Feature Extraction and Classification of UHF PD Signals Based on Improved S-Transform

LONG Jiachuan; WANG Xianpei; DAI Dangdang; TIAN Meng; ZHU Guowei; HUANG Yunguang

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Feature Extraction and Classification of UHF PD Signals Based on Improved S-Transform

更新时间：2025-12-08

- Feature Extraction and Classification of UHF PD Signals Based on Improved S-Transform
- Vol. 44, Issue 11, Pages: 3649-3656(2018)
- 作者机构：
  
  1. 武汉东湖学院电子信息工程学院
  2. 武汉大学电子信息学院
  3. 广西电网有限责任公司电力科学研究院
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published Online：22 November 2018，
  
  Published：2018
- 稿件说明：
移动端阅览
LONG Jiachuan, WANG Xianpei, DAI Dangdang, et al. Feature Extraction and Classification of UHF PD Signals Based on Improved S-Transform[J]. 2018, 44(11): 3649-3656.
DOI：

LONG Jiachuan, WANG Xianpei, DAI Dangdang, et al. Feature Extraction and Classification of UHF PD Signals Based on Improved S-Transform[J]. 2018, 44(11): 3649-3656. DOI：

摘要

超高频（ultra-high frequency

UHF）局部放电（partial discharge

PD）检测法是目前应用最广泛的PD检测方法之一

通过提取UHF PD信号的时频特征可实现PD类型的识别。因此提出了一种基于改进S变换的UHF PD信号时频特征提取方法

首先通过引入新的频域窗宽度计算公式对标准S变换进行改进;然后根据得到的S变换模矩阵计算频率-最大幅值图

并提取出6维统计特征量;最后结合支持向量机（support vector machine

SVM）完成PD信号的识别。试验结果表明:该方法兼顾了S变换的时、频域分辨率

使得到的特征量能更加准确地反映PD成分在时频域的分布特性;在未经去噪的情况下

该方法仍可获得高达97.33%的分类正确率

验证了其较强的噪声鲁棒性;与常用的PD信号特征提取法相比

所提方法获得的PD类型识别率更高。研究结果可以为超高频局部放电信号识别提供参考。

Abstract

The ultra-high frequency partial discharge detection method is one of the most widely used methods for PD monitoring. The PD signal type can be identified by extracting the time-frequency characteristics of UHF PD signals. We proposed a time-frequency feature extraction method for UHF PD signal based on the improved S-transform. Firstly

the S-transform was improved by introducing a new calculation formula for the frequency-domain window width. Then

the six-dimensional statistical features were computed from the frequency-maximum value graphs

which were calculated based on the S-transform modular matrix. Finally

the SVM algorithm was employed to perform the PD signals recognition. The experimental results show that the proposed method can reflect the distribution characteristics of PD components more accurately in the time-frequency domain due to the consideration of both time-domain and frequency-domain resolution. The proposed method can achieve a high classification accuracy of 97.33% even without denoising processing

which proves its strong noise robusticity. Compared with some commonly used feature extraction methods of PD signal

the proposed method can obtain a higher PD type recognition rate. The results provide references for the recognition of UHF PD signals.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Development of UHF PD Signal Simulator with Multiple Adjustable Parameters

Propagation Characteristics of Utral High Frequency Signals in an Actual Power Transformer

Feature Extraction Method for Partial Discharge Pattern in GIS Based on Time-frequency Analysis and Fractal Theory

Present Status and prospect of Research of On-Line Partial Discharge Monitoring System in GIS

超紧凑封装高压串联SiCMOSFET脉冲功率模块

Related Author

DU Lin

LIU Shuncheng

YANG Xian

LI Jian

WU Xiong

DU Jinchao

CHEN Weigen

ZHANG Zhixian

Related Institution

State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University

Economic and Technology Research Institute,State Grid Hunan Electric Power Company

Guangdong Electric Power Research Institute

Electric Power Research Institute of Guangdong Power Grid Corporation

Electric Research Institute of State Grid Zhejiang Electric Power Company

AI问答

⁰