Partial discharge (PD) measurements are crucial for evaluating the condition of the insulation systems of medium-voltage (MV) cables and their accessories. However, identifying PD defect types from phase-resolved partial discharge (PRPD) patterns still largely relies on expert knowledge. In this paper, the authors critically evaluate lightweight deep neural network architectures for automated classification of insulation defects from PRPD patterns: YOLOv8n, the MobileNetV2–YOLO hybrid network, and a compact SqueezeNet-based model. PD measurements were performed in a controlled environment in a factory laboratory for MV power cables in order to better evaluate the capability of the investigated models. The results demonstrate that lightweight deep neural architectures can effectively classify PRPD patterns and be deployed in a real measurement environment. The proposed approach has been integrated with the OMICRON MPD Suite measurement system, enabling automated defect recognition and visualisation during routine testing of MV cable.
Kluge et al. (Wed,) studied this question.