基于CNN的平波电抗器声纹模式识别方法A voiceprint pattern recognition method of smoothing reactor based on CNN
胡锦根,石明垒,焦晨骅,沈正元
HU Jingen,SHI Minglei,JIAO Chenhua,SHEN Zhengyuan
摘要(Abstract)：
为实现对平波电抗器运行状态的准确识别，引入一种基于CNN（卷积神经网络）的深度学习方法，建立了使用Mel时频谱的电抗器绕组声纹模式识别模型。以干式平波电抗器作为实验对象采集声音信号，使用Mel滤波器方法将采集到的声音信号转化为时频谱图，以不同的工况类型作为数据集的标签，基于CNN算法识别不同信号所对应的工况类型。结果表明，CNN可用于干式平波电抗器声纹模式的准确识别，优化后的神经网络对正弦激励、谐波激励和直流偏磁激励下的声纹信号识别准确率高达98.4%。研究结果为实现电网信号的智能化检测提供了潜在的技术方案。
In order to accurately identify the operating condition of the smoothing reactor, a deep learning method based on CNN(convolutional neural network) is introduced. A voiceprint pattern recognition model for reactor windings using Mel spectrogram is developed. The sound signals are collected using dry smoothing reactors as the experimental object. The Mel filter method is used to convert the collected sound signals into a spectrogram with different working conditions used as the labels of the data set. The CNN algorithm is used to identify the working conditions corresponding to the different signals. The results show that CNN can be used to accurately identify dry voiceprint patterns of smoothing reactors. The optimized neural network can achieve an accuracy of 98.4% in recognition of voiceprint signals under sinusoidal excitation, harmonic excitation and DC bias excitation. The research results provide a potential technical solution for realizing intelligent detection of power grid signals.
关键词(KeyWords)：
平波电抗器;运行状态;绕组;Mel时频谱;卷积神经网络
smoothing reactor;operating condition;winding;Mel spectrogram;convolutional neural network
基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211MR20004U）
作者(Author):
胡锦根,石明垒,焦晨骅,沈正元
HU Jingen,SHI Minglei,JIAO Chenhua,SHEN Zhengyuan
DOI: 10.19585/j.zjdl.202303011
参考文献(References)：
- [1]李宁，田冬梅，单大鹏，等.城市变电站噪声分析及降噪措施探讨[J].高压电器，2015,51(1):139-144.LI Ning,TIAN Dongmei,SHAN Dapeng,et al.Analysis and discussion on the noise arised from substation in city[J].High Voltage Apparatus,2015,51(1):139-144.
- [2] LAHN L,WANG C Y,ALLWARDT A,et al.Improved transformer noise behavior by optimized laser domain refinement at ThyssenKrupp electrical steel[J].IEEE Transactions on Magnetics,2012,48(4):1453-1456.
- [3]刘云鹏，罗世豪，王博闻，等.基于Mel时频谱-卷积神经网络的变压器铁芯夹件松动故障声纹模式识别[J].华北电力大学学报（自然科学版），2020,47(6):52-60.LIU Yunpeng,LUO Shihao,WANG Bowen,et al.Voiceprint recognition of transformer core clamp looseness fault by Mel-spectrum and convolutional neural network[J].Journal of North China Electric Power University(Natural Science Edition),2020,47(6):52-60.
- [4] KORNATOWSKI E,BANASZAK S. Diagnostics of a transformer’s active part with complementary FRA and VM measurements[J].IEEE Transactions on Power Delivery,2014,29(3):1398-1406.
- [5] MIZOKAMI M,KUROSAKI Y.Noise variation by compressive stress on the model core of power transformers[J].Journal of Magnetism and Magnetic Materials,2015,381:208-214.
- [6]王丰华，王邵菁，陈颂，等.基于改进MFCC和VQ的变压器声纹识别模型[J].中国电机工程学报，2017,37(5):1535-1542.WANG Fenghua,WANG Shaojing,CHEN Song,et al.Voiceprint recognition model of power transformers based on improved MFCC and VQ[J]. Proceedings of the CSEE,2017,37(5):1535-1542.
- [7]舒畅，金潇，李自品，等.基于CEEMDAN的配电变压器放电故障噪声诊断方法[J].高电压技术，2018,44(8):2603-2611.SHU Chang,JIN Xiao,LI Zipin,et al. Noise diagnosis method of distribution transformer discharge fault based on CEEMDAN[J]. High Voltage Engineering,2018,44(8):2603-2611.
- [8]张重远，罗世豪，岳浩天，等.基于Mel时频谱-卷积神经网络的变压器铁芯声纹模式识别方法[J].高电压技术，2020,46(2):413-423.ZHANG Zhongyuan,LUO Shihao,YUE Haotian,et al.Pattern recognition of acoustic signals of transformer core based on Mel-spectrum and CNN[J].High Voltage Engineering,2020,46(2):413-423.
- [9]宋新伟.干式空心电抗器振动特性研究[D].合肥：合肥工业大学，2018.SONG Xinwei. Research on vibration characteristics of dry-type air-core reactor[D]. Hefei:Hefei University of Technology,2018.
- [10]段小木.电力变压器振动发生传播机理及自适应有源噪声控制[D].济南：山东大学，2019.DUAN Xiaomu.Study on vibration generation and transmission mechanism of power transformer and adaptive active noise control[D].Jinan:Shandong University,2019.
- [11] KERSTA L G. Voiceprint-identification infallibility[J].The Journal of the Acoustical Society of America,1962,34(12):1978.
- [12] SCHMIDHUBER J.Deep learning in neural networks[J].Neural Networks,2015,61(C):85-117.
- [13]李彦冬，郝宗波，雷航.卷积神经网络研究综述[J].计算机应用，2016,36(9):2508-2515.LI Yandong,HAO Zongbo,LEI Hang.Survey of convolutional neural network[J]. Journal of Computer Applications,2016,36(9):2508-2515.
- [14] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM,2017,60(6):84-90.