Partial Discharge Pattern Recognition of XLPE Cable Based on Vector Quantization

The apparent charge sequence of cable joint samples with typical defects at different test voltages is utilized as a feature for pattern recognition of partial discharge (PD). The vector quantization and fast matching algorithm are introduced to realize PD pattern recognition of the cable. First, the codebook design makes use of Linde-Buzo-Gray encoding technology. Second, the code matrices of PD training samples and testing samples under different defects of cable joints are obtained, and the code occurrence frequency matrix is calculated. Finally, a fast matching algorithm is used to match the code occurrence frequency matrices of training and testing samples. The defect type with the highest matching degree is chosen as the recognition result. The recognition results of 100 samples of cable joints with four defect types demonstrate that the recognition algorithm has the advantages of high execution efficiency and high-recognition rate.