Bearing fault diagnosis method based on improved Siamese neural network with small sample
Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory e...
Ausführliche Beschreibung
Autor*in: |
Zhao, Xiaoping [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2022 |
---|
Schlagwörter: |
---|
Anmerkung: |
© The Author(s) 2022 |
---|
Übergeordnetes Werk: |
Enthalten in: Journal of Cloud Computing - Berlin : SpringerOpen, 2012, 11(2022), 1 vom: 19. Nov. |
---|---|
Übergeordnetes Werk: |
volume:11 ; year:2022 ; number:1 ; day:19 ; month:11 |
Links: |
---|
DOI / URN: |
10.1186/s13677-022-00350-1 |
---|
Katalog-ID: |
SPR048668710 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | SPR048668710 | ||
003 | DE-627 | ||
005 | 20230509120510.0 | ||
007 | cr uuu---uuuuu | ||
008 | 221119s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1186/s13677-022-00350-1 |2 doi | |
035 | |a (DE-627)SPR048668710 | ||
035 | |a (SPR)s13677-022-00350-1-e | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zhao, Xiaoping |e verfasserin |4 aut | |
245 | 1 | 0 | |a Bearing fault diagnosis method based on improved Siamese neural network with small sample |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
500 | |a © The Author(s) 2022 | ||
520 | |a Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. | ||
650 | 4 | |a Rolling bearing |7 (dpeaa)DE-He213 | |
650 | 4 | |a Siamese neural network |7 (dpeaa)DE-He213 | |
650 | 4 | |a Small sample |7 (dpeaa)DE-He213 | |
650 | 4 | |a Fault diagnosis |7 (dpeaa)DE-He213 | |
700 | 1 | |a Ma, Mengyao |4 aut | |
700 | 1 | |a Shao, Fan |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of Cloud Computing |d Berlin : SpringerOpen, 2012 |g 11(2022), 1 vom: 19. Nov. |w (DE-627)726491810 |w (DE-600)2682472-3 |x 2192-113X |7 nnns |
773 | 1 | 8 | |g volume:11 |g year:2022 |g number:1 |g day:19 |g month:11 |
856 | 4 | 0 | |u https://dx.doi.org/10.1186/s13677-022-00350-1 |z kostenfrei |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_SPRINGER | ||
912 | |a GBV_ILN_11 | ||
912 | |a GBV_ILN_20 | ||
912 | |a GBV_ILN_22 | ||
912 | |a GBV_ILN_23 | ||
912 | |a GBV_ILN_24 | ||
912 | |a GBV_ILN_39 | ||
912 | |a GBV_ILN_40 | ||
912 | |a GBV_ILN_60 | ||
912 | |a GBV_ILN_62 | ||
912 | |a GBV_ILN_63 | ||
912 | |a GBV_ILN_65 | ||
912 | |a GBV_ILN_69 | ||
912 | |a GBV_ILN_70 | ||
912 | |a GBV_ILN_73 | ||
912 | |a GBV_ILN_95 | ||
912 | |a GBV_ILN_105 | ||
912 | |a GBV_ILN_110 | ||
912 | |a GBV_ILN_151 | ||
912 | |a GBV_ILN_161 | ||
912 | |a GBV_ILN_170 | ||
912 | |a GBV_ILN_213 | ||
912 | |a GBV_ILN_230 | ||
912 | |a GBV_ILN_285 | ||
912 | |a GBV_ILN_293 | ||
912 | |a GBV_ILN_370 | ||
912 | |a GBV_ILN_602 | ||
912 | |a GBV_ILN_2014 | ||
912 | |a GBV_ILN_2055 | ||
912 | |a GBV_ILN_4012 | ||
912 | |a GBV_ILN_4037 | ||
912 | |a GBV_ILN_4112 | ||
912 | |a GBV_ILN_4125 | ||
912 | |a GBV_ILN_4126 | ||
912 | |a GBV_ILN_4249 | ||
912 | |a GBV_ILN_4305 | ||
912 | |a GBV_ILN_4306 | ||
912 | |a GBV_ILN_4307 | ||
912 | |a GBV_ILN_4313 | ||
912 | |a GBV_ILN_4322 | ||
912 | |a GBV_ILN_4323 | ||
912 | |a GBV_ILN_4324 | ||
912 | |a GBV_ILN_4325 | ||
912 | |a GBV_ILN_4326 | ||
912 | |a GBV_ILN_4335 | ||
912 | |a GBV_ILN_4338 | ||
912 | |a GBV_ILN_4367 | ||
912 | |a GBV_ILN_4700 | ||
951 | |a AR | ||
952 | |d 11 |j 2022 |e 1 |b 19 |c 11 |
author_variant |
x z xz m m mm f s fs |
---|---|
matchkey_str |
article:2192113X:2022----::ernfutigoimtobsdnmrvdimsnuan |
hierarchy_sort_str |
2022 |
publishDate |
2022 |
allfields |
10.1186/s13677-022-00350-1 doi (DE-627)SPR048668710 (SPR)s13677-022-00350-1-e DE-627 ger DE-627 rakwb eng Zhao, Xiaoping verfasserin aut Bearing fault diagnosis method based on improved Siamese neural network with small sample 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2022 Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. Rolling bearing (dpeaa)DE-He213 Siamese neural network (dpeaa)DE-He213 Small sample (dpeaa)DE-He213 Fault diagnosis (dpeaa)DE-He213 Ma, Mengyao aut Shao, Fan aut Enthalten in Journal of Cloud Computing Berlin : SpringerOpen, 2012 11(2022), 1 vom: 19. Nov. (DE-627)726491810 (DE-600)2682472-3 2192-113X nnns volume:11 year:2022 number:1 day:19 month:11 https://dx.doi.org/10.1186/s13677-022-00350-1 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2022 1 19 11 |
spelling |
10.1186/s13677-022-00350-1 doi (DE-627)SPR048668710 (SPR)s13677-022-00350-1-e DE-627 ger DE-627 rakwb eng Zhao, Xiaoping verfasserin aut Bearing fault diagnosis method based on improved Siamese neural network with small sample 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2022 Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. Rolling bearing (dpeaa)DE-He213 Siamese neural network (dpeaa)DE-He213 Small sample (dpeaa)DE-He213 Fault diagnosis (dpeaa)DE-He213 Ma, Mengyao aut Shao, Fan aut Enthalten in Journal of Cloud Computing Berlin : SpringerOpen, 2012 11(2022), 1 vom: 19. Nov. (DE-627)726491810 (DE-600)2682472-3 2192-113X nnns volume:11 year:2022 number:1 day:19 month:11 https://dx.doi.org/10.1186/s13677-022-00350-1 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2022 1 19 11 |
allfields_unstemmed |
10.1186/s13677-022-00350-1 doi (DE-627)SPR048668710 (SPR)s13677-022-00350-1-e DE-627 ger DE-627 rakwb eng Zhao, Xiaoping verfasserin aut Bearing fault diagnosis method based on improved Siamese neural network with small sample 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2022 Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. Rolling bearing (dpeaa)DE-He213 Siamese neural network (dpeaa)DE-He213 Small sample (dpeaa)DE-He213 Fault diagnosis (dpeaa)DE-He213 Ma, Mengyao aut Shao, Fan aut Enthalten in Journal of Cloud Computing Berlin : SpringerOpen, 2012 11(2022), 1 vom: 19. Nov. (DE-627)726491810 (DE-600)2682472-3 2192-113X nnns volume:11 year:2022 number:1 day:19 month:11 https://dx.doi.org/10.1186/s13677-022-00350-1 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2022 1 19 11 |
allfieldsGer |
10.1186/s13677-022-00350-1 doi (DE-627)SPR048668710 (SPR)s13677-022-00350-1-e DE-627 ger DE-627 rakwb eng Zhao, Xiaoping verfasserin aut Bearing fault diagnosis method based on improved Siamese neural network with small sample 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2022 Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. Rolling bearing (dpeaa)DE-He213 Siamese neural network (dpeaa)DE-He213 Small sample (dpeaa)DE-He213 Fault diagnosis (dpeaa)DE-He213 Ma, Mengyao aut Shao, Fan aut Enthalten in Journal of Cloud Computing Berlin : SpringerOpen, 2012 11(2022), 1 vom: 19. Nov. (DE-627)726491810 (DE-600)2682472-3 2192-113X nnns volume:11 year:2022 number:1 day:19 month:11 https://dx.doi.org/10.1186/s13677-022-00350-1 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2022 1 19 11 |
allfieldsSound |
10.1186/s13677-022-00350-1 doi (DE-627)SPR048668710 (SPR)s13677-022-00350-1-e DE-627 ger DE-627 rakwb eng Zhao, Xiaoping verfasserin aut Bearing fault diagnosis method based on improved Siamese neural network with small sample 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2022 Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. Rolling bearing (dpeaa)DE-He213 Siamese neural network (dpeaa)DE-He213 Small sample (dpeaa)DE-He213 Fault diagnosis (dpeaa)DE-He213 Ma, Mengyao aut Shao, Fan aut Enthalten in Journal of Cloud Computing Berlin : SpringerOpen, 2012 11(2022), 1 vom: 19. Nov. (DE-627)726491810 (DE-600)2682472-3 2192-113X nnns volume:11 year:2022 number:1 day:19 month:11 https://dx.doi.org/10.1186/s13677-022-00350-1 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2022 1 19 11 |
language |
English |
source |
Enthalten in Journal of Cloud Computing 11(2022), 1 vom: 19. Nov. volume:11 year:2022 number:1 day:19 month:11 |
sourceStr |
Enthalten in Journal of Cloud Computing 11(2022), 1 vom: 19. Nov. volume:11 year:2022 number:1 day:19 month:11 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Rolling bearing Siamese neural network Small sample Fault diagnosis |
isfreeaccess_bool |
true |
container_title |
Journal of Cloud Computing |
authorswithroles_txt_mv |
Zhao, Xiaoping @@aut@@ Ma, Mengyao @@aut@@ Shao, Fan @@aut@@ |
publishDateDaySort_date |
2022-11-19T00:00:00Z |
hierarchy_top_id |
726491810 |
id |
SPR048668710 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR048668710</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230509120510.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221119s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1186/s13677-022-00350-1</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR048668710</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s13677-022-00350-1-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhao, Xiaoping</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Bearing fault diagnosis method based on improved Siamese neural network with small sample</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s) 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Rolling bearing</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Siamese neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Small sample</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fault diagnosis</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ma, Mengyao</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shao, Fan</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Journal of Cloud Computing</subfield><subfield code="d">Berlin : SpringerOpen, 2012</subfield><subfield code="g">11(2022), 1 vom: 19. Nov.</subfield><subfield code="w">(DE-627)726491810</subfield><subfield code="w">(DE-600)2682472-3</subfield><subfield code="x">2192-113X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:11</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:1</subfield><subfield code="g">day:19</subfield><subfield code="g">month:11</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1186/s13677-022-00350-1</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">11</subfield><subfield code="j">2022</subfield><subfield code="e">1</subfield><subfield code="b">19</subfield><subfield code="c">11</subfield></datafield></record></collection>
|
author |
Zhao, Xiaoping |
spellingShingle |
Zhao, Xiaoping misc Rolling bearing misc Siamese neural network misc Small sample misc Fault diagnosis Bearing fault diagnosis method based on improved Siamese neural network with small sample |
authorStr |
Zhao, Xiaoping |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)726491810 |
format |
electronic Article |
delete_txt_mv |
keep |
author_role |
aut aut aut |
collection |
springer |
remote_str |
true |
illustrated |
Not Illustrated |
issn |
2192-113X |
topic_title |
Bearing fault diagnosis method based on improved Siamese neural network with small sample Rolling bearing (dpeaa)DE-He213 Siamese neural network (dpeaa)DE-He213 Small sample (dpeaa)DE-He213 Fault diagnosis (dpeaa)DE-He213 |
topic |
misc Rolling bearing misc Siamese neural network misc Small sample misc Fault diagnosis |
topic_unstemmed |
misc Rolling bearing misc Siamese neural network misc Small sample misc Fault diagnosis |
topic_browse |
misc Rolling bearing misc Siamese neural network misc Small sample misc Fault diagnosis |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
cr |
hierarchy_parent_title |
Journal of Cloud Computing |
hierarchy_parent_id |
726491810 |
hierarchy_top_title |
Journal of Cloud Computing |
isfreeaccess_txt |
true |
familylinks_str_mv |
(DE-627)726491810 (DE-600)2682472-3 |
title |
Bearing fault diagnosis method based on improved Siamese neural network with small sample |
ctrlnum |
(DE-627)SPR048668710 (SPR)s13677-022-00350-1-e |
title_full |
Bearing fault diagnosis method based on improved Siamese neural network with small sample |
author_sort |
Zhao, Xiaoping |
journal |
Journal of Cloud Computing |
journalStr |
Journal of Cloud Computing |
lang_code |
eng |
isOA_bool |
true |
recordtype |
marc |
publishDateSort |
2022 |
contenttype_str_mv |
txt |
author_browse |
Zhao, Xiaoping Ma, Mengyao Shao, Fan |
container_volume |
11 |
format_se |
Elektronische Aufsätze |
author-letter |
Zhao, Xiaoping |
doi_str_mv |
10.1186/s13677-022-00350-1 |
title_sort |
bearing fault diagnosis method based on improved siamese neural network with small sample |
title_auth |
Bearing fault diagnosis method based on improved Siamese neural network with small sample |
abstract |
Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. © The Author(s) 2022 |
abstractGer |
Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. © The Author(s) 2022 |
abstract_unstemmed |
Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples. © The Author(s) 2022 |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 |
container_issue |
1 |
title_short |
Bearing fault diagnosis method based on improved Siamese neural network with small sample |
url |
https://dx.doi.org/10.1186/s13677-022-00350-1 |
remote_bool |
true |
author2 |
Ma, Mengyao Shao, Fan |
author2Str |
Ma, Mengyao Shao, Fan |
ppnlink |
726491810 |
mediatype_str_mv |
c |
isOA_txt |
true |
hochschulschrift_bool |
false |
doi_str |
10.1186/s13677-022-00350-1 |
up_date |
2024-07-03T20:42:53.658Z |
_version_ |
1803592006273859585 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">SPR048668710</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230509120510.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221119s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1186/s13677-022-00350-1</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR048668710</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s13677-022-00350-1-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhao, Xiaoping</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Bearing fault diagnosis method based on improved Siamese neural network with small sample</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s) 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Fault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be obtained, which leads to an unsatisfactory effect of traditional fault diagnosis models based on data-driven methods. Therefore, this study proposes a small-sample bearing fault diagnosis method based on an improved Siamese neural network (ISNN). This method adds a classification branch to the standard Siamese network and replaces the common Euclidean distance measurement with a network measurement. The model includes three networks: a feature extraction network, a relationship measurement network, and a fault classification network. First, the fault samples were input into the same feature extraction network in pairs, and a long and short-term memory (LSTM) network and convolutional neural network (CNN) were used to map the bearing signal data to the low-dimensional feature space. Then, the extracted sample features were measured for similarity by the relationship measurement network; at the same time, the features were input into the classification network to complete the bearing fault recognition. When the number of training samples was particularly small (training set A, 10 samples), the accuracy of 1D CNN, Prototype net and Siamese net were 49.8%, 60.2% and 58.6% respectively, while the accuracy of the proposed ISNN method was 84.1%. For the 100-sample case of training set D, the accuracy of 1D CNN was improved to 93.4%, which was still higher than that of prototype and Siam network, while the accuracy of ISNN method reached 98.1%.The experimental results show that the method in this study achieved higher fault diagnosis accuracy and better generalization in the case of small samples.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Rolling bearing</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Siamese neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Small sample</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fault diagnosis</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ma, Mengyao</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shao, Fan</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Journal of Cloud Computing</subfield><subfield code="d">Berlin : SpringerOpen, 2012</subfield><subfield code="g">11(2022), 1 vom: 19. Nov.</subfield><subfield code="w">(DE-627)726491810</subfield><subfield code="w">(DE-600)2682472-3</subfield><subfield code="x">2192-113X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:11</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:1</subfield><subfield code="g">day:19</subfield><subfield code="g">month:11</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1186/s13677-022-00350-1</subfield><subfield code="z">kostenfrei</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">11</subfield><subfield code="j">2022</subfield><subfield code="e">1</subfield><subfield code="b">19</subfield><subfield code="c">11</subfield></datafield></record></collection>
|
score |
7.4002085 |