Compression Methods for Current Wave-forms of Partial Discharges in High Voltage Systems

Inhalt:
In order to improve automated AI-based partial discharge (PD) analysis, it will be investigated whether the use of the entire PD current waveform has advantages over using only the apparent charge and phase reference. As a part of the research, this paper investigates the use of compression algorithms to reduce the amount of data when transmitting, storing and analyzing high-resolution PD current waveforms. For this purpose, traditional compression methods are extended by an AI-based approach. This leads to significantly higher compression rates, which makes it possible to reduce the com-plexity of AI based analysis systems.