An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy
Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a norm...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Shang, Zhiwu [verfasserIn] Li, Wanxiang [verfasserIn] Gao, Maosheng [verfasserIn] Liu, Xia [verfasserIn] Yu, Yan [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s) 2021 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Chinese Journal of Mechanical Engineering - Chinese Mechanical Engineering Society, 2012, 34(2021), 1 vom: 09. Juni |
|---|---|
| Übergeordnetes Werk: |
volume:34 ; year:2021 ; number:1 ; day:09 ; month:06 |
| Links: |
|---|
| DOI / URN: |
10.1186/s10033-021-00580-5 |
|---|
| Katalog-ID: |
SPR044259131 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR044259131 | ||
| 003 | DE-627 | ||
| 005 | 20210610064748.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 210610s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s10033-021-00580-5 |2 doi | |
| 035 | |a (DE-627)SPR044259131 | ||
| 035 | |a (SPR)s10033-021-00580-5-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Shang, Zhiwu |e verfasserin |4 aut | |
| 245 | 1 | 3 | |a An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy |
| 264 | 1 | |c 2021 | |
| 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) 2021 | ||
| 520 | |a Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. | ||
| 650 | 4 | |a Fault diagnosis |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Feature fusion |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Information entropy |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Deep autoencoder |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Deep belief network |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Li, Wanxiang |e verfasserin |4 aut | |
| 700 | 1 | |a Gao, Maosheng |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Xia |e verfasserin |4 aut | |
| 700 | 1 | |a Yu, Yan |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Chinese Journal of Mechanical Engineering |d Chinese Mechanical Engineering Society, 2012 |g 34(2021), 1 vom: 09. Juni |w (DE-627)SPR008124000 |7 nnns |
| 773 | 1 | 8 | |g volume:34 |g year:2021 |g number:1 |g day:09 |g month:06 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1186/s10033-021-00580-5 |z kostenfrei |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 951 | |a AR | ||
| 952 | |d 34 |j 2021 |e 1 |b 09 |c 06 | ||
| author_variant |
z s zs w l wl m g mg x l xl y y yy |
|---|---|
| matchkey_str |
shangzhiwuliwanxianggaomaoshengliuxiayuy:2021----:nnelgnfutigoimtoomlicldefaueuin |
| hierarchy_sort_str |
2021 |
| publishDate |
2021 |
| allfields |
10.1186/s10033-021-00580-5 doi (DE-627)SPR044259131 (SPR)s10033-021-00580-5-e DE-627 ger DE-627 rakwb eng Shang, Zhiwu verfasserin aut An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2021 Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. Fault diagnosis (dpeaa)DE-He213 Feature fusion (dpeaa)DE-He213 Information entropy (dpeaa)DE-He213 Deep autoencoder (dpeaa)DE-He213 Deep belief network (dpeaa)DE-He213 Li, Wanxiang verfasserin aut Gao, Maosheng verfasserin aut Liu, Xia verfasserin aut Yu, Yan verfasserin aut Enthalten in Chinese Journal of Mechanical Engineering Chinese Mechanical Engineering Society, 2012 34(2021), 1 vom: 09. Juni (DE-627)SPR008124000 nnns volume:34 year:2021 number:1 day:09 month:06 https://dx.doi.org/10.1186/s10033-021-00580-5 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 34 2021 1 09 06 |
| spelling |
10.1186/s10033-021-00580-5 doi (DE-627)SPR044259131 (SPR)s10033-021-00580-5-e DE-627 ger DE-627 rakwb eng Shang, Zhiwu verfasserin aut An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2021 Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. Fault diagnosis (dpeaa)DE-He213 Feature fusion (dpeaa)DE-He213 Information entropy (dpeaa)DE-He213 Deep autoencoder (dpeaa)DE-He213 Deep belief network (dpeaa)DE-He213 Li, Wanxiang verfasserin aut Gao, Maosheng verfasserin aut Liu, Xia verfasserin aut Yu, Yan verfasserin aut Enthalten in Chinese Journal of Mechanical Engineering Chinese Mechanical Engineering Society, 2012 34(2021), 1 vom: 09. Juni (DE-627)SPR008124000 nnns volume:34 year:2021 number:1 day:09 month:06 https://dx.doi.org/10.1186/s10033-021-00580-5 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 34 2021 1 09 06 |
| allfields_unstemmed |
10.1186/s10033-021-00580-5 doi (DE-627)SPR044259131 (SPR)s10033-021-00580-5-e DE-627 ger DE-627 rakwb eng Shang, Zhiwu verfasserin aut An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2021 Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. Fault diagnosis (dpeaa)DE-He213 Feature fusion (dpeaa)DE-He213 Information entropy (dpeaa)DE-He213 Deep autoencoder (dpeaa)DE-He213 Deep belief network (dpeaa)DE-He213 Li, Wanxiang verfasserin aut Gao, Maosheng verfasserin aut Liu, Xia verfasserin aut Yu, Yan verfasserin aut Enthalten in Chinese Journal of Mechanical Engineering Chinese Mechanical Engineering Society, 2012 34(2021), 1 vom: 09. Juni (DE-627)SPR008124000 nnns volume:34 year:2021 number:1 day:09 month:06 https://dx.doi.org/10.1186/s10033-021-00580-5 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 34 2021 1 09 06 |
| allfieldsGer |
10.1186/s10033-021-00580-5 doi (DE-627)SPR044259131 (SPR)s10033-021-00580-5-e DE-627 ger DE-627 rakwb eng Shang, Zhiwu verfasserin aut An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2021 Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. Fault diagnosis (dpeaa)DE-He213 Feature fusion (dpeaa)DE-He213 Information entropy (dpeaa)DE-He213 Deep autoencoder (dpeaa)DE-He213 Deep belief network (dpeaa)DE-He213 Li, Wanxiang verfasserin aut Gao, Maosheng verfasserin aut Liu, Xia verfasserin aut Yu, Yan verfasserin aut Enthalten in Chinese Journal of Mechanical Engineering Chinese Mechanical Engineering Society, 2012 34(2021), 1 vom: 09. Juni (DE-627)SPR008124000 nnns volume:34 year:2021 number:1 day:09 month:06 https://dx.doi.org/10.1186/s10033-021-00580-5 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 34 2021 1 09 06 |
| allfieldsSound |
10.1186/s10033-021-00580-5 doi (DE-627)SPR044259131 (SPR)s10033-021-00580-5-e DE-627 ger DE-627 rakwb eng Shang, Zhiwu verfasserin aut An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s) 2021 Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. Fault diagnosis (dpeaa)DE-He213 Feature fusion (dpeaa)DE-He213 Information entropy (dpeaa)DE-He213 Deep autoencoder (dpeaa)DE-He213 Deep belief network (dpeaa)DE-He213 Li, Wanxiang verfasserin aut Gao, Maosheng verfasserin aut Liu, Xia verfasserin aut Yu, Yan verfasserin aut Enthalten in Chinese Journal of Mechanical Engineering Chinese Mechanical Engineering Society, 2012 34(2021), 1 vom: 09. Juni (DE-627)SPR008124000 nnns volume:34 year:2021 number:1 day:09 month:06 https://dx.doi.org/10.1186/s10033-021-00580-5 kostenfrei Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 34 2021 1 09 06 |
| language |
English |
| source |
Enthalten in Chinese Journal of Mechanical Engineering 34(2021), 1 vom: 09. Juni volume:34 year:2021 number:1 day:09 month:06 |
| sourceStr |
Enthalten in Chinese Journal of Mechanical Engineering 34(2021), 1 vom: 09. Juni volume:34 year:2021 number:1 day:09 month:06 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Fault diagnosis Feature fusion Information entropy Deep autoencoder Deep belief network |
| isfreeaccess_bool |
true |
| container_title |
Chinese Journal of Mechanical Engineering |
| authorswithroles_txt_mv |
Shang, Zhiwu @@aut@@ Li, Wanxiang @@aut@@ Gao, Maosheng @@aut@@ Liu, Xia @@aut@@ Yu, Yan @@aut@@ |
| publishDateDaySort_date |
2021-06-09T00:00:00Z |
| hierarchy_top_id |
SPR008124000 |
| id |
SPR044259131 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">SPR044259131</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20210610064748.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210610s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1186/s10033-021-00580-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR044259131</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s10033-021-00580-5-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">Shang, Zhiwu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="3"><subfield code="a">An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</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) 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fault diagnosis</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Feature fusion</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Information entropy</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep autoencoder</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep belief network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Wanxiang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gao, Maosheng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Xia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yu, Yan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Chinese Journal of Mechanical Engineering</subfield><subfield code="d">Chinese Mechanical Engineering Society, 2012</subfield><subfield code="g">34(2021), 1 vom: 09. Juni</subfield><subfield code="w">(DE-627)SPR008124000</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:1</subfield><subfield code="g">day:09</subfield><subfield code="g">month:06</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1186/s10033-021-00580-5</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="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2021</subfield><subfield code="e">1</subfield><subfield code="b">09</subfield><subfield code="c">06</subfield></datafield></record></collection>
|
| author |
Shang, Zhiwu |
| spellingShingle |
Shang, Zhiwu misc Fault diagnosis misc Feature fusion misc Information entropy misc Deep autoencoder misc Deep belief network An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy |
| authorStr |
Shang, Zhiwu |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)SPR008124000 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy Fault diagnosis (dpeaa)DE-He213 Feature fusion (dpeaa)DE-He213 Information entropy (dpeaa)DE-He213 Deep autoencoder (dpeaa)DE-He213 Deep belief network (dpeaa)DE-He213 |
| topic |
misc Fault diagnosis misc Feature fusion misc Information entropy misc Deep autoencoder misc Deep belief network |
| topic_unstemmed |
misc Fault diagnosis misc Feature fusion misc Information entropy misc Deep autoencoder misc Deep belief network |
| topic_browse |
misc Fault diagnosis misc Feature fusion misc Information entropy misc Deep autoencoder misc Deep belief network |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Chinese Journal of Mechanical Engineering |
| hierarchy_parent_id |
SPR008124000 |
| hierarchy_top_title |
Chinese Journal of Mechanical Engineering |
| isfreeaccess_txt |
true |
| familylinks_str_mv |
(DE-627)SPR008124000 |
| title |
An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy |
| ctrlnum |
(DE-627)SPR044259131 (SPR)s10033-021-00580-5-e |
| title_full |
An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy |
| author_sort |
Shang, Zhiwu |
| journal |
Chinese Journal of Mechanical Engineering |
| journalStr |
Chinese Journal of Mechanical Engineering |
| lang_code |
eng |
| isOA_bool |
true |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
txt |
| author_browse |
Shang, Zhiwu Li, Wanxiang Gao, Maosheng Liu, Xia Yu, Yan |
| container_volume |
34 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Shang, Zhiwu |
| doi_str_mv |
10.1186/s10033-021-00580-5 |
| author2-role |
verfasserin |
| title_sort |
intelligent fault diagnosis method of multi-scale deep feature fusion based on information entropy |
| title_auth |
An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy |
| abstract |
Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. © The Author(s) 2021 |
| abstractGer |
Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. © The Author(s) 2021 |
| abstract_unstemmed |
Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy. © The Author(s) 2021 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER |
| container_issue |
1 |
| title_short |
An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy |
| url |
https://dx.doi.org/10.1186/s10033-021-00580-5 |
| remote_bool |
true |
| author2 |
Li, Wanxiang Gao, Maosheng Liu, Xia Yu, Yan |
| author2Str |
Li, Wanxiang Gao, Maosheng Liu, Xia Yu, Yan |
| ppnlink |
SPR008124000 |
| mediatype_str_mv |
c |
| isOA_txt |
true |
| hochschulschrift_bool |
false |
| doi_str |
10.1186/s10033-021-00580-5 |
| up_date |
2024-07-03T23:47:10.376Z |
| _version_ |
1803603600082993152 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">SPR044259131</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20210610064748.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210610s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1186/s10033-021-00580-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR044259131</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s10033-021-00580-5-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">Shang, Zhiwu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="3"><subfield code="a">An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</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) 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract For a single-structure deep learning fault diagnosis model, its disadvantages are an insufficient feature extraction and weak fault classification capability. This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy. First, a normal autoencoder, denoising autoencoder, sparse autoencoder, and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extraction structure. A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features. Finally, the advantage of the deep belief network probability model is used as the fault classifier to identify the faults. The effectiveness of the proposed method was verified by a gearbox test-bed. Experimental results show that, compared with traditional and existing intelligent fault diagnosis methods, the proposed method can obtain representative information and features from the raw data with higher classification accuracy.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fault diagnosis</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Feature fusion</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Information entropy</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep autoencoder</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Deep belief network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Wanxiang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gao, Maosheng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Xia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yu, Yan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Chinese Journal of Mechanical Engineering</subfield><subfield code="d">Chinese Mechanical Engineering Society, 2012</subfield><subfield code="g">34(2021), 1 vom: 09. Juni</subfield><subfield code="w">(DE-627)SPR008124000</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:1</subfield><subfield code="g">day:09</subfield><subfield code="g">month:06</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1186/s10033-021-00580-5</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="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2021</subfield><subfield code="e">1</subfield><subfield code="b">09</subfield><subfield code="c">06</subfield></datafield></record></collection>
|
| score |
7.3999033 |