Proposal and Experimental Study on a Diagnosis Method for Hermetic Refrigeration Compressor Using Dual Time-Frequency Image Fusion

The hermetic refrigeration compressor is the core component of the refrigeration system, failure of which will cause energy waste and reduce service life. Fault diagnosis based on vibration signal is a research hotspot. However, it is challenging to extract features of nonlinear and nonstationary vi...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 12; no. 6; p. 3033
Main Authors Li, Kang, Sun, Zhe, Jin, Huaqiang, Xu, Yingjie, Gu, Jiangping, Huang, Yuejin, Zhang, Qinjian, Shen, Xi
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.03.2022
Subjects
Algorithms
Complementarity
Computer vision
Continuous wavelet transform
convolutions neural network
deep learning
dual time-frequency images fusion
Energy consumption
Failure
Fault diagnosis
hermetic refrigeration compressor
Hilbert transformation
Image processing
Manufacturing
manufacturing defect diagnosis
Manufacturing defects
Medical imaging
Methods
Neural networks
Refrigeration
Service life
Support vector machines
Time-frequency analysis
Vibration
Wavelet transforms
Online AccessGet full text

Cover

More Information
Summary:The hermetic refrigeration compressor is the core component of the refrigeration system, failure of which will cause energy waste and reduce service life. Fault diagnosis based on vibration signal is a research hotspot. However, it is challenging to extract features of nonlinear and nonstationary vibration signals, which severely restricts the development of this method. This paper proposes a dual time-frequency images fusion method to obtain more effective features for diagnosing compressor manufacturing defects. Firstly, two time-frequency images are obtained by implementing continuous wavelet transform and Hilbert-Huang transform of the same vibration signal sample. Then, a convolutional neural network is used for image feature extraction and fusion, where the features extracted from two time-frequency images have complementarity. A data set containing six categories of typical manufacturing defects is used to verify the proposed method. The results show that the average diagnostic accuracy of the proposed method reaches 95.9%, and the proposed method has a better performance than other methods.
ISSN:2076-3417
2076-3417
DOI:10.3390/app12063033