Research on Transformer Noise Suppression Based on Redundant Convolutional Encoder Decoder

doi:10.11930/j.issn.1004-9649.202203065

Abstract

Abstract: The acoustic signal generated during the operation of the transformer is an important basis for evaluating the operation status of the transformer and the noise level of the substation. A transformer noise suppression method based on redundant convolutional codec (RCED) network is proposed. The time-frequency characteristics of clean acoustic signal and noisy signal are obtained by using short-time Fourier transform, and the noise reduction model of transformer acoustic signal is constructed. The noise signal of converter transformer in a converter station is tested and verified. The results show that the proposed model has good noise reduction effect, and the proposed method has reference significance for the online monitoring system of transformer voiceprint vibration and the accurate detection of substation noise.

Key words: power transformer, acoustic signal preprocessing, redundant convolutional encoder decoder, signal-to-noise separation

XIN Quanjin, LI Xiaohua, YANG Yi, LI Juncong, XIA Nenghong. Research on Transformer Noise Suppression Based on Redundant Convolutional Encoder Decoder[J]. Electric Power, 2023, 56(4): 112-118.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202203065

https://www.electricpower.com.cn/EN/Y2023/V56/I4/112

References

[1] 卢梦瑶, 李国勇, 陈静, 等. 基于半消声环境声学测试平台的干式配电变压器噪声特性负载因素影响研究[J]. 智慧电力, 2020, 48(11): 108–112
LU Mengyao, LI Guoyong, CHEN Jing, et al. Influence of load factors on dry-type distribution transformer noise level based on semi-anechoic environment acoustic test platform[J]. Smart Power, 2020, 48(11): 108–112
[2] 杜一明. 基于声信号的变压器故障诊断系统研究[D]. 武汉: 华中科技大学, 2013.
DU Yiming. Research on fault diagnosis system for power transformer based on audio signal[D]. Wuhan: Huazhong University of Science and Technology, 2013.
[3] 马春雷, 谢荣斌, 赵莉华, 等. 变压器可听声信号特征分析[J]. 电力大数据, 2018, 21(2): 18–26
MA Chunlei, XIE Rongbin, ZHAO Lihua, et al. Characteristic analysis of transformer audible acoustic signals[J]. Power Systems and Big Data, 2018, 21(2): 18–26
[4] 黄长铎. 变压器故障信号去噪方法的研究[J]. 装备制造技术, 2010(9): 29–30
HUANG Changduo. Study on de-noising methods of transformer fault signal[J]. Equipment Manufacturing Technology, 2010(9): 29–30
[5] 彭鹏, 吴晓文, 陈炜, 等. 基于小波分解与谱减法的变压器噪声测量预处理方法[J]. 高压电器, 2019, 55(11): 177–183
PENG Peng, WU Xiaowen, CHEN Wei, et al. Preprocessing method for transformer noise measurement based on wavelet packet decomposition and spectral subtraction algorithm[J]. High Voltage Apparatus, 2019, 55(11): 177–183
[6] 周东旭, 王丰华, 党晓婧, 等. 基于稀疏表示理论的特高压交流变压器声信号盲分离研究[J]. 电网技术, 2020, 44(8): 3139–3148
ZHOU Dongxu, WANG Fenghua, DANG Xiaojing, et al. Blind separation of UHV power transformer acoustic signal preprocessing based on sparse representation theory[J]. Power System Technology, 2020, 44(8): 3139–3148
[7] 杨鹏, 应黎明, 陈敏, 等. ANC系统次级通道背景噪声的处理方法[J]. 电测与仪表, 2017, 54(8): 99–103
YANG Peng, YING Liming, CHEN Min, et al. The processing method of background noise in secondary path identification of ANC system[J]. Electrical Measurement & Instrumentation, 2017, 54(8): 99–103
[8] 彭任华, 郑成诗, 丁茫, 等. 高压变电站噪声分离算法及其应用[J]. 高电压技术, 2015, 41(5): 1680–1686
PENG Renhua, ZHENG Chengshi, DING Mang, et al. Separation algorithm of the noise in high voltage substation and its application[J]. High Voltage Engineering, 2015, 41(5): 1680–1686
[9] 宋威, 林建维, 周方泽, 等. 基于改进降噪自编码器的风机轴承故障诊断方法[J]. 电力系统保护与控制, 2022, 50(10): 61–68
SONG Wei, LIN Jianwei, ZHOU Fangze, et al. Wind turbine bearing fault diagnosis method based on an improved denoising AutoEncoder[J]. Power System Protection and Control, 2022, 50(10): 61–68
[10] WANG Y X, WANG D L. Towards scaling up classification-based speech separation[J]. IEEE Transactions on Audio, Speech, and Language Processing, 2013, 21(7): 1381–1390.
[11] 程林, 柯贤波, 霍超, 等. 基于Hopfield神经网络的供电网黑启动分区方案计算方法[J]. 智慧电力, 2022, 50(3): 72–79
CHENG Lin, KE Xianbo, HUO Chao, et al. Calculation method of black-start zone partitioning scheme for power supply network based on hopfield neural network[J]. Smart Power, 2022, 50(3): 72–79
[12] 张宸滔, 郑永康, 卢继平, 等. 基于图神经网络的智能变电站二次回路故障定位研究[J]. 电力系统保护与控制, 2022, 50(11): 81–90
ZHANG Chentao, ZHENG Yongkang, LU Jiping, et al. Fault location of secondary circuits in a smart substation based on a graph neural network[J]. Power System Protection and Control, 2022, 50(11): 81–90
[13] 刘赫, 皮俊波, 宋鹏程, 等. 基于混合神经网络的电力调度文本事件抽取方法[J]. 中国电力, 2022, 55(9): 105–110, 120
LIU He, PI Junbo, SONG Pengcheng, et al. An event extraction method for power dispatching text based on hybrid neural network[J]. Electric Power, 2022, 55(9): 105–110, 120
[14] 徐浩, 刘利强, 吕超. 基于迁移学习的配电网内部过电压识别方法[J]. 中国电力, 2021, 54(8): 52–59
XU Hao, LIU Liqiang, LV Chao. An internal overvoltage identification method for distribution network based on transfer learning[J]. Electric Power, 2021, 54(8): 52–59
[15] EPHRAIM Y, MALAH D. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1985, 33(2): 443–445.
[16] 张允耀, 黄鹤鸣, 张会云. 复杂噪声环境下语音识别研究[J]. 计算机与现代化, 2021(9): 68–74
ZHANG Yunyao, HUANG Heming, ZHANG Huiyun. Speech recognition in complex noise environment[J]. Computer and Modernization, 2021(9): 68–74
[17] 马宏彬, 何金良, 陈青恒. 500 kV单相电力变压器的振动与噪声波形分析[J]. 高电压技术, 2008, 34(8): 1599–1604
MA Hongbin, HE Jinliang, CHEN Qingheng. Vibration and sound waveform analysis of 500 kV single phase power transformer[J]. High Voltage Engineering, 2008, 34(8): 1599–1604
[18] 陈青恒, 马宏彬, 何金良. 直流偏磁引起的500 kV电力变压器振动和噪声的现场测量与分析[J]. 高压电器, 2009, 45(3): 93–96
CHEN Qingheng, MA Hongbin, HE Jinliang. Field monitoring and analysis on vibration and noise of 500 kV electrical transformer under DC current biasing[J]. High Voltage Apparatus, 2009, 45(3): 93–96
[19] 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): 1535–1543
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): 1535–1543
[20] PARK S R, LEE J W. A fully convolutional neural network for speech enhancement[C]//Interspeech 2017. ISCA: ISCA, 2017.
[21] 时文华, 张雄伟, 邹霞, 等. 利用深度全卷积编解码网络的单通道语音增强[J]. 信号处理, 2019, 35(4): 631–640
SHI Wenhua, ZHANG Xiongwei, ZOU Xia, et al. Single channel speech enhancement based on deep fully convolutional encoder-decoder neural network[J]. Journal of Signal Processing, 2019, 35(4): 631–640
[22] 白爽冉. 基于深度神经网络的有监督语音增强研究[D]. 济南: 山东大学, 2019.
BAI Shuangran. Research on supervised speech enhancement based on deep neural networks[D]. Jinan: Shandong University, 2019.
[23] 潘楠, 伍星, 迟毅林, 等. 欠定盲解卷积用于滚动轴承复合故障声学诊断[J]. 振动测试与诊断, 2013, 33(2): 284–289, 341
PAN Nan, WU Xing, CHI Yilin, et al. Undertermined blind deconvolution in bearing combined failure detection acoustical diagnosis[J]. Journal of Vibration, Measurement & Diagnosis, 2013, 33(2): 284–289, 341
[24] LIU L, HE J L, PALM G. Effects of phase on the perception of intervocalic stop consonants[J]. Speech Communication, 1997, 22(4): 403–417.
[25] 汪欣, 毛东兴, 李晓东. 基于声信号和一维卷积神经网络的电机故障诊断研究[J]. 噪声与振动控制, 2021, 41(2): 125–129
WANG Xin, MAO Dongxing, LI Xiaodong. Motor fault diagnosis using microphones and one-dimensional convolutional neural network[J]. Noise and Vibration Control, 2021, 41(2): 125–129