基于改进MFCC和RF的配电网故障电弧声纹识别方法

陈凯; 吴田; 杨莹; 何清; 黎鹏; 普子恒

doi:null

您当前的位置：

首页 >

文章列表页 >

基于改进MFCC和RF的配电网故障电弧声纹识别方法

更新时间：2025-06-18

- 基于改进MFCC和RF的配电网故障电弧声纹识别方法
- Fault Arc Voiceprint Recognition Method in Distribution Network Based on Improved MFCC and RF
- 高压电器 2025年页码：1-12
- 作者机构：
  
  1.三峡大学电气与新能源学院，湖北　宜昌　 443002
  2.国网湖北送变电工程有限公司，武汉　 430063
  3.国网湖北电力科学研究院，武汉　 430015
- 作者简介：
  
  陈凯（2000—），男，硕士研究生，主要从事故障电弧检测与定位技术研究（E-mail：673681917@qq.com）。
  吴田（1983—），男，博士，高级工程师，主要从事电网智能运检和带电作业（E-mail：wutian_08@163.com）。
- 基金信息：
  
  国家自然科学基金资助项目(51807110)
- DOI：
  中图分类号：
- 纸质出版日期：
- 稿件说明：
移动端阅览
陈凯, 吴田, 杨莹, 等. 基于改进MFCC和RF的配电网故障电弧声纹识别方法[J/OL]. 高压电器, 2025,1-12.

CHEN Kai, WU Tian, YANG Ying, et al. Fault Arc Voiceprint Recognition Method in Distribution Network Based on Improved MFCC and RF[J/OL]. High voltage apparatus, 2025, 1-12.
陈凯, 吴田, 杨莹, 等. 基于改进MFCC和RF的配电网故障电弧声纹识别方法[J/OL]. 高压电器, 2025,1-12. DOI：

CHEN Kai, WU Tian, YANG Ying, et al. Fault Arc Voiceprint Recognition Method in Distribution Network Based on Improved MFCC and RF[J/OL]. High voltage apparatus, 2025, 1-12. DOI：

摘要

针对电力系统中配电网线路中的电弧故障检测易发生故障误判的问题，提出了一种基于改进梅尔倒谱系数和随机森林算法的故障电弧声纹识别模型。该模型首先对故障电弧声信号进行分帧加窗处理，提取其梅尔倒谱系数，使用费舍尔比计算特征各维度对区分故障的贡献度，根据贡献度设计出合适的权值对特征向量进行加权降维处理，得到区分性更强的特征向量。最后采用随机森林算法对故障电弧声纹信号进行识别。为了验证该模型的有效性，文中搭建故障电弧试验平台采集故障电弧声信号，对故障电弧燃烧发展过程的声信号时频域进行分析，确定了声信号特征与电弧燃烧程度之间存在相关性，验证了以声信号作为故障电弧检测参量的可行性，并对不同燃烧程度的电弧弧声信号使用故障电弧声纹识别模型进行计算分析。结果表明，基于改进梅尔倒谱系数和随机森林算法的故障电弧声纹识别模型对故障电弧声信号的识别结果符合预期，该系统可为配电网电弧故障检测提供一种新方法。

Abstract

To address the issue of frequent false positives in arc fault detection within power system distribution network lines

a model based on improved Mel-frequency cepstral coefficients (MFCC) and random forest algorithm for arc fault sound pattern recognition is proposed. The model first processes the arc fault sound signals by framing and windowing

then extracts their MFCCs. Using the Fisher ratio

the contribution of each feature dimension to fault differentiation is calculated. Based on these contributions

appropriate weights are designed to perform weighted dimensionality reduction on the feature vectors

yielding more discriminative feature vectors. Finally

the random forest algorithm is employed to recognize the arc fault sound patterns. To validate the effectiveness of this model

an arc fault test platform was constructed to collect arc fault sound signals. Analysis of the time-frequency domain of these signals during the arc fault combustion process established a correlation between the sound signal features and the degree of arc combustion

confirming the feasibility of using sound signals as parameters for arc fault detection. The model was then applied to sound signals from different combustion stages of the arc fault for calculation and analysis. Results indicate that the fault arc sound pattern recognition model

based on improved MFCC and random forest algorithm

achieves expected recognition outcomes. This system offers a novel method for detecting arc faults in distribution networks.

关键词

Keywords

references

盛戈皞 , 钱勇 , 罗林根 , 等 . 面向新型电力系统的电力设备运行维护关键技术及其应用展望 [J ] . 高电压技术 , 2021 , 47 ( 9 ): 3072 - 3084 .

SHENG Gehao , QIAN Yong , LUO Lingen , et al . Key technologies and application prospects for operation and maintenance of power equipment in new type power system [J ] . High Voltage Engineering , 2021 , 47 ( 9 ): 3072 - 3084 .

刘科研 , 董伟杰 , 肖仕武 , 等 . 基于电压数据SVM分类的有源配电网故障判别及定位 [J ] . 电网技术 , 2021 , 45 ( 6 ): 2369 - 2379 .

LIU Keyan , DONG Weijie , XIAO Shiwu , et al . Fault identification and location of active distribution network based on SVM classification of voltage data [J ] . Power System Technology , 2021 , 45 ( 6 ): 2369 - 2379 .

蒋原 , 李擎 , 冯茜 , 等 . 基于BP神经网络的直流电网故障定位与保护方法 [J ] . 高压电器 , 2020 , 56 ( 8 ): 23 - 28 .

JIANG Yuan , LI Qing , FENG Qian , et al . Fault location and protection method for DC power grid based on BP neural network [J ] . High Voltage Apparatus , 2020 , 56 ( 8 ): 23 - 28 .

朱晓红 , 杨伟荣 , 张蓉 , 等 . 基于RNN-LSTM神经网络的小电流接地故障选线方法 [J ] . 高压电器 , 2023 , 59 ( 7 ): 213 - 220 .

ZHU Xiaohong , YANG Weirong , ZHANG Rong , et al . Line selection method of low current grounding fault based on RNN-LSTM neural network [J ] . High Voltage Apparatus , 2023 , 59 ( 7 ): 213 - 220 .

罗晗菁 , 曾祥君 , 喻锟 , 等 . 基于多维波形差异度聚类分析的配电网故障区段定位方法 [J ] . 南方电网技术 , 2024 , 18 ( 6 ): 58 - 68, 97 .

LUO Hanjing , ZENG Xiangjun , YU Kun , et al . Fault section location method for distribution network based on Multi-Dimensional waveform difference clustering analysis [J ] . Southern Power System Technology , 2024 , 18 ( 6 ): 58 - 68, 97 .

秦译为 , 张蓬鹤 , 宋如楠 , 等 . 新型电力系统下电弧故障诊断技术及发展趋势 [J ] . 电测与仪表 , 2024 , 61 ( 2 ): 1 - 9 .

QIN Yiwei , ZHANG Penghe , SONG Runan , et al . Arc fault diagnosis technology and trend of development in novel power system [J ] . Electrical Measurement & Instrumentation , 2024 , 61 ( 2 ): 1 - 9 .

熊庆 , 陈维江 , 汲胜昌 , 等 . 低压直流系统故障电弧特性、检测和定位方法研究进展综述 [J ] . 中国电机工程学报 , 2020 , 40 ( 18 ): 6015 - 6026 .

XIONG Qing , CHEN Weijiang , JI Shengchang , et al . Review of research progress on characteristics, detection and localization approaches of fault arc in low voltage DC system [J ] . Proceedings of the CSEE , 2020 , 40 ( 18 ): 6015 - 6026 .

李松浓 , 晏尧 , 向菲 , 等 . 光伏直流系统故障电弧检测方法研究综述 [J ] . 电测与仪表 , 2024 , 61 ( 2 ): 10 - 16 .

LI Songnong , YAN Yao , XIANG Fei , et al . A comprehensive review on detection method for DC fault arc in photovoltaic system [J ] . Electrical Measurement & Instrumentation , 2024 , 61 ( 2 ): 10 - 16 .

何志鹏 , 李伟林 , 邓云坤 , 等 . 低压交流串联故障电弧辨识方法 [J ] . 电工技术学报 , 2023 , 38 ( 10 ): 2806 - 2817 .

HE Zhipeng , LI Weilin , DENG Yunkun , et al . The detection of series AC arc fault in low-voltage distribution system [J ] . Transactions of China Electrotechnical Society , 2023 , 38 ( 10 ): 2806 - 2817 .

贺胜 , 疏学明 , 胡俊 , 等 . 基于消防大数据的电气火灾风险预测预警方法 [J ] . 清华大学学报(自然科学版) , 2024 , 64 ( 3 ): 478 - 491 .

HE Sheng , SHU Xueming , HU Jun , et al . Prediction and early-warning method of electrical fire risk based on fire-fighting big data [J ] . Journal of Tsinghua University (Science and Technology) , 2024 , 64 ( 03 ): 478 - 491 .

YAO Xiu , LE V , LEE I . Unknown input observer-based series DC arc fault detection in DC microgrids [J ] . IEEE Transactions on Power Electronics , 2022 , 37 ( 4 ): 4708 - 4718 .

LE V , YAO Xiu , MILLER C , et al . Series DC arc fault detection based on ensemble machine learning [J ] . IEEE Transactions on Power Electronics , 2020 , 35 ( 8 ): 7826 - 7839 .

王毅 , 刘黎明 , 李松浓 , 等 . 基于经验小波变换复合熵值与特征融合的故障电弧检测 [J ] . 电网技术 , 2023 , 47 ( 5 ): 1912 - 1919 .

WANG Yi , LIU Liming , LI Songnong , et al . Arc fault detection based on empirical wavelet transform composite entropy and feature fusion [J ] . Power System Technology , 2023 , 47 ( 5 ): 1912 - 1919 .

WANG Yangkun , ZHANG Feng , ZHANG Xueheng , et al . Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network [J ] . IEEE Transactions on Industrial Informatics , 2019 , 15 ( 12 ): 6210 - 6219 .

焦治杰 , 李腾 , 王莉娜 , 等 . 基于卷积神经网络的光伏系统直流串联电弧故障检测 [J ] . 电工电能新技术 , 2019 , 38 ( 7 ): 29 - 34 .

JIAO Zhijie , LI Teng , WANG Lina , et al . DC series arc-fault detection of photovoltaic system based on convolutional neural network [J ] . Advanced Technology of Electrical Engineering and Energy , 2019 , 38 ( 7 ): 29 - 34 .

季坤 , 张晨晨 , 丁国成 , 等 . 粒子群优化算法在电力变压器声纹识别中的应用 [J ] . 沈阳工业大学学报 , 2023 , 45 ( 6 ): 643 - 648 .

JI Kun , ZHANG Chenchen , DING Guocheng , et al . Application of particle swarm optimization algorithm in power transformer voiceprint recognition [J ] . Journal of Shenyang University of Technology , 2023 , 45 ( 6 ): 643 - 648 .

CUI Yao , HUANG Xin , ZHANG Xin . Deep neural network based acoustic pattern recognition system for fault localization application [J ] . Applied Mathematics and Nonlinear Sciences , 2024 , 9 ( 1 ): 01232 .

WANG J , ZHAO Z , ZHU J , et al . Improved support vector machine for voiceprint diagnosis of typical faults in power transformers [J ] . Machines , 2023 , 11 ( 5 ): 539 .

周梦茜 , 唐志国 , 王泽瑞 , 等 . 基于声纹识别系统的局部放电超声信号识别研究 [J ] . 高压电器 , 2022 , 58 ( 9 ): 127 - 133 .

ZHOU Mengqian , TANG Zhiguo , WANG Zerui , et al . Study on ultrasonic signal recognition of partial discharge based on voiceprint recognition system [J ] . High Voltage Apparatus , 2022 , 58 ( 9 ): 127 - 133 .

于达 , 张玮 , 王辉 . 基于LSTM神经网络的油浸式变压器异常声纹诊断方法研究 [J ] . 智慧电力 , 2023 , 51 ( 2 ): 45 - 52 .

YU Da , ZHANG Wei , WANG Hui . Abnormal voiceprint diagnosis method of oil-immersed transformer based on LSTM neural network [J ] . Smart Power , 2023 , 51 ( 2 ): 45 - 52 .

耿琪深 , 王丰华 , 金霄 . 基于Gammatone滤波器倒谱系数与鲸鱼算法优化随机森林的干式变压器机械故障声音诊断 [J ] . 电力自动化设备 , 2020 , 40 ( 8 ): 191 - 196 .

GENG Qishen , WANG Fenghua , JIN Xiao . Mechanical fault sound diagnosis based on GFCC and random forest optimized by whale algorithm for dry type transformer [J ] . Electric Power Automation Equipment , 2020 , 40 ( 8 ): 191 - 196 .

YAO W , XU Y , QIAN Y , et al . A classification system for insulation defect identification of gas-insulated switchgear (GIS), based on voiceprint recognition technology [J ] . Applied Sciences , 2020 , 10 ( 11 ): 3995 .

孙汉文 , 李喆 , 盛戈皞 , 等 . 基于机器学习与卷积神经网络的放电声音识别研究 [J ] . 高压电器 , 2020 , 56 ( 9 ): 107 - 113 .

SUN Hanwen , LI Zhe , SHENG Gehao , et al . Study of discharge sound diagnosis based on machine learning and convolutional neural networks [J ] . High Voltage Apparatus , 2020 , 56 ( 9 ): 107 - 113 .

董哲为 . 基于Fisher融合的含噪声纹特征提取与识别研究 [D ] . 西安 : 长安大学 , 2023 .

DONG Zhewei . Research on features extraction and recognition of noisy voiceprint based on fisher fusion algorithm [D ] . Xi'an : Chang'an University , 2023 .

刘芹 , 彭在兴 , 王颂 , 等 . 基于随机森林算法的断路器分合闸线圈故障电流曲线识别 [J ] . 高压电器 , 2019 , 55 ( 7 ): 93 - 100 .

LIU Qin , PENG Zaixing , WANG Song , et al . Fault current curves identification of circuit breaker opening/closing coil based on random forest algorithm [J ] . High Voltage Apparatus , 2019 , 55 ( 7 ): 93 - 100 .

赵洲峰 , 赵志勇 , 邹君文 , 等 . 基于声振信号组合特征的随机森林模型及其在绝缘子故障识别中的应用 [J ] . 广东电力 , 2022 , 35 ( 12 ): 93 - 100 .

ZHAO Zhoufeng , ZHAO Zhiyong , ZOU Junwen , et al . A random forest model based on combination features of acoustic-vibration signals and its application in insulator fault identification [J ] . Guangdong Electric Power , 2022 , 35 ( 12 ): 93 - 100 .

王兰兰 , 朱捷 , 周正平 , 等 . 基于随机森林的滚动轴承故障辨识方法研究 [J ] . 机电工程 , 2021 , 38 ( 12 ): 1599 - 1604 .

WANG Lanlan , ZHU Jie , ZHOU Zhengping , et al . Fault identification method of rolling bearing based on random forest [J ] . Journal of Mechanical & Electrical Engineering , 2021 , 38 ( 12 ): 1599 - 1604 .

高电压实验技术　第1部分：一般定义及实验　要求：GB/T 16927.1—2011 [S ] . 2011 .

High-voltage test techniques. Part 1: General definitions and test requirements: GB/T 16927.1—2011 [S ] . 2011 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

考虑柴油机测功系统接入的配电网韧性提升方法研究

基于融合特征和残差神经网络的10 kV高压断路器机械故障声纹识别方法

自取电的电缆故障类型及故障分段定位的研究

基于矢量空间状态优化的GIS机械故障检测方法

配电网电容电流的测量方法分析