Application of the Hilbert–Huang transform with fractal feature enhancement on partial discharge recognition of power cable joints

Abstract

This study proposes a novel method of partial discharge (PD) pattern recognition based on the Hilbert-Huang transform (HHT) with fractal feature enhancement. First, this study establishes three common defect types with one blank sample of 25 kV cross-linked polyethylene (XLPE) power cable joints and uses a commercial acoustic emission sensor to measure the acoustic signals caused by the PD phenomenon. The HHT can represent instantaneous frequency components through empirical mode decomposition, and then transform to a 3D Hilbert energy spectrum. Finally, this study extracts the fractal theory feature parameters from the 3D energy spectrum by using a neural network for PD recognition. To demonstrate the effectiveness of the proposed method, this study investigates its identification ability using 120 sets of field-tested PD patterns generated by XLPE power cable joints. Unlike the fractal features extracted from traditional 3D PD images, the proposed method can separate different defect types easily and shows good tolerance to random noise.