Fractal Features-Based Partial Discharge Pattern Recognition Using Extension Method

Abstract

Partial discharge (PD) may cause the insulation deterioration in power equipments and impact the reliability. Therefore, the PD detection with pattern recognition is an important tool in high-voltage insulation diagnosis of power systems. A PD recognition system for high-voltage power cable based on extension method is proposed in this paper. A PD detector is used to measure the raw three-dimension (3D) PD patterns of XLPE power cable using L sensor, from which two fractal features (fractal dimension and lacunarity) and the mean discharge are extracted as PD features. These critical features form the cluster domains of defect types. The matter-element models of the PD defect types are then built according to the PD features derived from practical experimental results. The PD defect type can be directly identified by correlation degrees between the tested pattern and the matter-element models. To demonstrate the effectiveness of the PD features extraction and the extension method, the recognition ability is investigated on 160 sets of field-tested PD patterns of XLPE power cable. Compared whit a multilayer neural network (MNN) and K-means method, the results show the extension method has high accuracy and high tolerance in noise interference.