家电科技 ›› 2022, Vol. 0 ›› Issue (4): 42-45.doi: 10.19784/j.cnki.issn1672-0172.2022.04.006

• 论文 • 上一篇    下一篇

基于自编码器的冰箱压缩机振动信号特征提取及故障检测

刘恒1, 冯涛1, 王晶1, 杨伟成2   

  1. 1.北京工商大学 北京 100048;
    2.中国家用电器研究院 北京 100037
  • 出版日期:2022-08-01 发布日期:2022-08-18
  • 通讯作者: 冯涛,E-mail:fengt@btbu.edu.cn。
  • 作者简介:刘恒,在读硕士研究生。研究方向:噪声与振动控制。地址:北京工商大学。E-mail:931364458@qq.com。

Refrigerator compressor vibration signal feature extraction and fault detection based on self-encoder

LIU Heng1, FENG Tao1, WANG Jing1, YANG Weicheng2   

  1. 1. Beijing Technology and Business University Beijing 100048;
    2. China Household Electric Appliances Research Institute Beijing 100037
  • Online:2022-08-01 Published:2022-08-18

摘要: 异音检测是压缩机质量控制的重要环节,针对压缩机故障样本信号稀少的特点,提出了一种利用自编码器提取冰箱压缩机正常信号样本共性特征进而实现故障检测的方法。在大量正常信号样本的基础上提取出共性特征,由于正常和故障样本的重构误差不同,可确定最优阈值作为故障分类标准。研究结果表明:在故障信号样本稀少的条件下,应用冰箱压缩机正常信号样本的共性特征对其故障信号样本进行检测,判断准确率可达97.4%。

关键词: 自编码器, 声信号, 共性特征, 故障稀少

Abstract: Abnormal sound detection is an important part of compressor quality control. Aiming at the characteristics of rare compressor fault sample signals, a method is proposed to extract the common characteristics of normal signal samples of refrigerator compressors by using self-encoder to realize fault detection. On the basis of a large number of normal signal samples, common features are extracted. Due to the different reconstruction errors of normal and faulty samples, the optimal threshold can be determined as the fault classification standard. The research results show that: under the condition that the fault signal samples are sparse, the common characteristics of the normal signal samples of the refrigerator compressor are used to detect the fault signal samples, and the judgment accuracy rate can reach 97.4%.

Key words: Autoencoder, Acoustic signal, Common feature, Fault sparse

中图分类号: