基于小波散射网络-贝叶斯优化门控循环单元的电力变压器声纹识别方法

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1882 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract This paper proposes a voiceprint recognition method for power transformers with small-scale samples based on wavelet scattering network-Bayesian optimized gated recurrent unit (GRU). Firstly, in order to filter out interference components and improve the accuracy of voiceprint recognition, the original signal extracted from the transformer is subjected to blind source separation through empirical wavelet transform (EWT) and fast independent component analysis algorithm (FastICA), resulting in the voiceprint signal of the transformer itself. Then, the feature vector of the voiceprint signal is extracted using the wavelet scattering network as the input of the voiceprint recognition model, and a GRU is applied as the classifier. To improve the recognition accuracy, Bayesian algorithm is utilized to optimize the hyperparameters of GRU layers and initial learning rate. The experimental results show that in the case of small sample size, compared with the commonly used voiceprint time-frequency spectrum and deep convolutional neural network, the model constructed in this paper converges faster and the recognition accuracy increases, significantly improving its performance.

Key words： power transformer voiceprint blind source separation wavelet scattering network gated recurrent unit (GRU)

Received: 12 April 2024

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	HU Ruizhe
	YANG Xiaofeng

Cite this article:

HU Ruizhe,YANG Xiaofeng. The voiceprint recognition method for power transformers based on wavelet scattering network-Bayesian optimized gated recurrent unit[J]. Electrical Engineering, 2024, 25(8): 35-40.

URL:

http://dqjs.cesmedia.cn/EN/Y2024/V25/I8/35

[1] 吴书煜, 汲胜昌, 祝令瑜, 等. 基于多重信息分解与时变权重组合的换流变压器振动状态参量综合预测方法[J]. 中国电机工程学报, 2020, 40(23): 7792-7805.
[2] 王淼, 杨晓峰, 李世翔, 等. 城市轨道交通直流自耦变压器牵引供电系统故障保护研究[J]. 电工技术学报, 2022, 37(4): 976-989.
[3] 张立石, 梁得亮, 刘桦, 等. 基于小波变换与逻辑斯蒂回归的混合式配电变压器故障辨识[J]. 电工技术学报, 2021, 36(增刊2): 467-476.
[4] 李典阳, 张育杰, 冯健, 等. 变压器故障样本多维诊断及结果可信度分析[J]. 电工技术学报, 2022, 37(3): 667-675.
[5] 杨戈辉, 赵桐浠, 姚鑫, 等. 基于健康指数和非等间隔灰色预测的重载铁路牵引变压器状态评估方法[J]. 电气技术, 2023, 24(11): 10-17.
[6] 齐子豪, 仝杰, 张中浩, 等. 基于多粒度知识特征和Transformer网络的电力变压器故障声纹辨识方法[J/OL].中国电机工程学报, 1-13[2024-05-17]. http://kns.cnki.net/kcms/detail/11.2107.TM.20231204.1422.004.html.
[7] 卢宇飞, 林建新. 基于图像特征筛选与融合网络的电力系统动态稳定评估[J]. 电气技术, 2023, 24(12): 1-6.
[8] 杨思莹, 王松, 陈志豪, 等. 基于优化算法的变压器绕组等效电路建模[J]. 电气技术, 2023, 24(8): 29-36, 49.
[9] 何安明, 赵鑫, 吴立刚, 等. 基于双向长短期记忆网络的区域电网新能源消纳预测算法[J]. 电气技术, 2023, 24(3): 23-30.
[10] 杨思莹, 王松, 杨丰野, 等. 基于增量网络法的变压器绕组等效电路参数灵敏度分析[J]. 电气技术, 2023, 24(3): 9-15, 22.
[11] 钱国超, 王丰华, 王劭菁, 等. 大型变压器绕组振动频响特性的试验研究[J]. 高电压技术, 2018, 44(3): 821-826.
[12] 赵莉华, 丰遥, 谢荣斌, 等. 基于交叉小波的变压器振动信号幅频特征量提取方法[J]. 高电压技术, 2019, 45(2): 505-511.
[13] 王荣昊, 李喆, 孙正, 等. 基于FISVDD与GRU的变压器声纹识别技术[J]. 高电压技术, 2022, 48(11): 4546-4556.
[14] 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.
[15] 刘云鹏, 王博闻, 岳浩天, 等. 基于50Hz倍频倒谱系数与门控循环单元的变压器偏磁声纹识别[J]. 中国电机工程学报, 2020, 40(14): 4681-4694.
[16] 张占龙, 肖睿, 武雍烨, 等. 换流变压器振动信号多层次特征提取模型研究[J]. 中国电机工程学报, 2021, 41(20): 7093-7104.
[17] 朱叶叶, 汲胜昌, 张凡, 等. 电力变压器振动产生机理及影响因素研究[J]. 西安交通大学学报, 2015, 49(6): 115-125.
[18] 顾天易. 变压器铁芯故障诊断方法研究[J]. 现代工业经济和信息化, 2023, 13(5): 308-312.
[19] 靳铭凯, 郭鹏鸿, 陈维江, 等. 磁场-结构场双向耦合作用对变压器绕组轴向振动过程的影响[J]. 高电压技术, 2023, 49(8): 3296-3304.
[20] 张凡, 吴书煜, 徐征宇, 等. 变压器绕组非线性动力学模型及多次短路冲击下的振动特征[J]. 高电压技术, 2022, 48(12): 4882-4892.
[21] 赵若妤, 马宏忠, 魏旭, 等. 基于EWT及多尺度形态谱的高压并联电抗器故障诊断研究[J]. 电力系统保护与控制, 2020, 48(17): 68-75.
[22] BARHATTE A S, GHONGADE R, TEKALE S V.Noise analysis of ECG signal using fast ICA[C]//2016 Conference on Advances in Signal Processing (CASP), Pune, India, 2016: 118-122.
[23] MALLAT S.Group invariant scattering[J]. Communi- cations on Pure and Applied Mathematics, 2012, 65(10): 1331-1398.
[24] ANDEN J, MALLAT S.Deep scattering spectrum[J]. IEEE Transactions on Signal Processing, 2014, 62(16): 4114-4128.
[25] XIAO Yan, CHEN Yiyun, WANG Qian.Robust bluetooth RF-fingerprint identifier using wavelet scattering network[C]//2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), Beijing, China, 2023: 1-5.
[26] 全睿, 刘品, 张键, 等. 基于RSN-GRU融合网络的锂电池荷电状态估计[J]. 华中科技大学学报(自然科学版), 2024, 52(7): 76-82.
[27] 毕贵红, 鲍童语, 陈臣鹏, 等. 基于混合分解多尺度时频图和Res-GRU-AT的电能质量复合扰动识别[J]. 电力系统保护与控制, 2024, 52(4): 12-25.