A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction
Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health st...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Jang, Jaeyeon [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
|---|
| Übergeordnetes Werk: |
Enthalten in: Soft Computing - Springer-Verlag, 2003, 27(2022), 7 vom: 09. Nov., Seite 3641-3654 |
|---|---|
| Übergeordnetes Werk: |
volume:27 ; year:2022 ; number:7 ; day:09 ; month:11 ; pages:3641-3654 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00500-022-07625-4 |
|---|
| Katalog-ID: |
SPR049589431 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR049589431 | ||
| 003 | DE-627 | ||
| 005 | 20230323103901.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230323s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00500-022-07625-4 |2 doi | |
| 035 | |a (DE-627)SPR049589431 | ||
| 035 | |a (SPR)s00500-022-07625-4-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Jang, Jaeyeon |e verfasserin |0 (orcid)0000-0001-6255-2044 |4 aut | |
| 245 | 1 | 2 | |a A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction |
| 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), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
| 520 | |a Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. | ||
| 650 | 4 | |a Health index |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Prognostics and health management |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Remaining useful life |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Stacked denoising autoencoder |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Uncertainty management |7 (dpeaa)DE-He213 | |
| 773 | 0 | 8 | |i Enthalten in |t Soft Computing |d Springer-Verlag, 2003 |g 27(2022), 7 vom: 09. Nov., Seite 3641-3654 |w (DE-627)SPR006469531 |7 nnns |
| 773 | 1 | 8 | |g volume:27 |g year:2022 |g number:7 |g day:09 |g month:11 |g pages:3641-3654 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s00500-022-07625-4 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 951 | |a AR | ||
| 952 | |d 27 |j 2022 |e 7 |b 09 |c 11 |h 3641-3654 | ||
| author_variant |
j j jj |
|---|---|
| matchkey_str |
jangjaeyeon:2022----:delannbsdodtoassehatidxehdoeuehucranyfe |
| hierarchy_sort_str |
2022 |
| publishDate |
2022 |
| allfields |
10.1007/s00500-022-07625-4 doi (DE-627)SPR049589431 (SPR)s00500-022-07625-4-e DE-627 ger DE-627 rakwb eng Jang, Jaeyeon verfasserin (orcid)0000-0001-6255-2044 aut A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. Health index (dpeaa)DE-He213 Prognostics and health management (dpeaa)DE-He213 Remaining useful life (dpeaa)DE-He213 Stacked denoising autoencoder (dpeaa)DE-He213 Uncertainty management (dpeaa)DE-He213 Enthalten in Soft Computing Springer-Verlag, 2003 27(2022), 7 vom: 09. Nov., Seite 3641-3654 (DE-627)SPR006469531 nnns volume:27 year:2022 number:7 day:09 month:11 pages:3641-3654 https://dx.doi.org/10.1007/s00500-022-07625-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2022 7 09 11 3641-3654 |
| spelling |
10.1007/s00500-022-07625-4 doi (DE-627)SPR049589431 (SPR)s00500-022-07625-4-e DE-627 ger DE-627 rakwb eng Jang, Jaeyeon verfasserin (orcid)0000-0001-6255-2044 aut A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. Health index (dpeaa)DE-He213 Prognostics and health management (dpeaa)DE-He213 Remaining useful life (dpeaa)DE-He213 Stacked denoising autoencoder (dpeaa)DE-He213 Uncertainty management (dpeaa)DE-He213 Enthalten in Soft Computing Springer-Verlag, 2003 27(2022), 7 vom: 09. Nov., Seite 3641-3654 (DE-627)SPR006469531 nnns volume:27 year:2022 number:7 day:09 month:11 pages:3641-3654 https://dx.doi.org/10.1007/s00500-022-07625-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2022 7 09 11 3641-3654 |
| allfields_unstemmed |
10.1007/s00500-022-07625-4 doi (DE-627)SPR049589431 (SPR)s00500-022-07625-4-e DE-627 ger DE-627 rakwb eng Jang, Jaeyeon verfasserin (orcid)0000-0001-6255-2044 aut A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. Health index (dpeaa)DE-He213 Prognostics and health management (dpeaa)DE-He213 Remaining useful life (dpeaa)DE-He213 Stacked denoising autoencoder (dpeaa)DE-He213 Uncertainty management (dpeaa)DE-He213 Enthalten in Soft Computing Springer-Verlag, 2003 27(2022), 7 vom: 09. Nov., Seite 3641-3654 (DE-627)SPR006469531 nnns volume:27 year:2022 number:7 day:09 month:11 pages:3641-3654 https://dx.doi.org/10.1007/s00500-022-07625-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2022 7 09 11 3641-3654 |
| allfieldsGer |
10.1007/s00500-022-07625-4 doi (DE-627)SPR049589431 (SPR)s00500-022-07625-4-e DE-627 ger DE-627 rakwb eng Jang, Jaeyeon verfasserin (orcid)0000-0001-6255-2044 aut A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. Health index (dpeaa)DE-He213 Prognostics and health management (dpeaa)DE-He213 Remaining useful life (dpeaa)DE-He213 Stacked denoising autoencoder (dpeaa)DE-He213 Uncertainty management (dpeaa)DE-He213 Enthalten in Soft Computing Springer-Verlag, 2003 27(2022), 7 vom: 09. Nov., Seite 3641-3654 (DE-627)SPR006469531 nnns volume:27 year:2022 number:7 day:09 month:11 pages:3641-3654 https://dx.doi.org/10.1007/s00500-022-07625-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2022 7 09 11 3641-3654 |
| allfieldsSound |
10.1007/s00500-022-07625-4 doi (DE-627)SPR049589431 (SPR)s00500-022-07625-4-e DE-627 ger DE-627 rakwb eng Jang, Jaeyeon verfasserin (orcid)0000-0001-6255-2044 aut A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. Health index (dpeaa)DE-He213 Prognostics and health management (dpeaa)DE-He213 Remaining useful life (dpeaa)DE-He213 Stacked denoising autoencoder (dpeaa)DE-He213 Uncertainty management (dpeaa)DE-He213 Enthalten in Soft Computing Springer-Verlag, 2003 27(2022), 7 vom: 09. Nov., Seite 3641-3654 (DE-627)SPR006469531 nnns volume:27 year:2022 number:7 day:09 month:11 pages:3641-3654 https://dx.doi.org/10.1007/s00500-022-07625-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER AR 27 2022 7 09 11 3641-3654 |
| language |
English |
| source |
Enthalten in Soft Computing 27(2022), 7 vom: 09. Nov., Seite 3641-3654 volume:27 year:2022 number:7 day:09 month:11 pages:3641-3654 |
| sourceStr |
Enthalten in Soft Computing 27(2022), 7 vom: 09. Nov., Seite 3641-3654 volume:27 year:2022 number:7 day:09 month:11 pages:3641-3654 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Health index Prognostics and health management Remaining useful life Stacked denoising autoencoder Uncertainty management |
| isfreeaccess_bool |
false |
| container_title |
Soft Computing |
| authorswithroles_txt_mv |
Jang, Jaeyeon @@aut@@ |
| publishDateDaySort_date |
2022-11-09T00:00:00Z |
| hierarchy_top_id |
SPR006469531 |
| id |
SPR049589431 |
| 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">SPR049589431</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230323103901.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230323s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00500-022-07625-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR049589431</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s00500-022-07625-4-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">Jang, Jaeyeon</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-6255-2044</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction</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), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Health index</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Prognostics and health management</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Remaining useful life</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Stacked denoising autoencoder</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Uncertainty management</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Soft Computing</subfield><subfield code="d">Springer-Verlag, 2003</subfield><subfield code="g">27(2022), 7 vom: 09. Nov., Seite 3641-3654</subfield><subfield code="w">(DE-627)SPR006469531</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:27</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:7</subfield><subfield code="g">day:09</subfield><subfield code="g">month:11</subfield><subfield code="g">pages:3641-3654</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s00500-022-07625-4</subfield><subfield code="z">lizenzpflichtig</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">27</subfield><subfield code="j">2022</subfield><subfield code="e">7</subfield><subfield code="b">09</subfield><subfield code="c">11</subfield><subfield code="h">3641-3654</subfield></datafield></record></collection>
|
| author |
Jang, Jaeyeon |
| spellingShingle |
Jang, Jaeyeon misc Health index misc Prognostics and health management misc Remaining useful life misc Stacked denoising autoencoder misc Uncertainty management A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction |
| authorStr |
Jang, Jaeyeon |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)SPR006469531 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction Health index (dpeaa)DE-He213 Prognostics and health management (dpeaa)DE-He213 Remaining useful life (dpeaa)DE-He213 Stacked denoising autoencoder (dpeaa)DE-He213 Uncertainty management (dpeaa)DE-He213 |
| topic |
misc Health index misc Prognostics and health management misc Remaining useful life misc Stacked denoising autoencoder misc Uncertainty management |
| topic_unstemmed |
misc Health index misc Prognostics and health management misc Remaining useful life misc Stacked denoising autoencoder misc Uncertainty management |
| topic_browse |
misc Health index misc Prognostics and health management misc Remaining useful life misc Stacked denoising autoencoder misc Uncertainty management |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Soft Computing |
| hierarchy_parent_id |
SPR006469531 |
| hierarchy_top_title |
Soft Computing |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)SPR006469531 |
| title |
A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction |
| ctrlnum |
(DE-627)SPR049589431 (SPR)s00500-022-07625-4-e |
| title_full |
A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction |
| author_sort |
Jang, Jaeyeon |
| journal |
Soft Computing |
| journalStr |
Soft Computing |
| lang_code |
eng |
| isOA_bool |
false |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| container_start_page |
3641 |
| author_browse |
Jang, Jaeyeon |
| container_volume |
27 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Jang, Jaeyeon |
| doi_str_mv |
10.1007/s00500-022-07625-4 |
| normlink |
(ORCID)0000-0001-6255-2044 |
| normlink_prefix_str_mv |
(orcid)0000-0001-6255-2044 |
| title_sort |
deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction |
| title_auth |
A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction |
| abstract |
Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| abstractGer |
Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| abstract_unstemmed |
Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER |
| container_issue |
7 |
| title_short |
A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction |
| url |
https://dx.doi.org/10.1007/s00500-022-07625-4 |
| remote_bool |
true |
| ppnlink |
SPR006469531 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00500-022-07625-4 |
| up_date |
2024-07-04T01:26:49.289Z |
| _version_ |
1803609869428719616 |
| 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">SPR049589431</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230323103901.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230323s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00500-022-07625-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR049589431</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s00500-022-07625-4-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">Jang, Jaeyeon</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-6255-2044</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction</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), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Health index</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Prognostics and health management</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Remaining useful life</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Stacked denoising autoencoder</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Uncertainty management</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Soft Computing</subfield><subfield code="d">Springer-Verlag, 2003</subfield><subfield code="g">27(2022), 7 vom: 09. Nov., Seite 3641-3654</subfield><subfield code="w">(DE-627)SPR006469531</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:27</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:7</subfield><subfield code="g">day:09</subfield><subfield code="g">month:11</subfield><subfield code="g">pages:3641-3654</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s00500-022-07625-4</subfield><subfield code="z">lizenzpflichtig</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">27</subfield><subfield code="j">2022</subfield><subfield code="e">7</subfield><subfield code="b">09</subfield><subfield code="c">11</subfield><subfield code="h">3641-3654</subfield></datafield></record></collection>
|
| score |
7.4018965 |