Typical Defect Identification Method of Transformer Based on Robust Local Mean Decomposition and Voiceprint Features

WANG Leilei; ZHANG Zhuangzhuang; WANG Donghui; TONG Jianwei; ZHANG Yang; WANG Xiao

doi:10.13296/j.1001-1609.hva.2026.02.028

您当前的位置：

首页 >

文章列表页 >

Typical Defect Identification Method of Transformer Based on Robust Local Mean Decomposition and Voiceprint Features

Technical Discussion | 更新时间：2026-03-16

- Typical Defect Identification Method of Transformer Based on Robust Local Mean Decomposition and Voiceprint Features
- High Voltage Apparatus Vol. 62, Issue 2, Pages: 230-236(2026)
- 作者机构：
  
  国网河南省电力公司电力科学研究院，郑州 450052
  国网河南省电力公司鹤壁供电公司，河南鹤壁 458030
  上海睿深电子科技有限公司，上海 200237
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2026.02.028
  CLC：
- Received：21 July 2025，
  
  Revised：2025-10-11，
  
  Published：16 February 2026
- 稿件说明：
移动端阅览
WANG Leilei, ZHANG Zhuangzhuang, WANG Donghui, et al. Typical Defect Identification Method of Transformer Based on Robust Local Mean Decomposition and Voiceprint Features[J]. High Voltage Apparatus, 2026, 62(2): 230-236.
DOI：

WANG Leilei, ZHANG Zhuangzhuang, WANG Donghui, et al. Typical Defect Identification Method of Transformer Based on Robust Local Mean Decomposition and Voiceprint Features[J]. High Voltage Apparatus, 2026, 62(2): 230-236. DOI： 10.13296/j.1001-1609.hva.2026.02.028.

摘要

为实现现场运行环境下电力变压器运行状态的可靠辨识，提出了一种基于鲁棒局部均值分解（robust local mean decomposition，RLMD）与声纹特征的变压器典型缺陷辨识方法。该方法首先利用RLMD方法实现原始采集声纹信号的降噪处理，再借助皮尔逊相关系数保留与原始声纹信号相关性强的子带分量；其次提取每个子带分量的声纹特征值组成变压器不同状态的特征参量矩阵；最后利用随机森林算法进行状态辨识。搭建了包含3种电力变压器设备典型故障的试验模拟系统，试验结果表明：所提方法实现了电力变压器不同工作状态的可靠表征，且辨识精度较常规方法提升约7%。

Abstract

For achieving reliable identification of operating status of power transformer in the on-site operating environment

a typical defect identification method of transformer based on robust local mean decomposition (RLMD) and voiceprint features is proposed. Firstly

the RLMD method is used to achieve noise reduction processing of the original collected voiceprint signal

and the sub-band components with strong correlation with the original voiceprint signal are retained with the Pearson correlation coefficient. Then

the voiceprint feature values of each sub-band component are extracted to form the feature parameter matrix of the transformer in different status. Finally

the random forest algorithm is used for status identification. A simulation system containing three typical faults of power transformer is set up

and the test results show that the proposed method realizes reliable characterization of power transformer in different working status

and the identification accuracy is improved by about 7%compared with conventional methods.

关键词

Keywords

references

王署东.基于传感器阵列的变电站局部放电定位关键技术研究[D].合肥：合肥工业大学,2021.

WANG Shudong. Research on key technologies of partial discharge localization in substation based on sensor array[D]. Hefei:Heifei University of Technology, 2021.

李旭,王文森,郭丽,等.基于多传感器融合的电力变压器内部放电定位与辨识技术[J].电网与清洁能源,2024,40(3):22-31.

LI Xu, WANG Wensen, GUO Li, et al.Internal discharge location and identification for power transformers based on multi-sensor fusion[J]. Power System and Clean Energy, 2024, 40(3):22-31.

尚海昆,张冉喆,黄涛,等.基于CEEMDANTQWT方法的变压器局部放电信号降噪[J].电力科学与技术学报,2024(1):272-284.

SHANG Haikun, ZHANG Ranzhe, HUANG Tao, et al. Partial discharge signal denoising based onCEEMDANTQWTmethod for power transformers[J]. Journal of Electric Power Science and Technology, 2024(1):272-284.

唐贵基,李树才,卢盛阳,等.基于CERLMDAN的转子故障诊断[J].动力工程学报,2020,40(9):720-727.

TANG Guiji, LI Shucai, LU Shengyang, et al. Rotor fault diagnosis based onCERLMDAN[J]. Journal of Chinese Society of Power Engineering, 2020, 40(9):720-727.

陈志刚,赵志川,钟新荣,等.基于鲁棒局部均值分解与二阶瞬态提取变换的滚动轴承故障诊断[J].科学技术与工程,2022, 22(1):157-165.

CHEN Zhigang, ZHAO Zhichuan, ZHONG Xinrong, et al. Fault diagnosis of rolling bearing based on robust local mean decomposition and second-order transient-extracting transform[J]. Science Technology and Engineering, 2022, 22(1):157-165.

柯伟,金仲平,吕信策,等.基于RLMD和WSET的变转速下滚动轴承故障诊断[J].机电工程,2022,39(3):300-308.

KE Wei, JIN Zhongping, LYU Xince, et al. Fault diagnosis method of variable speed rolling bearing based on RLMD and WSET[J]. Mechanical & Electrical Engineering Magazine , 2022 , 39(3):300-308.

LU X,ZHU A,SONG Y,et al. Application of improved robust local mean decomposition and multiple disturbance multi-verse optimizer-based MCKD in the diagnosis of multiple rolling element bearing faults[J]. Machines,2022(10):883.

NGOC-LAN HUYNH A,DEO R C,ALI M,et al. Novel short-term solar radiation hybrid model:Long short-term memory network integrated with robust local mean decomposition[J]. Applied Energy,2021(298):117193.

LI Yongbo,SI Shubin,LIU Zhiliang ,et al. Review of local mean decomposition and its application in fault diagnosis of rotating machinery[J]. Journal of Systems Engineering and Electronics, 2019,30(4):799-814.

JIANG Yan,LIU Shuoyu,PENG Liuliu,et al. A novel wind speed prediction method based on robust local mean decomposition, group method of data handling and conditional kernel density estimation[J]. Energy Conversion and Management,2019(200):112099.

YU Kui,LIU Lin,LI Jiuyong,et al. Multi-source causal feature selection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(9):2240-2256.

POWELL G E,PERCIVAL I C. Aspectral entropy method for distinguishing regular and irregular motion of Hamiltonian systems[J]. Journal of Physics A:Mathematical and General,1979,12(11):2053.

HONG Kaixing,HUANG Hai,FU Yaqiong,et al. A vibration measurement system for health monitoring of power transformers[J]. Measurement,2016(93):135-147.

PAUL A,MUKHERJEE D P,DAS P,et al. Improved random forest for classification[J]. IEEE Transactions on Image Processing :A Publication of the IEEE Signal Processing Society,2018,27(8):4012-4024.

BELGIU M,DRĂGUŢ L. Random forest in remote sensing:A review of applications and future directions[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2016(114):24-31.

杨金鑫,廖才波,胡雄,等.基于DGA与TPELightGBM的变压器故障诊断[J].电力科学与技术学报,2024,39(4):70-77.

YANG Jinxin, LIAO Caibo, HU Xiong, et al. Transformer fault diagnosis based on DGA and TPELightGBM[J]. Journal of Electric Power Science and Technology, 2024, 39(4):70-77.

戚沁雅,曹伯仲,安义,等.基于改进Prony算法的配电变压器群励磁涌流多特征综合辨识方法[J].电力科学与技术学报, 2024,39(6):69-78.

QI Qinya, CAO Bozhong, AN Yi, et al. Comprehensive multifeature identification method of magnetizing inrush current in distribution transformers based on improved Prony algorithm[J]. Journal of Electric Power Science and Technology, 2024, 39(6):69-78.

XU Jianfeng,ZHANG Yuanjian,MIAO Duoqian. Three-way confusion matrix for classification:A measure driven view[J]. Information Sciences,2020(507):772-794.

HUANG Guangbin,ZHU Qinyu,SIEW C K. Extreme learning machine:Theory and applications[J]. Neurocomputing,2006,70(1/3):489-501.

ILIEV A,KYURKCHIEV N,MARKOV S. On the approximation of the step function by some sigmoid functions[J]. Mathematics and Computers in Simulation,2017(133):223-234.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of Dissolved Gas in Transformer Oil Based on Optimized VMD-TCN-LSTM

Analysis and Handling of a 110 kV Transformer Differential Protection Trip Incident

Research on Modeling Method for Broadband Transmission Characteristics of Transformer

Research on UHF Partial Discharge Detection Method Based on Grounding Current of Transformer Core

Experimental Research on Mechanical Properties of Copper Wires in Transformer Winding Under Thermal Effects

Related Author

DAI Hao

HU Dong

YANG Tongliang

FU Qiang

YANG Yong

TANG Chao

TAN Weimin

LIU Jun

Related Institution

School of Engineering and Technology, Southwest University

International R&D Center for Smart Grid and New Equipment Technology, Southwest University

College of Electrical and Information Engineering, Hunan University

Institute of Electric Power Science, Guizhou Power Grid Co., Ltd.

School of Electrical Engineering, Guizhou University

⁰