Fault Diagnosis of a Reciprocating Compressor Air Valve Based on Deep Learning
With the development of machine learning in recent years, the application of machine learning to machine fault diagnosis has become increasingly popular. Applying traditional feature extraction methods for complex systems will weaken the characterization capacity of features, which are not conducive...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/18/6596 |
id |
doaj-19cd0fb5d5834533b3de47c7a3b526b6 |
---|---|
record_format |
Article |
spelling |
doaj-19cd0fb5d5834533b3de47c7a3b526b62020-11-25T03:35:01ZengMDPI AGApplied Sciences2076-34172020-09-01106596659610.3390/app10186596Fault Diagnosis of a Reciprocating Compressor Air Valve Based on Deep LearningShungen Xiao0Ang Nie1Zexiong Zhang2Shulin Liu3Mengmeng Song4Hongli Zhang5College of Information, Mechanical and Electrical Engineering, Ningde Normal University, Ningde 352100, Fujian, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200072, ChinaCollege of Information, Mechanical and Electrical Engineering, Ningde Normal University, Ningde 352100, Fujian, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200072, ChinaCollege of Information, Mechanical and Electrical Engineering, Ningde Normal University, Ningde 352100, Fujian, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200072, ChinaWith the development of machine learning in recent years, the application of machine learning to machine fault diagnosis has become increasingly popular. Applying traditional feature extraction methods for complex systems will weaken the characterization capacity of features, which are not conducive to subsequent classification work. A reciprocating compressor is a complex system. In order to improve the fault diagnosis accuracy of complex systems, this paper does not use traditional fault diagnosis methods and applies deep convolutional neural networks (CNNs) to process this nonlinear and non-stationary fault signal. The valve fault data is obtained from the reciprocating compressor test bench of the Daqing Natural Gas Company. Firstly, the single-channel vibration signal is collected on the reciprocating compressor and the one-dimensional CNN (1-D CNN) is used for fault diagnosis and compared with the traditional model to verify the effectiveness of the 1-D CNN. Next, the collected eight channels signals (three channels of vibration signals, four channels of pressure signals, one channel key phase signal) are applied by 1-D CNN and 2-D CNN for fault diagnosis to verify the CNN that it is still suitable for multi-channel signal processing. Finally, further study on the influence of the input of different channel signal combinations on the model diagnosis accuracy is carried out. Experiments show that the seven-channel signal (three-channel vibration signal, four-channel pressure signal) with the key phase signal removed has the highest diagnostic accuracy in the 2-D CNN. Therefore, proper deletion of useless channels can not only speed up network operations but also improve diagnosis accuracy.https://www.mdpi.com/2076-3417/10/18/6596reciprocating compressorfault diagnosisdeep learningCNN |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shungen Xiao Ang Nie Zexiong Zhang Shulin Liu Mengmeng Song Hongli Zhang |
spellingShingle |
Shungen Xiao Ang Nie Zexiong Zhang Shulin Liu Mengmeng Song Hongli Zhang Fault Diagnosis of a Reciprocating Compressor Air Valve Based on Deep Learning Applied Sciences reciprocating compressor fault diagnosis deep learning CNN |
author_facet |
Shungen Xiao Ang Nie Zexiong Zhang Shulin Liu Mengmeng Song Hongli Zhang |
author_sort |
Shungen Xiao |
title |
Fault Diagnosis of a Reciprocating Compressor Air Valve Based on Deep Learning |
title_short |
Fault Diagnosis of a Reciprocating Compressor Air Valve Based on Deep Learning |
title_full |
Fault Diagnosis of a Reciprocating Compressor Air Valve Based on Deep Learning |
title_fullStr |
Fault Diagnosis of a Reciprocating Compressor Air Valve Based on Deep Learning |
title_full_unstemmed |
Fault Diagnosis of a Reciprocating Compressor Air Valve Based on Deep Learning |
title_sort |
fault diagnosis of a reciprocating compressor air valve based on deep learning |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-09-01 |
description |
With the development of machine learning in recent years, the application of machine learning to machine fault diagnosis has become increasingly popular. Applying traditional feature extraction methods for complex systems will weaken the characterization capacity of features, which are not conducive to subsequent classification work. A reciprocating compressor is a complex system. In order to improve the fault diagnosis accuracy of complex systems, this paper does not use traditional fault diagnosis methods and applies deep convolutional neural networks (CNNs) to process this nonlinear and non-stationary fault signal. The valve fault data is obtained from the reciprocating compressor test bench of the Daqing Natural Gas Company. Firstly, the single-channel vibration signal is collected on the reciprocating compressor and the one-dimensional CNN (1-D CNN) is used for fault diagnosis and compared with the traditional model to verify the effectiveness of the 1-D CNN. Next, the collected eight channels signals (three channels of vibration signals, four channels of pressure signals, one channel key phase signal) are applied by 1-D CNN and 2-D CNN for fault diagnosis to verify the CNN that it is still suitable for multi-channel signal processing. Finally, further study on the influence of the input of different channel signal combinations on the model diagnosis accuracy is carried out. Experiments show that the seven-channel signal (three-channel vibration signal, four-channel pressure signal) with the key phase signal removed has the highest diagnostic accuracy in the 2-D CNN. Therefore, proper deletion of useless channels can not only speed up network operations but also improve diagnosis accuracy. |
topic |
reciprocating compressor fault diagnosis deep learning CNN |
url |
https://www.mdpi.com/2076-3417/10/18/6596 |
work_keys_str_mv |
AT shungenxiao faultdiagnosisofareciprocatingcompressorairvalvebasedondeeplearning AT angnie faultdiagnosisofareciprocatingcompressorairvalvebasedondeeplearning AT zexiongzhang faultdiagnosisofareciprocatingcompressorairvalvebasedondeeplearning AT shulinliu faultdiagnosisofareciprocatingcompressorairvalvebasedondeeplearning AT mengmengsong faultdiagnosisofareciprocatingcompressorairvalvebasedondeeplearning AT honglizhang faultdiagnosisofareciprocatingcompressorairvalvebasedondeeplearning |
_version_ |
1724556073216507904 |