A Review of Research on Voiceprint Fault Diagnosis of Transformers

GONG Wenjie; LIN Guosong; WEI Xiaoguang

doi:10.11999/JEIT251076

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2025 >

GONG Wenjie, LIN Guosong, WEI Xiaoguang. A Review of Research on Voiceprint Fault Diagnosis of Transformers[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251076

Citation:

GONG Wenjie, LIN Guosong, WEI Xiaoguang. A Review of Research on Voiceprint Fault Diagnosis of Transformers[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251076

GONG Wenjie, LIN Guosong, WEI Xiaoguang. A Review of Research on Voiceprint Fault Diagnosis of Transformers[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251076

Citation:

GONG Wenjie, LIN Guosong, WEI Xiaoguang. A Review of Research on Voiceprint Fault Diagnosis of Transformers[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251076

PDF( 7152 KB)

A Review of Research on Voiceprint Fault Diagnosis of Transformers

doi: 10.11999/JEIT251076 cstr: 32379.14.JEIT251076

School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China

Funds: The National Natural Science Foundation of China(52307143)

Received Date: 2025-10-11
Accepted Date: 2025-12-29
Rev Recd Date: 2025-12-24

Available Online: 2026-01-12

Abstract

Abstract

Significance Voiceprint fault diagnosis of transformers has become an active research area for ensuring the safe and reliable operation of power systems. Traditional monitoring methods, such as dissolved gas analysis, infrared temperature measurement, and online partial discharge monitoring, exhibit limited real-time capability and rely heavily on expert experience. These limitations hinder effective detection of early-stage faults. Voiceprint fault diagnosis captures operational voiceprint signals from transformers and enables non-contact monitoring for early anomaly warning. This approach offers advantages in real-time performance, sensitivity, and fault coverage. This review systematically traces the technological evolution from traditional signal analysis to deep learning and compares the advantages, limitations, and application scenarios of different models across multiple dimensions. Key challenges are identified, including limited robustness to noise and imbalanced datasets. Potential research directions are proposed, including integration of physical mechanisms with data-driven methods and improvement of diagnostic transparency and interpretability. These analyses provide theoretical support and practical guidance for promoting the transition of voiceprint fault diagnosis from laboratory research to engineering applications. Progress Research on voiceprint fault diagnosis of transformers has progressed from traditional signal analysis to an intelligent recognition paradigm based on deep learning, reflecting a clear technological evolution. A bibliometric analysis of 188 papers from the CNKI and Web of Science databases shows that annual publications remained at 1–10 papers between 1997 and 2020, corresponding to an exploratory stage. Studies during this period focused mainly on fundamental voiceprint signal processing methods, including acoustic wave detection, wavelet transform, and Empirical Mode Decomposition (EMD). After 2020, Variational Modal Decomposition (VMD), Mel spectrum, and Mel Frequency Cepstral Coefficient (MFCC) were gradually applied to voiceprint feature extraction. Since 2021, publication output has increased rapidly and reached a historical peak in 2023. This growth was driven by advances in image and speech processing technologies. Early studies emphasized time-domain and frequency-domain analysis of voiceprint signals. Recent research increasingly converts voiceprint signals into two-dimensional time–frequency spectrogram representations. Model architectures have evolved from single-channel feature inputs with single-model outputs to complex frameworks with multi-channel feature extraction and multi-model fusion. Classical machine learning models, including Gaussian Mixture Model (GMM), Support Vector Machine (SVM), Random Forest (RF), and Back Propagation Neural Network (BPNN), form the foundation of voiceprint fault diagnosis but are limited in handling high-dimensional features. Deep learning models, such as Convolutional Neural Network (CNN), Residual Neural Network (ResNet), Recurrent Neural Network (RNN), and Transformer, demonstrate advantages in automatic feature extraction and complex pattern recognition, although they require substantial computational resources. Conclusions This review summarizes the technological development of transformer voiceprint fault diagnosis from machine learning to deep learning. Although deep learning methods achieve high recognition accuracy for complex voiceprint signals, five major challenges remain. These challenges include limited robustness to noise in non-stationary environments, severe data imbalance caused by scarce fault samples, the black-box nature of deep learning models, fragmented evaluation systems resulting from inconsistent data acquisition standards, and insufficient cross-modal fusion of multi-source data. Sensitivity to environmental noise limits diagnostic performance under varying operating conditions. Data imbalance reduces recognition accuracy for rare fault types. Limited interpretability restricts fault mechanism analysis and diagnostic credibility. Inconsistent sensor placement and sampling parameters lead to poor comparability across datasets. Single-modal voiceprint analysis restricts effective utilization of complementary information from other data sources. Addressing these challenges is essential for advancing voiceprint fault diagnosis from laboratory validation to field deployment. Prospects Future research should focus on five directions. First, noise-robust voiceprint feature extraction methods based on physical mechanisms should be developed to address non-stationary interference in complex operating environments. Second, the lack of real-world fault data should be alleviated by constructing electromagnetic field–structural mechanics–acoustic coupling models of transformers to generate high-fidelity voiceprint fault samples, while unsupervised clustering methods should be applied to improve annotation efficiency and quality. Third, explainable deep learning architectures for voiceprint fault diagnosis that incorporate physical mechanisms should be designed. Attention mechanisms combined with SHapley Additive exPlanations, Grad-CAM, and physical equations can support process-level and post hoc interpretation of diagnostic results. Fourth, industry-wide collaboration is required to establish standardized voiceprint data acquisition protocols, benchmark datasets, and unified evaluation systems. Fifth, cross-modal fusion models based on multi-channel and multi-feature analysis should be developed to enable integrated transformer fault diagnosis through comprehensive utilization of multi-source information.
- Transformer,
- Voiceprint recognition,
- Fault diagnosis,
- Deep learning

FullText(HTML)

References(75)

References

[1]	ZHU Yongcan, GUO Zhenyan, ZHAN Xiaoxuan, et al. Research on transformer fault diagnosis models with feature extraction[J]. Review of Scientific Instruments, 2024, 95(11): 115109. doi: 10.1063/5.0225204.
[2]	马宏忠, 李楠, 杨启帆, 等. 基于多特征声纹图谱的变压器绕组松动在线故障诊断方法[J]. 电机与控制学报, 2023, 27(5): 76–87. doi: 10.15938/j.emc.2023.05.009. MA Hongzhong, LI Nan, YANG Qifan, et al. On-line fault diagnosis method of transformer winding looseness based on multi-characteristic voiceprint maps[J]. Electric Machines and Control, 2023, 27(5): 76–87. doi: 10.15938/j.emc.2023.05.009.
[3]	周东旭, 王丰华, 党晓婧, 等. 基于压缩观测与判别字典学习的干式变压器声纹识别[J]. 中国电机工程学报, 2020, 40(19): 6380–6389. doi: 10.13334/j.0258-8013.pcsee.191577. ZHOU Dongxu, WANG Fenghua, DANG Xiaojing, et al. Dry type transformer voiceprint recognition based on compressed observation and discrimination dictionary learning[J]. Proceedings of the CSEE, 2020, 40(19): 6380–6389. doi: 10.13334/j.0258-8013.pcsee.191577.
[4]	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): 413–422. doi: 10.13336/j.1003-6520.hve.20200131005. 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): 413–422. doi: 10.13336/j.1003-6520.hve.20200131005.
[5]	ELGOHARY A A, BADR M M, ELMALHY N A, et al. Transfer of learning in convolutional neural networks for thermal image classification in electrical transformer rooms[J]. Alexandria Engineering Journal, 2024, 105: 423–436. doi: 10.1016/j.aej.2024.07.077.
[6]	NIU Ben, WEI Yangjie, YU Zhuoran, et al. Acoustic signal augmentation for fault diagnosis of power transformers based on improved cycle generative adversarial networks[J]. Expert Systems with Applications, 2025, 288: 127997. doi: 10.1016/j.eswa.2025.127997.
[7]	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. doi: 10.13336/j.1003-6520.hve.20230646. WANG Yuwei, YU Junlong, PENG Ping, et al. Online detection method for transformer faults based on multi-model fusion[J]. High Voltage Engineering, 2023, 49(8): 3415–3424. doi: 10.13336/j.1003-6520.hve.20230646.
[8]	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. doi: 10.3969/j.issn.1673-7598.2023.02.008. YU Da, ZHANG Wei, and WANG Hui. Abnormal voiceprint diagnosis method of oil-immersed transformer based on LSTM neural network[J]. Smart Power, 2023, 51(2): 45–52. doi: 10.3969/j.issn.1673-7598.2023.02.008.
[9]	李楠, 马宏忠, 段大卫, 等. 基于多传感器融合声纹特征图谱的变压器铁芯松动故障诊断方法[J]. 振动与冲击, 2023, 42(15): 129–137,198. doi: 10.13465/j.cnki.jvs.2023.15.016. LI Nan, MA Hongzhong, DUAN Dawei, et al. Fault diagnosis method for transformer core looseness based on multi-sensor fusion voiceprint feature map[J]. Journal of Vibration and Shock, 2023, 42(15): 129–137,198. doi: 10.13465/j.cnki.jvs.2023.15.016.
[10]	PENG Jiaqi, MA Yulin, YE Haiping, et al. Voiceprint recognition method of transformer based on LBT-ODF and MVN[J]. Journal of Measurements in Engineering, 2025, 13(2): 387–404. doi: 10.21595/jme.2024.24496.
[11]	柴斌, 韦鹏, 宁复茂, 等. 基于S变换时频谱和KHA-CNN的换流变故障声纹识别[J]. 电网与清洁能源, 2024, 40(2): 103–109. doi: 10.3969/j.issn.1674-3814.2024.02.012. CHAI Bin, WEI Peng, NING Fumao, et al. Voiceprint recognition of converter transformer faults based on S transform time-frequency spectrum and KHA-CNN[J]. Power System and Clean Energy, 2024, 40(2): 103–109. doi: 10.3969/j.issn.1674-3814.2024.02.012.
[12]	WANG Jianxin, ZHAO Zhishan, ZHU Jun, et al. Improved support vector machine for voiceprint diagnosis of typical faults in power transformers[J]. Machines, 2023, 11(5): 539. doi: 10.3390/machines11050539.
[13]	WANG Yuwei, DONG Wenjuan, AZAN D, et al. Voiceprint state identification of power transformers based on probabilistic neural network[C]. The 6th International Conference on Artificial Intelligence and Computer Applications, Dalian, China, 2024: 154–158. doi: 10.1109/ICAICA63239.2024.10823067.
[14]	梁广平, 彭昌, 王杰, 等. 基于图注意力网络的变压器声纹信号故障检测方法[J]. 华北电力大学学报: 自然科学版, 2024: 1–9. LIANG Guangping, PENG Chang, WANG Jie, et al. Fault detection method of graph attention network based on transformer acoustic signal[J]. Journal of North China Electric Power University: Natural Science Edition, 2024: 1–9.
[15]	万可力, 马宏忠, 崔佳嘉, 等. 基于Mel-GADF与ConvNeXt-T的变压器铁心松动故障诊断方法[J]. 电力自动化设备, 2024, 44(3): 217–224. doi: 10.16081/j.epae.202307003. WAN Keli, MA Hongzhong, CUI Jiajia, et al. Fault diagnosis method of transformer core loosening based on Mel-GADF and ConvNeXt-T[J]. Electric Power Automation Equipment, 2024, 44(3): 217–224. doi: 10.16081/j.epae.202307003.
[16]	WANG Shuchen, XU Qizhi, ZHU Shunpeng, et al. Making transformer hear better: Adaptive feature enhancement based multi-level supervised acoustic signal fault diagnosis[J]. Expert Systems with Applications, 2025, 264: 125736. doi: 10.1016/j.eswa.2024.125736.
[17]	沈国堂, 郭振宇, 黄道均, 等. 基于特征提取和神经网络的电力变压器声纹诊断方法建立与应用[J]. 变压器, 2024, 61(6): 39–43. doi: 10.19487/j.cnki.1001-8425.2024.06.012. SHEN Guotang, GUO Zhenyu, HUANG Daojun, et al. Establishment and application of power transformer voiceprint diagnosis method based on feature fusion and neural network[J]. Transformer, 2024, 61(6): 39–43. doi: 10.19487/j.cnki.1001-8425.2024.06.012.
[18]	吴晓文, 孙静玲, 曹浩, 等. 电力变压器典型声纹特征分布规律统计分析[J]. 武汉大学学报: 工学版, 2025, 58(1): 84–93. doi: 10.14188/j.1671-8844.2020.0172. WU Xiaowen, SUN Jingling, CAO Hao, et al. Statistical analysis of typical voiceprint feature distribution of power transformers[J]. Engineering Journal of Wuhan University, 2025, 58(1): 84–93. doi: 10.14188/j.1671-8844.2020.0172.
[19]	YU Zhuoran, WEI Yangjie, NIU Ben, et al. Automatic condition monitoring and fault diagnosis system for power transformers based on voiceprint recognition[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 9600411. doi: 10.1109/TIM.2024.3384551.
[20]	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): 52–60,67. doi: 10.3969/j.ISSN.1007-2691.2020.06.06. 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): 52–60,67. doi: 10.3969/j.ISSN.1007-2691.2020.06.06.
[21]	冶海平, 彭家琦, 方保民, 等. 基于Mel时频谱的变压器铁心松动故障声纹识别[J]. 信息技术, 2025(9): 37–42. doi: 10.13274/j.cnki.hdzj.2025.09.007. YE Haiping, PENG Jiaqi, FANG Baomin, et al. Voiceprint recognition of transformer core looseness fault based on Mel time-frequency spectrum[J]. Information Technology, 2025(9): 37–42. doi: 10.13274/j.cnki.hdzj.2025.09.007.
[22]	狄晓栋, 李震梅, 李宗哲, 等. 基于混合特征MGCC的干式变压器故障诊断[J]. 电子测量技术, 2021, 44(12): 57–62. doi: 10.19651/j.cnki.emt.2106561. DI Xiaodong, LI Zhenmei, LI Zongzhe, et al. Fault diagnosis of dry-type transformer based on combination of MGCC feature parameters[J]. Electronic Measurement Technology, 2021, 44(12): 57–62. doi: 10.19651/j.cnki.emt.2106561.
[23]	PEI Xiping, HAN Songtao, BAO Yanyan, et al. Fault diagnosis of transformer winding short circuit based on WKPCA-WM and IPOA-CNN[J]. Frontiers in Energy Research, 2023, 11: 1151612. doi: 10.3389/fenrg.2023.1151612.
[24]	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. doi: 10.7688/j.issn.1000-1646.2023.06.08. 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. doi: 10.7688/j.issn.1000-1646.2023.06.08.
[25]	LI Hui, YAO Qi, and LI Xin. Voiceprint fault diagnosis of converter transformer under load influence based on multi-strategy improved Mel-Frequency spectrum coefficient and temporal convolutional network[J]. Sensors, 2024, 24(3): 757. doi: 10.3390/s24030757.
[26]	李明朗, 杨洋, 王凤雪, 等. 基于声纹信号的变压器故障检测技术分析[J]. 电子元器件与信息技术, 2025, 9(8): 58–60. doi: 10.19772/j.cnki.2096-4455.2025.08.018. LI Minglang, YANG Yang, WANG Fengxue, et al. Analysis of transformer fault detection technology based on acoustic signal[J]. Electronic Components and Information Technology, 2025, 9(8): 58–60. doi: 10.19772/j.cnki.2096-4455.2025.08.018.
[27]	李波, 闫胜春. 基于深度学习的变压器声纹故障诊断方法研究[J]. 电工技术, 2025(17): 60–62,65. doi: 10.19768/j.cnki.dgjs.2025.17.015. LI Bo and YAN Shengchun. Research on deep learning based acoustic fault diagnosis method of transformer[J]. Electric Engineering, 2025(17): 60–62,65. doi: 10.19768/j.cnki.dgjs.2025.17.015.
[28]	SUN Yanfei, ZHAO Tao, GAO Li, et al. An attention-guided semi-supervised model for power transformer fault diagnosis via vibration-acoustic data fusion[J]. IET Electric Power Applications, 2025, 19(1): e70062. doi: 10.1049/elp2.70062.
[29]	李腾, 樊培培, 廖军, 等. 基于奇异值能量标准谱和改进TVF-EMD的换流变压器局部放电去噪方法[J]. 高压电器, 2025, 61(11): 221–230. doi: 10.13296/j.1001-1609.hva.2025.11.021. LI Teng, FAN Peipei, LIAO Jun, et al. Partial discharge denoising method for converter transformer based on singular value energy standard spectrum and improved TVF-EMD[J]. High Voltage Apparatus, 2025, 61(11): 221–230. doi: 10.13296/j.1001-1609.hva.2025.11.021.
[30]	魏才懿, 杨军, 马建桥. 参数优化VMD对变压器声音信号的故障诊断[J]. 兰州交通大学学报, 2021, 40(4): 49–58. doi: 10.3969/j.issn.1001-4373.2021.04.008. WEI Caiyi, YANG Jun, and MA Jianqiao. Fault diagnosis of transformer sound signal by parameter optimization VMD[J]. Journal of Lanzhou Jiaotong University, 2021, 40(4): 49–58. doi: 10.3969/j.issn.1001-4373.2021.04.008.
[31]	SHEN Xiang, XU Fei, XU Long, et al. Research on transformer voiceprint feature extraction oriented to complex noise environment[J]. International Journal of Acoustics and Vibration, 2023, 28(2): 193–199. doi: 10.20855/ijav.2023.28.21933.
[32]	陆云才, 廖才波, 李群, 等. 基于声纹特征和集成学习的变压器缺陷诊断方法[J]. 电力工程技术, 2023, 42(5): 46–55. doi: 10.12158/j.2096-3203.2023.05.006. LU Yuncai, LIAO Caibo, LI Qun, et al. Transformer fault diagnosis method based on voiceprint feature and ensemble learning[J]. Electric Power Engineering Technology, 2023, 42(5): 46–55. doi: 10.12158/j.2096-3203.2023.05.006.
[33]	段梵, 李先允, 单光瑞, 等. 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[J]. 高压电器, 2025, 61(3): 205–213. doi: 10.13296/j.1001-1609.hva.2025.03.025. DUAN Fan, LI Xianyun, SHAN Guangrui, et al. Voiceprint recognition method for mechanical faults of 10 kV circuit breaker based on fusion feature residual neural network[J]. High Voltage Apparatus, 2025, 61(3): 205–213. doi: 10.13296/j.1001-1609.hva.2025.03.025.
[34]	CAI Rui, WANG Qian, HOU Yucheng, et al. Event monitoring of transformer discharge sounds based on voiceprint[J]. Journal of Physics: Conference Series, 2021, 2078(1): 012066. doi: 10.1088/1742-6596/2078/1/012066.
[35]	王广真, 付德慧, 杜非, 等. 基于重复模式提取与高斯混合模型的变压器故障声纹识别[J]. 广东电力, 2023, 36(1): 126–134. doi: 10.3969/j.issn.1007-290X.2023.01.014. WANG Guangzhen, FU Dehui, DU Fei, et al. Transformer fault voiceprint recognition based on repeating pattern extraction and Gaussian mixture model[J]. Guangdong Electric Power, 2023, 36(1): 126–134. doi: 10.3969/j.issn.1007-290X.2023.01.014.
[36]	陈睿妍, 卢璐, 沈明威, 等. 基于线性SVM的变电站故障声纹检测算法[J]. 中国电子科学研究院学报, 2023, 18(11): 989–995. doi: 10.3969/j.issn.1673-5692.2023.11.003. CHEN Ruiyan, LU Lu, SHEN Mingwei, et al. Faulty voiceprint detection algorithm based on linear SVM for substation[J]. Journal of China Academy of Electronics and Information Technology, 2023, 18(11): 989–995. doi: 10.3969/j.issn.1673-5692.2023.11.003.
[37]	高家通, 康兵, 许志浩, 等. 基于FRCMDE与IBOA-LSSVM的变压器故障声纹诊断方法[J]. 噪声与振动控制, 2025, 45(5): 123–130. doi: 10.3969/j.issn.1006-1355.2025.05.020. GAO Jiatong, KANG Bing, XU Zhihao, et al. Fault voiceprint diagnosis method for transformers based on FRCMDE and IBOA-LSSVM[J]. Noise and Vibration Control, 2025, 45(5): 123–130. doi: 10.3969/j.issn.1006-1355.2025.05.020.
[38]	熊威, 龚康, 张鑫, 等. 基于COA-SVM变压器铁芯松动识别模型[J]. 电工技术, 2025(5): 141–144. doi: 10.19768/j.cnki.dgjs.2025.05.036. XIONG Wei, GONG Kang, ZHANG Xin, et al. Based on the COA-SVM transformer core loosening identification model[J]. Electric Engineering, 2025(5): 141–144. doi: 10.19768/j.cnki.dgjs.2025.05.036.
[39]	梁延昌. 基于机器学习的变压器声学异常检测方法研究[D]. [硕士论文], 华北电力大学(北京), 2021. doi: 10.27140/d.cnki.ghbbu.2021.001080. LIANG Yanchang. Research on machine learning based acoustic anomaly detection method for power transformers[D]. [Master dissertation], North China Electric Power University (Beijing), 2021. doi: 10.27140/d.cnki.ghbbu.2021.001080.
[40]	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): 191–196,224. doi: 10.16081/j.epae.202007022. GENG Qishen, WANG Fenghua, and 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): 191–196,224. doi: 10.16081/j.epae.202007022.
[41]	陈静. 基于声音信号分析的牵引变压器故障诊断方法研究[J]. 电气应用, 2020, 39(2): 25–29. CHEN Jing. Research on traction transformer fault diagnosis method based on sound signal analysis[J]. Electrotechnical Application, 2020, 39(2): 25–29.
[42]	吴国鑫, 詹花茂, 李敏. 声纹的变压器放电与机械故障诊断研究[J]. 应用声学, 2021, 40(4): 602–610. doi: 10.11684/j.issn.1000-310X.2021.04.015. WU Guoxin, ZHAN Huamao, and LI Min. Research on transformer discharge and mechanical fault diagnosis based on voiceprint[J]. Journal of Applied Acoustics, 2021, 40(4): 602–610. doi: 10.11684/j.issn.1000-310X.2021.04.015.
[43]	黄锐, 吕学宾, 苏永智, 等. 基于“声音+BP神经网络”的变压器故障诊断[J]. 信息技术, 2022, 46(11): 71–76. doi: 10.13274/j.cnki.hdzj.2022.11.013. HUANG Rui, LV Xuebin, SU Yongzhi, et al. Transformer fault diagnosis based on “sound + BP neural network”[J]. Information Technology, 2022, 46(11): 71–76. doi: 10.13274/j.cnki.hdzj.2022.11.013.
[44]	余金龙. 电力变压器异常故障智能声纹监测与诊断系统研究及应用[J]. 科技创新与应用, 2024, 14(8): 149–152. doi: 10.19981/j.CN23-1581/G3.2024.08.034. YU Jinlong. Research and application of intelligent acoustic monitoring and diagnosis system for abnormal faults of power transformer[J]. Technology Innovation and Application, 2024, 14(8): 149–152. doi: 10.19981/j.CN23-1581/G3.2024.08.034.
[45]	余长树. 基于声纹的变压器故障诊断算法及其应用研究[D]. [硕士论文], 华北电力大学(北京), 2023. doi: 10.27140/d.cnki.ghbbu.2023.001152. YU Changshu. Sound pattern based transformer fault diagnosis algorithm and application research[D]. [Master dissertation], North China Electric Power University (Beijing), 2023. doi: 10.27140/d.cnki.ghbbu.2023.001152.
[46]	包艳艳, 杨广泽, 陈伟, 等. 基于SBSS与CNN的750 kV变压器和尖板的放电信号声纹识别[J]. 西南交通大学学报, 2025, 60(3): 781–792. doi: 10.3969/j.issn.0258-2724.20230177. BAO Yanyan, YANG Guangze, CHEN Wei, et al. Voiceprint recognition of discharge aliasing signals from 750 kV transformer and pin-plate based on sparse representation theory and convolutional neural network[J]. Journal of Southwest Jiaotong University, 2025, 60(3): 781–792. doi: 10.3969/j.issn.0258-2724.20230177.
[47]	崔佳嘉, 马宏忠. 基于改进MFCC和3D-CNN的变压器铁心松动故障声纹识别模型[J]. 电机与控制学报, 2022, 26(12): 150–160. doi: 10.15938/j.emc.2022.12.015. CUI Jiajia and MA Hongzhong. Voiceprint recognition model of transformer core looseness fault based on improved MFCC and 3D-CNN[J]. Electric Machines and Control, 2022, 26(12): 150–160. doi: 10.15938/j.emc.2022.12.015.
[48]	王欢, 王昕, 张峰, 等. 基于改进生成对抗网络的变压器声纹故障诊断[J]. 智慧电力, 2024, 52(4): 24–31. doi: 10.3969/j.issn.1673-7598.2024.04.005. WANG Huan, WANG Xin, ZHANG Feng, et al. Transformer voiceprint fault diagnosis based on improved generative adversarial network[J]. Smart Power, 2024, 52(4): 24–31. doi: 10.3969/j.issn.1673-7598.2024.04.005.
[49]	WAN Shuting, DONG Fan, ZHANG Xiong, et al. Fault voiceprint signal diagnosis method of power transformer based on mixup data enhancement[J]. Sensors, 2023, 23(6): 3341. doi: 10.3390/s23063341.
[50]	吴帆, 刘艳霞, 刘力铭, 等. 基于深度学习模型的电力变压器故障声音诊断方法研究[J]. 电声技术, 2020, 44(1): 76–80. doi: 10.16311/j.audioe.2020.01.020. WU Fan, LIU Yanxia, LIU Liming, et al. Study on the fault diagnosis method of power transformer by sound signals based on deep learning model[J]. Audio Engineering, 2020, 44(1): 76–80. doi: 10.16311/j.audioe.2020.01.020.
[51]	LI Min, ZHAN Huamao, and QIU Annan. Voiceprint recognition of transformer fault based on blind source separation and convolutional neural network[C]. 2021 IEEE Electrical Insulation Conference (EIC), Denver, CO, USA, 2021: 618–621. doi: 10.1109/EIC49891.2021.9612322.
[52]	刘鹏华, 段颖梨, 刘凯, 等. 基于卷积神经网络的换流变压器智能检测算法设计[J]. 科技创新与应用, 2025, 15(20): 142–145. doi: 10.19981/j.CN23-1581/G3.2025.20.033. LIU Penghua, DUAN Yingli, LIU Kai, et al. Design of intelligent detection algorithm for converter transformer based on convolutional neural network[J]. Technology Innovation and Application, 2025, 15(20): 142–145. doi: 10.19981/j.CN23-1581/G3.2025.20.033.
[53]	XU Zhendong, GAO Feng, JIA Yuebo, et al. Research on transformer fault diagnosis algorithm based on MFCC features and deep learning[C]. The 6th International Conference on Electrical, Electronic Information and Communication Engineering (EEICE), Shenzhen, China, 2025: 192–195. doi: 10.1109/EEICE65049.2025.11033961.
[54]	LONG Yujiang, WEI Wei, and WANG Ce. A lightweight sound diagnosis model for transformer discharge fault based on knowledge distillation with supercomputing[C]. The 3rd International Conference on Computer Science and Management Technology (ICCSMT), Shanghai, China, 2022: 408–412. doi: 10.1109/ICCSMT58129.2022.00093.
[55]	宋诚, 夏翔, 王鑫一, 等. 基于MFCC和CNN的变压器声学特征提取及故障识别[J]. 电工电气, 2023(6): 49–54. doi: 10.3969/j.issn.1007-3175.2023.06.009. SONG Cheng, XIA Xiang, WANG Xinyi, et al. Transformer acoustic feature extraction and fault identification based on MFCC and CNN[J]. Electrotechnics Electric, 2023(6): 49–54. doi: 10.3969/j.issn.1007-3175.2023.06.009.
[56]	邹国春, 卢强, 鲁斌, 等. 复杂环境噪声条件下变压器故障声纹识别技术[J]. 电子制作, 2024, 32(24): 23–28. doi: 10.16589/j.cnki.cn11-3571/tn.2024.24.001. ZOU Guochun, LU Qiang, LU Bin, et al. Transformer fault acoustic recognition technology under complex environmental noise conditions[J]. Practical Electronics, 2024, 32(24): 23–28. doi: 10.16589/j.cnki.cn11-3571/tn.2024.24.001.
[57]	吴宁, 王世旭, 杨宏宇, 等. 基于MDF-BSRNet的变压器声纹故障诊断方法研究[J/OL]. 自动化技术与应用, https://link.cnki.net/urlid/23.1474.TP.20241223.1335.076, 2024. WU Ning, WANG Shixu, YANG Hongyu, et al. Research on fault diagnosis method of transformer voicing based on MDF-BSRNet[J/OL]. Techniques of Automation and Applications, 2024: 1–8.
[58]	QIAN Qinglin, GAO Penglu, ZHAO Honglin, et al. Electrical voiceprint recognition algorithm based on SN-GAN-ResNet network[C]. 2023 IEEE International Conference on Energy Internet (ICEI), Shenyang, China, 2023: 304–309. doi: 10.1109/icei60179.2023.00064.
[59]	何萍, 李勇, 陈寿龙, 等. 基于变压器声纹Mel语谱图-ResNet的铁心松动故障诊断[J]. 电机与控制应用, 2022, 49(9): 75–80. doi: 10.12177/emca.2022.084. HE Ping, LI Yong, CHEN Shoulong, et al. Fault diagnosis of iron core looseness based on Mel spectrogram-ResNet with transformer voiceprint[J]. Electric Machines & Control Application, 2022, 49(9): 75–80. doi: 10.12177/emca.2022.084.
[60]	张波, 黄英龄, 明志茂, 等. 基于同步压缩小波变换和ResNet的变压器放电故障诊断方法[J]. 现代电子技术, 2023, 46(10): 159–165. doi: 10.16652/j.issn.1004-373x.2023.10.030. ZHANG Bo, HUANG Yingling, MING Zhimao, et al. Method of transformer discharge fault diagnosis based on synchrosqueezed wavelet transform and ResNet[J]. Modern Electronics Technique, 2023, 46(10): 159–165. doi: 10.16652/j.issn.1004-373x.2023.10.030.
[61]	李嘉宁, 李喆, 陈海威, 等. 基于数据增强的变压器机械故障声纹识别方法[J]. 电气自动化, 2024, 46(6): 106–108. doi: 10.3969/j.issn.1000-3886.2024.06.030. LI Jianing, LI Zhe, CHEN Haiwei, et al. Voiceprint recognition of mechanical faults in transformers based on data enhancement[J]. Electrical Automation, 2024, 46(6): 106–108. doi: 10.3969/j.issn.1000-3886.2024.06.030.
[62]	赵晋级, 戴云飞. 基于改进MFCC和RNN的变压器放电故障诊断方法[J]. 山东电力高等专科学校学报, 2024, 27(4): 1–4,8. doi: 10.3969/j.issn.1008-3162.2024.04.001. ZHAO Jinji and DAI Yunfei. Transformer discharge fault diagnosis method based on improved MFCC and RNN[J]. Journal of Shandong Electric Power College, 2024, 27(4): 1–4,8. doi: 10.3969/j.issn.1008-3162.2024.04.001.
[63]	XIA Yici, HE Yan, KANG Bing, et al. Research and application of MFCC-LSTM based on improved ZOA algorithm to optimize transformer voice-print diagnosis[C]. The 4th International Conference on Electrical Engineering and Control Science (IC2ECS), Nanjing, China, 2024: 559–563. doi: 10.1109/IC2ECS64405.2024.10928641.
[64]	侯文彪, 徐宁. 基于多特征提取分析的变压器声纹故障识别技术研究[J]. 江西电力, 2025, 49(1): 70–74. doi: 10.3969/j.issn.1006-348X.2025.01.016. HOU Wenbiao and XU Ning. Research on transformer acoustic fault identification technology based on multi-feature extraction and analysis[J]. Jiangxi Electric Power, 2025, 49(1): 70–74. doi: 10.3969/j.issn.1006-348X.2025.01.016.
[65]	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. doi: 10.13334/j.0258-8013.pcsee.191922. LIU Yunpeng, WANG Bowen, YUE Haotian, et al. Identification of transformer bias voiceprint based on 50Hz frequency multiplication cepstrum coefficients and gated recurrent unit[J]. Proceedings of the CSEE, 2020, 40(14): 4681–4694. doi: 10.13334/j.0258-8013.pcsee.191922.
[66]	ABULIZI J, CHEN Zhen, LIU Peng, et al. Research on voiceprint recognition of power transformer anomalies using gated recurrent unit[C]. 2021 Power System and Green Energy Conference (PSGEC), Shanghai, China, 2021: 743–747. doi: 10.1109/PSGEC51302.2021.9542338.
[67]	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]. 中国电机工程学报, 2025, 45(4): 1311–1322. doi: 10.13334/j.0258-8013.pcsee.231543. QI Zihao, TONG Jie, ZHANG Zhonghao, et al. A voiceprint classification method for power transformer fault identification based on multi-granularity knowledge features and transformer network[J]. Proceedings of the CSEE, 2025, 45(4): 1311–1322. doi: 10.13334/j.0258-8013.pcsee.231543.
[68]	张寒, 熊云, 唐信, 等. 声纹信号-图形差分场增强和多头自注意力机制的变压器工作状态辨识方法[J]. 应用声学, 2024, 43(1): 119–130. doi: 10.11684/j.issn.1000-310X.2024.01.015. ZHANG Han, XIONG Yun, TANG Xin, et al. Transformer working state identification method based on voiceprint signal-motif difference field enhancement and multi-head self-attention mechanism[J]. Journal of Applied Acoustics, 2024, 43(1): 119–130. doi: 10.11684/j.issn.1000-310X.2024.01.015.
[69]	ZHANG Kai, LU Hongming, HAN Shuai, et al. A novel fault diagnosis method for power transformers based on voiceprint recognition considering multitype noises[J]. IEEE Transactions on Instrumentation and Measurement, 2025, 74: 3541311. doi: 10.1109/TIM.2025.3573012.
[70]	XUE Zichun, WANG Bo, MA Hengrui, et al. Research on transformer fault diagnosis and maintenance strategy generation based on TransQwen model[J]. Processes, 2025, 13(7): 1977. doi: 10.3390/pr13071977.
[71]	LU Hongming, ZHANG Kai, and HAN Shuai. A comparison of CNN-based transformer fault diagnosis methods based on voiceprint signal[C]. 2024 IEEE 13th Data Driven Control and Learning Systems Conference (DDCLS), Kaifeng, China, 2024: 819–824. doi: 10.1109/ddcls61622.2024.10606641.
[72]	辛全金, 李晓华, 杨义, 等. 基于冗余卷积编解码器的变压器噪声抑制[J]. 中国电力, 2023, 56(4): 112–118. doi: 10.11930/j.issn.1004-9649.202203065. XIN Quanjin, LI Xiaohua, YANG Yi, et al. Research on transformer noise suppression based on redundant convolutional encoder decoder[J]. Electric Power, 2023, 56(4): 112–118. doi: 10.11930/j.issn.1004-9649.202203065.
[73]	廖才波, 杨金鑫, 邱志斌, 等. 一种基于夏普利值及油中溶解气体分析的可解释变压器故障诊断方法[J]. 电网技术, 2024, 48(4): 1752–1761. doi: 10.13335/j.1000-3673.pst.2023.0727. LIAO Caibo, YANG Jinxin, QIU Zhibin, et al. Interpretable transformer fault diagnosis based on SHAP value and dissolved gas analysis of transformer oil[J]. Power System Technology, 2024, 48(4): 1752–1762. doi: 10.13335/j.1000-3673.pst.2023.0727.
[74]	TANG Pengfei, ZHANG Zhonghao, TONG Jie, et al. Predicting transformer temperature field based on physics-informed neural networks[J]. High Voltage, 2024, 9(4): 839–852. doi: 10.1049/hve2.12435.
[75]	林春清, 周颖, 杨超, 等. 面向电力变压器的声纹智能诊断装置设计与应用[J]. 传感技术学报, 2021, 34(10): 1412–1420. doi: 10.3969/j.issn.1004-1699.2021.10.021. LIN Chunqing, ZHOU Ying, YANG Chao, et al. Design and application of intelligent voiceprint diagnosis device for power transformer[J]. Chinese Journal of Sensors and Actuators, 2021, 34(10): 1412–1420. doi: 10.3969/j.issn.1004-1699.2021.10.021.