基于声学特征的变压器局部放电检测方法  

Transformer Partial Discharge Detection Method Based on Acoustic Characteristics

作　　者：徐欧珺 吕佳芮 XU Oujun;LYU Jiarui(Lishui Just Power Industrial Group Co.,Ltd.,Lishui 323000,China;Lishui Puming Electric Power Construction Engineering Co.,Ltd.,Lishui 323000,China)

机构地区：[1]丽水正好电力实业集团有限公司,浙江丽水323000 [2]丽水普明电力建设工程有限公司,浙江丽水323000

出　　处：《电声技术》2025年第1期135-137,共3页Audio Engineering

摘　　要：准确检测变压器局部放电对于电力系统的稳定运行具有至关重要的作用。研究一种面向声学特征的基于小波变换的时频域特征提取方法,并结合主成分分析与支持向量机检测变压器局部放电的声音信号。实验结果表明,所提出的方法在检测变压器正常和异常工作状态下的样本中具有出色的表现,精确率为0.915,准确率为0.915,F1值为0.92。Accurate detection of partial discharge of transformers plays a vital role in the stable operation of power systems.A timefrequency domain feature extraction method based on wavelet transform for acoustic features is studied,and combines principal component analysis and support vector machine to detect the sound signal of partial discharge of transformer.The experimental results show that the proposed method has excellent performance in detecting samples under normal and abnormal working conditions of transformers,with an accuracy rate of 0.915,an precision rate of 0.915,and an F,value of 0.92.

关 键 词：变压器 局部放电 声音特征 支持向量机(SVM) 

分 类 号：TM711[电气工程—电力系统及自动化]