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...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/6/3033 |
_version_ | 1797472976760733696 |
---|---|
author | Kang Li Zhe Sun Huaqiang Jin Yingjie Xu Jiangping Gu Yuejin Huang Qinjian Zhang Xi Shen |
author_facet | Kang Li Zhe Sun Huaqiang Jin Yingjie Xu Jiangping Gu Yuejin Huang Qinjian Zhang Xi Shen |
author_sort | Kang Li |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-09T20:08:40Z |
format | Article |
id | doaj.art-609bb4a8a6cf41e5a22384e146c460e7 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T20:08:40Z |
publishDate | 2022-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-609bb4a8a6cf41e5a22384e146c460e72023-11-24T00:22:42ZengMDPI AGApplied Sciences2076-34172022-03-01126303310.3390/app12063033Proposal and Experimental Study on a Diagnosis Method for Hermetic Refrigeration Compressor Using Dual Time-Frequency Image FusionKang Li0Zhe Sun1Huaqiang Jin2Yingjie Xu3Jiangping Gu4Yuejin Huang5Qinjian Zhang6Xi Shen7School of Mechanical Engineering, Zhejiang University of Technology, 288 Liuhe Road, Hangzhou 310023, ChinaSchool of Mechanical Engineering, Zhejiang University of Technology, 288 Liuhe Road, Hangzhou 310023, ChinaSchool of Education, Zhejiang University of Technology, 288 Liuhe Road, Hangzhou 310023, ChinaSchool of Mechanical Engineering, Zhejiang University of Technology, 288 Liuhe Road, Hangzhou 310023, ChinaSchool of Education, Zhejiang University of Technology, 288 Liuhe Road, Hangzhou 310023, ChinaSchool of Mechanical Engineering, Zhejiang University of Technology, 288 Liuhe Road, Hangzhou 310023, ChinaJoint Laboratory of Refrigeration Compressor Reliability Evaluation, Zhejiang University of Technology, Ltd., 288 Liuhe Road, Hangzhou 310023, ChinaSchool of Mechanical Engineering, Zhejiang University of Technology, 288 Liuhe Road, Hangzhou 310023, ChinaThe 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.https://www.mdpi.com/2076-3417/12/6/3033manufacturing defect diagnosisdual time-frequency images fusiondeep learningconvolutions neural networkhermetic refrigeration compressor |
spellingShingle | Kang Li Zhe Sun Huaqiang Jin Yingjie Xu Jiangping Gu Yuejin Huang Qinjian Zhang Xi Shen Proposal and Experimental Study on a Diagnosis Method for Hermetic Refrigeration Compressor Using Dual Time-Frequency Image Fusion Applied Sciences manufacturing defect diagnosis dual time-frequency images fusion deep learning convolutions neural network hermetic refrigeration compressor |
title | Proposal and Experimental Study on a Diagnosis Method for Hermetic Refrigeration Compressor Using Dual Time-Frequency Image Fusion |
title_full | Proposal and Experimental Study on a Diagnosis Method for Hermetic Refrigeration Compressor Using Dual Time-Frequency Image Fusion |
title_fullStr | Proposal and Experimental Study on a Diagnosis Method for Hermetic Refrigeration Compressor Using Dual Time-Frequency Image Fusion |
title_full_unstemmed | Proposal and Experimental Study on a Diagnosis Method for Hermetic Refrigeration Compressor Using Dual Time-Frequency Image Fusion |
title_short | Proposal and Experimental Study on a Diagnosis Method for Hermetic Refrigeration Compressor Using Dual Time-Frequency Image Fusion |
title_sort | proposal and experimental study on a diagnosis method for hermetic refrigeration compressor using dual time frequency image fusion |
topic | manufacturing defect diagnosis dual time-frequency images fusion deep learning convolutions neural network hermetic refrigeration compressor |
url | https://www.mdpi.com/2076-3417/12/6/3033 |
work_keys_str_mv | AT kangli proposalandexperimentalstudyonadiagnosismethodforhermeticrefrigerationcompressorusingdualtimefrequencyimagefusion AT zhesun proposalandexperimentalstudyonadiagnosismethodforhermeticrefrigerationcompressorusingdualtimefrequencyimagefusion AT huaqiangjin proposalandexperimentalstudyonadiagnosismethodforhermeticrefrigerationcompressorusingdualtimefrequencyimagefusion AT yingjiexu proposalandexperimentalstudyonadiagnosismethodforhermeticrefrigerationcompressorusingdualtimefrequencyimagefusion AT jiangpinggu proposalandexperimentalstudyonadiagnosismethodforhermeticrefrigerationcompressorusingdualtimefrequencyimagefusion AT yuejinhuang proposalandexperimentalstudyonadiagnosismethodforhermeticrefrigerationcompressorusingdualtimefrequencyimagefusion AT qinjianzhang proposalandexperimentalstudyonadiagnosismethodforhermeticrefrigerationcompressorusingdualtimefrequencyimagefusion AT xishen proposalandexperimentalstudyonadiagnosismethodforhermeticrefrigerationcompressorusingdualtimefrequencyimagefusion |