Contamination Level On-Line Diagnosis Method of Ceramic Insulator Based on Soundprint Recognition

In order to improve the external insulation level of insulators and maintain the stable operation of power system, an on-line analysis method based on wavelet packet decomposition and principal component analysis is proposed. The sound of insulator discharge under different pollution degree and discharge state can be identified effectively by using sound pressure level and frequency band energy through laboratory simulation. The results show that this research method can effectively distinguish the discharge types at different stages from the pollution discharge soundprint characteristics of insulators.