中国电机工程学报2025，Vol.45Issue(4)：1311-1322,中插8,13.DOI:10.13334/j.0258-8013.pcsee.231543
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
A Voiceprint Classification Method for Power Transformer Fault Identification Based on Multi-granularity Knowledge Features and Transformer Network
摘要
Abstract
The power transformer makes abnormal sounds when mechanical failures occur.The mechanical fault identification based on voiceprint signals has become a current research hotspot due to its high accuracy,timely detection,and non-invasiveness.However,voiceprint signals are easily affected by noise and difficult to obtain,and the processing speed is slow.Therefore,how to achieve rapid and accurate identification of mechanical fault based on voiceprint signals in the presence of strong noise and small sample sizes has become a current research difficulty.To address the aforementioned issues,this paper first incorporates physical principles and empirical knowledge to extract feature and builds an improved Transformer network,significantly enhancing the noise resistance.Then,a convolutional autoencoder for model compression is constructed to shorten the training time.Finally,this paper employs cross-modal Transfer Learning by pretraining the model on the ImageNet-1k dataset to address the issue of limited training samples.Compared to traditional time-series deep learning methods,the proposed method achieves higher accuracy in a high-noise environment(SNR=−16 dB).Experimental results demonstrate significant improvements in accuracy,robustness,and generalization.This work provides a reliable solution for implementing power transformer mechanical fault identification based on voiceprint signals in complex environments.关键词
机械故障/故障辨识/声纹识别/自编码器/TransformerKey words
mechanical fault/fault identification/voiceprint classification/autoencoder/Transformer分类
动力与电气工程引用本文复制引用
齐子豪,仝杰,张中浩,龙天航,唐鹏飞,黄灿..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,中插8,13.基金项目
国家电网有限公司科技项目(5108-202218280A-2-398-XG). Science and Technology Program of State Gird Corporation of China(5108-202218280A-2-398-XG). （5108-202218280A-2-398-XG）
