Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor

336 Views
209 Downloads
Export citation: ABNT
LI, Ying ;WANG, Jin Dong;ZHAO, Hai Yang;SONG, Mei Ping;OU, Ling Fei.
Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 65, n.2, p. 123-135, february 2019. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/fault-diagnosis-method-based-on-modified-multiscale-entropy-and-global-distance-evaluation-for-valve-fault-of-reciprocating-compressor/>. Date accessed: 21 aug. 2019. 
doi:http://dx.doi.org/10.5545/sv-jme.2018.5487.
Li, Y., Wang, J., Zhao, H., Song, M., & Ou, L.
(2019).
Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor.
Strojniški vestnik - Journal of Mechanical Engineering, 65(2), 123-135.
doi:http://dx.doi.org/10.5545/sv-jme.2018.5487
@article{sv-jmesv-jme.2018.5487,
	author = {Ying  Li and Jin Dong Wang and Hai Yang Zhao and Mei Ping Song and Ling Fei Ou},
	title = {Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {65},
	number = {2},
	year = {2019},
	keywords = {fault diagnosis; reciprocating compressor valve; modified multiscale entropy (MMSE); global distance evaluation (GDE); binary tree of support vector machine (BTSVM)},
	abstract = {According to the nonlinearity, non-stationarity and multi-component coupling characteristics of reciprocating compressor vibration signals, a fault diagnosis method of a reciprocating compressor valve based on modified multiscale entropy (MMSE) and global distance evaluation (GDE) is proposed. First, the variational mode decomposition (VMD) method with superior anti-interference performance was utilized to analyse the strong non-stationarity vibration signals for all fault states. The modified multiscale entropy (MMSE) method provided for movingaverage procedures by replacing mean-average coarse-grained procedures was developed for the vibration signals after de-noising, and then the GDE method of overall parameter selection was introduced to evaluate the extracted MMSE and to select the optimal sensitivity scale feature. Finally, a binary tree of support vector machine (BTSVM) was selected as the classifier to identify the reciprocating compressor valve fault type. By analysing the experimental data, it can be shown that the method can effectively identify the fault type of the reciprocating compressor valve.},
	issn = {0039-2480},	pages = {123-135},	doi = {10.5545/sv-jme.2018.5487},
	url = {https://www.sv-jme.eu/article/fault-diagnosis-method-based-on-modified-multiscale-entropy-and-global-distance-evaluation-for-valve-fault-of-reciprocating-compressor/}
}
Li, Y.,Wang, J.,Zhao, H.,Song, M.,Ou, L.
2019 February 65. Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 65:2
%A Li, Ying 
%A Wang, Jin Dong
%A Zhao, Hai Yang
%A Song, Mei Ping
%A Ou, Ling Fei
%D 2019
%T Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor
%B 2019
%9 fault diagnosis; reciprocating compressor valve; modified multiscale entropy (MMSE); global distance evaluation (GDE); binary tree of support vector machine (BTSVM)
%! Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor
%K fault diagnosis; reciprocating compressor valve; modified multiscale entropy (MMSE); global distance evaluation (GDE); binary tree of support vector machine (BTSVM)
%X According to the nonlinearity, non-stationarity and multi-component coupling characteristics of reciprocating compressor vibration signals, a fault diagnosis method of a reciprocating compressor valve based on modified multiscale entropy (MMSE) and global distance evaluation (GDE) is proposed. First, the variational mode decomposition (VMD) method with superior anti-interference performance was utilized to analyse the strong non-stationarity vibration signals for all fault states. The modified multiscale entropy (MMSE) method provided for movingaverage procedures by replacing mean-average coarse-grained procedures was developed for the vibration signals after de-noising, and then the GDE method of overall parameter selection was introduced to evaluate the extracted MMSE and to select the optimal sensitivity scale feature. Finally, a binary tree of support vector machine (BTSVM) was selected as the classifier to identify the reciprocating compressor valve fault type. By analysing the experimental data, it can be shown that the method can effectively identify the fault type of the reciprocating compressor valve.
%U https://www.sv-jme.eu/article/fault-diagnosis-method-based-on-modified-multiscale-entropy-and-global-distance-evaluation-for-valve-fault-of-reciprocating-compressor/
%0 Journal Article
%R 10.5545/sv-jme.2018.5487
%& 123
%P 13
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 65
%N 2
%@ 0039-2480
%8 2019-02-17
%7 2019-02-17
Li, Ying, Jin Dong Wang, Hai Yang Zhao, Mei Ping Song, & Ling Fei Ou.
"Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor." Strojniški vestnik - Journal of Mechanical Engineering [Online], 65.2 (2019): 123-135. Web.  21 Aug. 2019
TY  - JOUR
AU  - Li, Ying 
AU  - Wang, Jin Dong
AU  - Zhao, Hai Yang
AU  - Song, Mei Ping
AU  - Ou, Ling Fei
PY  - 2019
TI  - Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2018.5487
KW  - fault diagnosis; reciprocating compressor valve; modified multiscale entropy (MMSE); global distance evaluation (GDE); binary tree of support vector machine (BTSVM)
N2  - According to the nonlinearity, non-stationarity and multi-component coupling characteristics of reciprocating compressor vibration signals, a fault diagnosis method of a reciprocating compressor valve based on modified multiscale entropy (MMSE) and global distance evaluation (GDE) is proposed. First, the variational mode decomposition (VMD) method with superior anti-interference performance was utilized to analyse the strong non-stationarity vibration signals for all fault states. The modified multiscale entropy (MMSE) method provided for movingaverage procedures by replacing mean-average coarse-grained procedures was developed for the vibration signals after de-noising, and then the GDE method of overall parameter selection was introduced to evaluate the extracted MMSE and to select the optimal sensitivity scale feature. Finally, a binary tree of support vector machine (BTSVM) was selected as the classifier to identify the reciprocating compressor valve fault type. By analysing the experimental data, it can be shown that the method can effectively identify the fault type of the reciprocating compressor valve.
UR  - https://www.sv-jme.eu/article/fault-diagnosis-method-based-on-modified-multiscale-entropy-and-global-distance-evaluation-for-valve-fault-of-reciprocating-compressor/
@article{{sv-jme}{sv-jme.2018.5487},
	author = {Li, Y., Wang, J., Zhao, H., Song, M., Ou, L.},
	title = {Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {65},
	number = {2},
	year = {2019},
	doi = {10.5545/sv-jme.2018.5487},
	url = {https://www.sv-jme.eu/article/fault-diagnosis-method-based-on-modified-multiscale-entropy-and-global-distance-evaluation-for-valve-fault-of-reciprocating-compressor/}
}
TY  - JOUR
AU  - Li, Ying 
AU  - Wang, Jin Dong
AU  - Zhao, Hai Yang
AU  - Song, Mei Ping
AU  - Ou, Ling Fei
PY  - 2019/02/17
TI  - Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 65, No 2 (2019): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2018.5487
KW  - fault diagnosis, reciprocating compressor valve, modified multiscale entropy (MMSE), global distance evaluation (GDE), binary tree of support vector machine (BTSVM)
N2  - According to the nonlinearity, non-stationarity and multi-component coupling characteristics of reciprocating compressor vibration signals, a fault diagnosis method of a reciprocating compressor valve based on modified multiscale entropy (MMSE) and global distance evaluation (GDE) is proposed. First, the variational mode decomposition (VMD) method with superior anti-interference performance was utilized to analyse the strong non-stationarity vibration signals for all fault states. The modified multiscale entropy (MMSE) method provided for movingaverage procedures by replacing mean-average coarse-grained procedures was developed for the vibration signals after de-noising, and then the GDE method of overall parameter selection was introduced to evaluate the extracted MMSE and to select the optimal sensitivity scale feature. Finally, a binary tree of support vector machine (BTSVM) was selected as the classifier to identify the reciprocating compressor valve fault type. By analysing the experimental data, it can be shown that the method can effectively identify the fault type of the reciprocating compressor valve.
UR  - https://www.sv-jme.eu/article/fault-diagnosis-method-based-on-modified-multiscale-entropy-and-global-distance-evaluation-for-valve-fault-of-reciprocating-compressor/
Li, Ying, Wang, Jin, Zhao, Hai, Song, Mei, AND Ou, Ling.
"Fault Diagnosis Method Based on Modified Multiscale Entropy and Global Distance Evaluation for the Valve Fault of a Reciprocating Compressor" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 65 Number 2 (17 February 2019)

Authors

Affiliations

  • Northeast Petroleum University, Mechanical Science and Engineering Institute
  • Northeast Petroleum University, Mechanical Science and Engineering Institute
  • Northeast Petroleum University, Mechanical Science and Engineering Institute
  • Northeast Petroleum University, Mechanical Science and Engineering Institute
  • Northeast Petroleum University, Mechanical Science and Engineering Institute

Paper's information

Strojniški vestnik - Journal of Mechanical Engineering 65(2019)2, 123-135

10.5545/sv-jme.2018.5487

According to the nonlinearity, non-stationarity and multi-component coupling characteristics of reciprocating compressor vibration signals, a fault diagnosis method of a reciprocating compressor valve based on modified multiscale entropy (MMSE) and global distance evaluation (GDE) is proposed. First, the variational mode decomposition (VMD) method with superior anti-interference performance was utilized to analyse the strong non-stationarity vibration signals for all fault states. The modified multiscale entropy (MMSE) method provided for movingaverage procedures by replacing mean-average coarse-grained procedures was developed for the vibration signals after de-noising, and then the GDE method of overall parameter selection was introduced to evaluate the extracted MMSE and to select the optimal sensitivity scale feature. Finally, a binary tree of support vector machine (BTSVM) was selected as the classifier to identify the reciprocating compressor valve fault type. By analysing the experimental data, it can be shown that the method can effectively identify the fault type of the reciprocating compressor valve.

fault diagnosis; reciprocating compressor valve; modified multiscale entropy (MMSE); global distance evaluation (GDE); binary tree of support vector machine (BTSVM)