[1]曹 健,陈杉杉,包锡军,等.基于声谱图与改进残差网络的断路器故障诊断研究[J].机械与电子,2025,(03):9-15.
　CAO Jian,CHEN Shanshan,BAO Xijun,et al.Research on Fault Diagnosis of Circuit Breakers Based on Spectrograms and Improved Residual Networks[J].Machinery & Electronics,2025,(03):9-15.
点击复制

基于声谱图与改进残差网络的断路器故障诊断研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2025年03期
页码:
9-15
栏目:
研究与设计
出版日期:
2025-03-25

文章信息/Info

Title:
Research on Fault Diagnosis of Circuit Breakers Based on Spectrograms and Improved Residual Networks
文章编号:
1001-2257 ( 2025 ) 03-0009-07
作者:
曹 健; 陈杉杉; 包锡军; 从乐瑶; 周 菁
国网江苏省电力有限公司无锡供电分公司,江苏 无锡 214061
Author(s):
CAO Jian ;  CHEN Shanshan ;  BAO Xijun ;  CONG Leyao ;  ZHOU Jing
( Wuxi Power Supply Branch , State Grid Jiangsu Electric Power Co. , Ltd. , Wuxi 214061 , China )
关键词:
断路器; 声纹识别; 声谱图特征
Keywords:
circuit breakers ;  voiceprint recognition ;  spectrogram characteristics
分类号:
TM561
文献标志码:
A
摘要:
针对传统开关柜故障监测装置效果不显著,难以及时发现设备运行时的缺陷,以及现有声纹识别故障诊断方法应用于断路器故障诊断中存在识别准确率低的问题,提出了基于声谱图特征的 SE-ResNet深度学习神经网络识别模型。首先对声音信号进行声谱图( Spectrogram )特征提取,保留了声音信号的细节,提取出音频信号中的瞬态特性和非稳态特性。随后通过识别模型进行故障诊断。通过实验,针对不同模型以及不同特征提取方式进行比较,验证了所提方法的有效性和优越性。
Abstract:
The efficacy of conventional switchgear fault monitoring devices is negligible , posing chal-enges in rapidly identifying flaws during equipment operation.The current methods used for diagnosing faults in circuit breakers using voiceprint recognition have a low level of accuracy in identifying the faults. This research presents a recognition model for deep learning neural networks called SE-ResNet.The model is based on spectrogram characteristics.Initially , spectrogram features are derived from the sound signals , retaining the intricacies and capturing the transient and non-constant attributes of the audio signals. Afterwards , fault diagnosis is conducted using the recognition model.The proposed strategy is proven to be successful and superior through experimental validation that compares various models and feature extraction approaches.

参考文献/References:

[ 1 ] 赵磊,刘鹏,冯汝明,等 . 高压断路器分合闸故障诊断与分析[ J ] . 黑龙江电力, 2024 , 46 ( 1 ): 61-64 , 76.

[ 2 ] 尹子会,孟延辉,赵智龙,等 . 声振信号构造 CNN 特征矩阵的断路器储能机构故障诊断方法[ J ] . 高压电器,2023 , 59 ( 9 ): 242-249.
[ 3 ] 盖曜麟,葛丽娟,郭懿中,等 . 基于改进 SVM 算法的高压断路器故障诊断[ J ] . 高压电器, 2022 , 58 ( 12 ): 14-20.
[ 4 ] ABULIZI J , CHEN Z , LIU P , et al.Research on voiceprint recognition of power transformer anomalies using gated recurrent unit [ C ] ∥2021 Power System and Green Energy Conference ( PSGEC ) .New York : IEEE , 2021 : 743-747.
[ 5 ] 黄新波,王宁,朱永灿,等 . 基于 RST SOM 的高压断路器故障诊断[ J ]. 高压电器, 2020 , 56 ( 3 ): 1-8.
[ 6 ] 宋长铭,李岩,王飞,等 . 基于 Transformer 的有载分接开关故障诊断研究[ J ] . 自动化与仪器仪表, 2024 ( 3 ):26-29 , 34.
[ 7 ] 刘雪芹,力刚,葛强 . 基于声纹监测技术的大型泵站机组振动特性研究[ J ] . 中国农村水利水电,2024 ( 2 ):103-108.
[ 8 ] 夏小飞,易林,饶夏锦,等 . 基于声学指纹分析的高压断路器机械故障诊断方法[ J ] . 高压电器, 2021 , 57 ( 10 ):66-76.
[ 9 ] 丰硕,汪诗怡 . 基于声纹识别的变压器局部放电在线监测系统[ J ] . 电器工业, 2024 ( 4 ): 15-19 , 70.
?10 ] 王玉伟,余俊龙,彭平,等 . 基于多模型融合的变压器故障在线 检测 方法 [ J ] . 高电压技术,2023 , 49 ( 8 ):3415-3424.
[ 11 ] WAN S T , DONG F , ZHANG X , et al.Fault voiceprint signal diagnosis method of power transformer based on mixup data enhancement [ J ] .Sensors , 2023 , 23 ( 6 ): 3341.
[ 12 ] DONG Y Q , WANG D L , PAN Y , et al.Fault detection of in-service bridge expansion joint based on voiceprint recognition [ J ] .Structural control and health monitoring , 2024 : 1270912.
[ 13 ] 赵东豪,张继国,石雷,等 . 基于声信号特征声谱图的变压器状态监测与故障诊断[ J ] . 电气自动化, 2023 ,45 ( 1 ): 106-108 , 112.
[ 14 ] 彭威,李晶,刘卫东,等 .AE 声谱图特征的转子碰摩故障识别方法研究[ J ] . 振动工程学报, 2019 , 32 ( 6 ):1094-1103.
[ 15 ] 倪黎,邹卫军 . 基于 SE 模块改进 Xception 的动物种类识别[ J ] . 导航与控制, 2020 , 19 ( 2 ): 106-111.
[ 16 ] CHEN J B , CHEN T L , XIAO B , et al.SE-ECGNet : multi-scale SE-Net for multi-lead ECG data [ C ] ∥ 2020 Computing in Cardiology.New York : IEEE , 2020 : 1-4.
[ 17 ] ZHAO X J , WANG D L.Analyzing noise robustness of MFCC and GFCC features in speaker identification [ C ] ∥2013 IEEE international conference on acoustics , speech and signal processing.New York : IEEE , 2013 : 7204-7208.
[ 18 ] GENG Q S , WANG F H , ZHOU D X.Mechanical fault diagnosis of power transformer by GFCC time-frequency map of acoustic signal and convolutional neural network [ C ] ∥2019 IEEE Sustainable Power and Energy Conference ( iSPEC ) .New York : IEEE , 2019 : 2106-2110.

相似文献/References:

[1]杨 晨,刘志远,陆洪建,等.基于智能继电保护技术的超高压断路器控制研究[J].机械与电子,2023,41(08):45.
　YANG Chen,LIU Zhiyuan,LU Hongjian,et al.Research on Control of UHV Circuit Breaker Based on Intelligent Relay Protection Technology[J].Machinery & Electronics,2023,41(03):45.

备注/Memo

备注/Memo:
收稿日期: 2024-06-28
基金项目:国网无锡供电公司科技项目( SGJSWX00KJJS2312307 )
作者简介:曹 健 ( 1984- ),男,江苏宿迁人,高级工程师,研究方向为变电运维技术。
更新日期/Last Update: 2025-04-07