基于声纹压缩和代价敏感的变压器状态检测评估方法
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TM73

基金项目:

国家自然科学基金资助项目(52077133)


Transformer state detection and assessment method based on voiceprint compression and cost-sensitive techniques
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    声纹检测技术可以助力巡检人员对变压器状态进行检测和评估。文中提出一种基于声纹压缩和代价敏感的变压器状态检测和评估方法。该方法首先提取变压器音频的声纹特征,然后在频率维度上对声纹特征进行筛选和压缩,最后使用卷积神经网络评估变压器状态,并引入代价敏感损失函数以提高对难检出样本的关注度。以某35 kV变压器为研究对象,通过收集现场音频、模拟实验和样本扩充得到变压器音频数据集。测试结果表明,文中所提方法将声纹维度从1 025维降低到80维,计算量和显存分别降低到1 025维的8.1%和7.7%。同时,所提方法的声纹识别准确率高达83.5%,并将最难检出的短路电流异常状态的召回率从48.2%提升至63.6%。

    Abstract:

    Voiceprint detection technology can assist inspectors in assessing the state of transformers. A method for detecting and assessing transformer states based on voiceprint compression and cost-sensitive techniques is proposed. The method first extracts voiceprint features from transformer audio,then filters and compresses these features in the frequency domain. Subsequently,a convolutional neural network is employed to evaluate the transformer's state,incorporating a cost-sensitive loss function to enhance attention towards difficult samples. Using a 35 kV transformer as the experimental subject,transformer audio data is collected through on-site recordings,simulated experiments and sample augmentation. Test results demonstrate that the proposed method reduces the voiceprint dimensionality from 1 025 to 80,decreasing computational complexity and video memory usage to 8.1% and 7.7% of the original 1 025 dimensions,respectively. Simultaneously,the proposed method achieves a voiceprint recognition accuracy of 83.5% and improves the recall rate of the most challenging short-circuit current anomaly from 48.2% to 63.6%.

    参考文献
    相似文献
    引证文献
引用本文

胡赵宇,李喆,陈海威,陆忻.基于声纹压缩和代价敏感的变压器状态检测评估方法[J].电力工程技术,2024,43(3):209-216

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-11-18
  • 最后修改日期:2024-01-25
  • 录用日期:2023-10-23
  • 在线发布日期: 2024-05-23
  • 出版日期: 2024-05-28