Fusing physics-based and deep learning models for prognostics
Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset f...
Gespeichert in:
| Veröffentlicht in: | Reliability engineering & system safety Jg. 217; S. 107961 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Barking
Elsevier Ltd
01.01.2022
Elsevier BV |
| Schlagworte: | |
| ISSN: | 0951-8320, 1879-0836, 1879-0836 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physics-based performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising run-to-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance.
•Novel hybrid framework for prognostics of complex safety-critical systems proposed.•The framework combines deep learning and physics-based performance models.•Deep neural networks are trained with physics-augmented features for RUL prediction.•Framework evaluated on the new CMPASS aero-engine degradation dataset.•The proposed framework outperforms equivalent purely data-driven approaches. |
|---|---|
| AbstractList | Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physics-based performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising run-to-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance. Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physics-based performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising run-to-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance. •Novel hybrid framework for prognostics of complex safety-critical systems proposed.•The framework combines deep learning and physics-based performance models.•Deep neural networks are trained with physics-augmented features for RUL prediction.•Framework evaluated on the new CMPASS aero-engine degradation dataset.•The proposed framework outperforms equivalent purely data-driven approaches. |
| ArticleNumber | 107961 |
| Author | Kulkarni, Chetan Fink, Olga Arias Chao, Manuel Goebel, Kai |
| Author_xml | – sequence: 1 givenname: Manuel orcidid: 0000-0001-6134-3582 surname: Arias Chao fullname: Arias Chao, Manuel email: manuel.arias@ethz.ch organization: Chair of Intelligent Maintenance Systems, ETH Zurich, Switzerland – sequence: 2 givenname: Chetan surname: Kulkarni fullname: Kulkarni, Chetan email: chetan.s.kulkarni@nasa.gov organization: KBR, Inc., NASA Ames Research Center, USA – sequence: 3 givenname: Kai orcidid: 0000-0002-0240-0943 surname: Goebel fullname: Goebel, Kai email: kai.goebel@ltu.se organization: Luleå University of Technology, Operation and Maintenance Engineering, Luleå, Sweden – sequence: 4 givenname: Olga orcidid: 0000-0002-9546-1488 surname: Fink fullname: Fink, Olga email: ofink@ethz.ch organization: Chair of Intelligent Maintenance Systems, ETH Zurich, Switzerland |
| BackLink | https://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87121$$DView record from Swedish Publication Index |
| BookMark | eNp9kE1LxDAQhoOs4Lr6BzwVvNp10o80AT0s6ycIXtRrSNPpmqUmNWkV_71ZKh48eBqYeZ7h5T0kM-ssEnJCYUmBsvPt0mMIywwyGheVYHSPzCmvRAo8ZzMyB1HSlOcZHJDDELYAUIiympPLmzEYu0n6169gdEhrFbBJlG2SBrFPOlTe7u5vrsEuJK3zSe_dxrowRPyI7LeqC3j8Mxfk-eb6aX2XPjze3q9XD6kuQAypKvNMYFVALYDzXGeQ1yLnDGJcWjU1Q6xbVmDFtdBtKTgi56hzphmURY35gpxNf8Mn9mMte2_elP-SThl5ZV5W0vmN7IZR8opmNOKnEx6jvo8YBrl1o7cxocwYFawCJspIZROlvQvBY_v7loLctSq3cteq3LUqp1ajxP9I2gxqMM4OXpnuf_ViUmOR-GHQy6ANWo2N8agH2Tjzn_4NpmOUew |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2022_3203406 crossref_primary_10_2118_220725_PA crossref_primary_10_1002_qre_3698 crossref_primary_10_1016_j_ymssp_2025_113042 crossref_primary_10_1016_j_ress_2025_111730 crossref_primary_10_1177_14759217251324103 crossref_primary_10_1016_j_ymssp_2024_112192 crossref_primary_10_1109_JSEN_2023_3326487 crossref_primary_10_1016_j_renene_2024_122267 crossref_primary_10_1016_j_ifacol_2024_12_027 crossref_primary_10_1029_2022WR033318 crossref_primary_10_1088_1361_6501_ad83ea crossref_primary_10_1016_j_ymssp_2022_109610 crossref_primary_10_1007_s40430_025_05400_8 crossref_primary_10_1109_ACCESS_2025_3573400 crossref_primary_10_3390_s22249738 crossref_primary_10_1016_j_ress_2022_108676 crossref_primary_10_1145_3514228 crossref_primary_10_3390_aerospace12080725 crossref_primary_10_1109_JSEN_2025_3547323 crossref_primary_10_1088_1361_6501_adfcf9 crossref_primary_10_1007_s10845_023_02125_0 crossref_primary_10_1109_ACCESS_2025_3607733 crossref_primary_10_1038_s41598_023_33018_0 crossref_primary_10_1109_TIM_2025_3561378 crossref_primary_10_3390_ai5030074 crossref_primary_10_1109_TIM_2023_3260283 crossref_primary_10_1007_s10845_024_02398_z crossref_primary_10_1109_JSEN_2024_3514168 crossref_primary_10_1109_ACCESS_2024_3391823 crossref_primary_10_1080_24725854_2023_2223245 crossref_primary_10_1016_j_inffus_2025_103427 crossref_primary_10_1109_JSEN_2025_3563586 crossref_primary_10_1016_j_ymssp_2024_111120 crossref_primary_10_1016_j_ress_2024_110659 crossref_primary_10_1016_j_ymssp_2025_113200 crossref_primary_10_1109_TASE_2025_3549061 crossref_primary_10_1016_j_engappai_2023_106623 crossref_primary_10_3390_machines10110974 crossref_primary_10_1007_s00158_022_03425_4 crossref_primary_10_1109_MPEL_2024_3524742 crossref_primary_10_1016_j_measurement_2024_116345 crossref_primary_10_1680_jsmic_22_00003 crossref_primary_10_3390_aerospace12030175 crossref_primary_10_1016_j_engappai_2025_110246 crossref_primary_10_1007_s11071_024_10163_3 crossref_primary_10_3390_aerospace9050236 crossref_primary_10_1109_ACCESS_2022_3209205 crossref_primary_10_1007_s42484_024_00184_x crossref_primary_10_1016_j_ress_2023_109341 crossref_primary_10_1109_TASE_2023_3267860 crossref_primary_10_1088_1361_6501_ad0ad5 crossref_primary_10_1109_JIOT_2025_3569857 crossref_primary_10_3390_a15030098 crossref_primary_10_1002_qre_3445 crossref_primary_10_1016_j_ress_2024_110352 crossref_primary_10_1088_1361_6501_ad3b2c crossref_primary_10_1016_j_ress_2025_110893 crossref_primary_10_1007_s00521_024_10605_4 crossref_primary_10_3390_aerospace11030217 crossref_primary_10_3390_aerospace10060496 crossref_primary_10_3390_s23198124 crossref_primary_10_1016_j_apenergy_2025_125402 crossref_primary_10_1007_s10845_023_02077_5 crossref_primary_10_1109_JSEN_2024_3477489 crossref_primary_10_1109_OJITS_2025_3585274 crossref_primary_10_1080_23307706_2024_2398536 crossref_primary_10_3390_jlpea11040044 crossref_primary_10_1186_s10033_024_01173_8 crossref_primary_10_1016_j_ress_2024_110285 crossref_primary_10_1177_01423312241292756 crossref_primary_10_1016_j_engappai_2024_109556 crossref_primary_10_3390_coatings15060660 crossref_primary_10_1017_aer_2024_40 crossref_primary_10_1016_j_ress_2023_109723 crossref_primary_10_3390_aerospace11100809 crossref_primary_10_1016_j_asoc_2022_109533 crossref_primary_10_3390_jmse12111913 crossref_primary_10_1088_1361_6501_ad73f1 crossref_primary_10_1016_j_ress_2022_108908 crossref_primary_10_1109_TAES_2023_3338179 crossref_primary_10_1061_JAEEEZ_ASENG_5887 crossref_primary_10_1016_j_ress_2022_108628 crossref_primary_10_1016_j_aei_2023_101973 crossref_primary_10_1017_dce_2024_24 crossref_primary_10_1016_j_aei_2024_102566 crossref_primary_10_1016_j_ress_2022_108900 crossref_primary_10_1016_j_ress_2022_108989 crossref_primary_10_3390_pr10091764 crossref_primary_10_1080_08982112_2024_2385920 crossref_primary_10_1109_ACCESS_2023_3265722 crossref_primary_10_1088_1361_6501_ad2d50 crossref_primary_10_3390_aerospace10010010 crossref_primary_10_1088_1361_6501_ad5746 crossref_primary_10_1016_j_energy_2023_130153 crossref_primary_10_1109_TII_2023_3333933 crossref_primary_10_3390_aerospace10070644 crossref_primary_10_1038_s41598_025_09155_z crossref_primary_10_1016_j_autcon_2024_105648 crossref_primary_10_1142_S0218539325500068 crossref_primary_10_1016_j_apm_2023_07_011 crossref_primary_10_1016_j_engappai_2022_104926 crossref_primary_10_1016_j_engappai_2023_106707 crossref_primary_10_1115_1_4068697 crossref_primary_10_1016_j_apor_2024_104208 crossref_primary_10_1109_ACCESS_2022_3211258 crossref_primary_10_1109_TIM_2025_3551586 crossref_primary_10_1002_asmb_2930 crossref_primary_10_1016_j_apm_2023_05_038 crossref_primary_10_1177_14759217251368254 crossref_primary_10_1061_JHYEFF_HEENG_6316 crossref_primary_10_1016_j_eng_2024_12_034 crossref_primary_10_1088_2631_8695_ade04f crossref_primary_10_1016_j_ress_2025_110989 crossref_primary_10_1016_j_ress_2024_110394 crossref_primary_10_3390_s24061765 crossref_primary_10_1002_qre_3520 crossref_primary_10_1007_s00170_023_10969_2 crossref_primary_10_1007_s40747_025_01886_w crossref_primary_10_1016_j_ymssp_2023_110359 crossref_primary_10_1088_1361_648X_accdab crossref_primary_10_1109_ACCESS_2024_3387702 crossref_primary_10_1109_TASE_2023_3239004 crossref_primary_10_3390_machines10121137 crossref_primary_10_1016_j_ress_2022_108686 crossref_primary_10_1038_s42256_023_00662_0 crossref_primary_10_1109_TEM_2023_3268618 crossref_primary_10_1016_j_ress_2024_109974 crossref_primary_10_1038_s41598_023_37154_5 crossref_primary_10_1016_j_measurement_2024_114242 |
| Cites_doi | 10.3390/app9224813 10.3389/frai.2020.578613 10.1016/j.ress.2017.11.021 10.36001/phmconf.2019.v11i1.807 10.1214/14-STS511 10.1016/j.ress.2018.11.027 10.1109/ACCESS.2020.2987324 10.1115/1.4045293 10.3934/mbe.2019040 10.3390/data6010005 10.1016/j.ress.2020.106926 10.1016/j.ress.2020.107257 10.1109/TSMCA.2012.2207109 10.1016/j.ymssp.2017.11.024 10.1111/1467-9868.00294 10.1016/j.ress.2018.11.011 10.36001/phmconf.2019.v11i1.786 10.1016/j.engappai.2020.103678 10.1198/jasa.2009.ap07466 10.36001/phmconf.2019.v11i1.814 10.3390/s20164537 10.1109/TIE.2019.2962438 10.1109/ACCESS.2019.2920297 |
| ContentType | Journal Article |
| Copyright | 2021 The Authors Copyright Elsevier BV Jan 2022 |
| Copyright_xml | – notice: 2021 The Authors – notice: Copyright Elsevier BV Jan 2022 |
| DBID | 6I. AAFTH AAYXX CITATION 7ST 7TB 8FD C1K FR3 SOI ADTPV AOWAS D8T ZZAVC |
| DOI | 10.1016/j.ress.2021.107961 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef Environment Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Environmental Sciences and Pollution Management Engineering Research Database Environment Abstracts SwePub SwePub Articles SWEPUB Freely available online SwePub Articles full text |
| DatabaseTitle | CrossRef Engineering Research Database Technology Research Database Mechanical & Transportation Engineering Abstracts Environment Abstracts Environmental Sciences and Pollution Management |
| DatabaseTitleList | Engineering Research Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Physics |
| EISSN | 1879-0836 |
| ExternalDocumentID | oai_DiVA_org_ltu_87121 10_1016_j_ress_2021_107961 S0951832021004725 |
| GroupedDBID | --K --M .~1 0R~ 123 1B1 1~. 1~5 29P 4.4 457 4G. 5VS 6I. 7-5 71M 8P~ 9JN 9JO AABNK AACTN AAEDT AAEDW AAFJI AAFTH AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO ABEFU ABFNM ABJNI ABMAC ABMMH ABTAH ABXDB ABYKQ ACDAQ ACGFS ACIWK ACNNM ACRLP ADBBV ADEZE ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFRAH AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AIEXJ AIKHN AITUG AJBFU AJOXV AKYCK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOMHK ASPBG AVARZ AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HVGLF HZ~ IHE J1W JJJVA KOM LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PRBVW Q38 R2- RIG ROL RPZ SDF SDG SES SET SEW SPC SPCBC SSB SSO SST SSZ T5K TN5 WUQ XPP ZMT ZY4 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD 7ST 7TB 8FD AGCQF C1K FR3 SOI ADTPV AOWAS D8T ZZAVC |
| ID | FETCH-LOGICAL-c409t-a5329e740b90883c203b9386002117db6eebf64e78c9cf598ee88ec36c6054be3 |
| ISICitedReferencesCount | 260 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000702360100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0951-8320 1879-0836 |
| IngestDate | Sat Oct 25 06:17:02 EDT 2025 Wed Aug 13 10:34:36 EDT 2025 Sat Nov 29 07:05:12 EST 2025 Tue Nov 18 22:14:05 EST 2025 Fri Feb 23 02:39:43 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning CMAPSS Hybrid model Prognostics |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c409t-a5329e740b90883c203b9386002117db6eebf64e78c9cf598ee88ec36c6054be3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-0240-0943 0000-0001-6134-3582 0000-0002-9546-1488 |
| OpenAccessLink | https://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87121 |
| PQID | 2619670695 |
| PQPubID | 2045406 |
| ParticipantIDs | swepub_primary_oai_DiVA_org_ltu_87121 proquest_journals_2619670695 crossref_primary_10_1016_j_ress_2021_107961 crossref_citationtrail_10_1016_j_ress_2021_107961 elsevier_sciencedirect_doi_10_1016_j_ress_2021_107961 |
| PublicationCentury | 2000 |
| PublicationDate | January 2022 2022-01-00 20220101 2022 |
| PublicationDateYYYYMMDD | 2022-01-01 |
| PublicationDate_xml | – month: 01 year: 2022 text: January 2022 |
| PublicationDecade | 2020 |
| PublicationPlace | Barking |
| PublicationPlace_xml | – name: Barking |
| PublicationTitle | Reliability engineering & system safety |
| PublicationYear | 2022 |
| Publisher | Elsevier Ltd Elsevier BV |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier BV |
| References | Khan, Yairi (b5) 2018; 107 Wen, Dong, Gao (b51) 2019; 16 Yucesan YA, Viana FAC. Wind turbine main bearing fatigue life estimation with physics-informed neural networks. In: Annual conference of the PHM society, vol. 11, no. 1. p. 1–14. 2019. Jia, Karpatne, Willard, Steinbach, Read, Hanson (b21) 2018 Yang, Zhao, Jiang, Sun, Mei (b39) 2019; 9 Saxena, Celaya, Saha, Saha, Goebel (b45) 2010 Kingma, Ba (b43) 2015 Zhang, Dey, Perez, Moura (b17) 2017 Glorot, Bengio (b44) 2010 Walsh, Fletcher (b56) 2004 Rai, Sahu (b15) 2020; 8 Li, Zhang, Ding (b38) 2019; 182 Tian, Chao, Kulkarni, Goebel, Fink (b34) 2020 Arias Chao, Kulkarni, Goebel, Fink (b23) 2021; 6 Kantas, Doucet, Singh, Maciejowski, Chopin (b32) 2015; 30 Borguet (b31) 2012 Fink, Wang, Svensén, Dersin, Lee, Ducoffe (b13) 2020; 92 Ellefsen, Ushakov, Æsøy, Zhang (b35) 2019; 7 Arias Chao, Lilley, Mathé, Schloßhauer (b25) 2015 Biggio, Kastanis (b12) 2020; 3 Kennedy, O’Hagan (b26) 2001; 63 Turner, Rasmussen (b30) 2010 Roth, Doel, Cissell (b24) 2005 . Bolander, Qiu, Eklund, Hindle, Rosenfeld (b1) 2009 Shi, Chehade (b10) 2021; 205 Saxena, Goebel, Simon, Eklund (b46) 2008 Yu, Kim, Mechefske (b9) 2020; 199 Frederick, Decastro, Litt (b22) 2007 Rutter, Miglioretti, Savarino (b33) 2009; 104 de Oliveira da Costa, Akçay, Zhang, Kaymak (b36) 2020; 195 Crassidis, Junkins (b28) 2011 Julier, Uhlmann (b29) 1997 Kiranyaz, Ince, Abdeljaber, Avci, Gabbouj (b41) 2019 Li, Ding, Sun (b6) 2018; 172 Dourado A, Viana FAC. Physics-informed neural networks for corrosion-fatigue prognosis. In: Annual conference of the PHM society, vol. 11, no. 1. 2019. Saxena, Goebel (b11) 2008 Malhotra P, TV V, Ramakrishnan A, Anand G, Vig L, Agarwal P et al. Multi-sensor prognostics using an unsupervised health index based on LSTM encoder-decoder. In: 1st ACM SIGKDD workshop on machine learning for prognostics and health management. San Francisco: 2016. p. 10. Willard, Jia, Xu, Steinbach, Kumar (b16) 2020 Arias Chao, Kulkarni, Goebel, Fink (b14) 2019; 10 Schwabacher M, Goebel K. A survey of artificial intelligence for prognostics. In: Association for the advancement of artificial intelligence AAAI fall symposium 2007. 2007. p. 107–14. Sacks, Welch, Mitchell, Wynn (b27) 1989; 4 URL Daigle, Goebel (b3) 2013; 43 Alet, Kawaguchi, Bauza, Kuru, Lozano-Perez, Kaelbling (b53) 2020 de Oliveira da Costa, Akcay, Zhang, Kaymak (b7) 2019; 10 Listou Ellefsen, Bjørlykhaug, Æsøy, Ushakov, Zhang (b8) 2019; 183 Saravanamuttoo, Rogers, Cohen (b55) 2001 Ji, Han, Hou, Song, Du (b42) 2020; 20 Wang, Michau, Fink (b37) 2021; 68 Narwariya, Malhotra, TV, Vig, Shroff (b52) 2020 Razak (b54) 2013 Pasa GD, de Medeiros IP, Yoneyama T. Operating condition-invariant neural network-based prognostics methods applied on turbofan aircraft engines. In: Proceedings of the annual conference of the PHM society, vol. 11, no. 1. 2019. Mo, Wu, Li, Huang (b50) 2021 Xu, Wu, Li, Huang (b49) 2020; 20 May R, Csank J, Lavelle T, Litt J, Guo T-H. A high-fidelity simulation of a generic commercial aircraft engine and controller. In: 46th AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit. p. 6630. Nascimento, Viana (b18) 2019 Palazuelos, Droguett, Pascual (b48) 2020; 234 Daigle, Goebel (b2) 2011; 2 Daigle (10.1016/j.ress.2021.107961_b2) 2011; 2 Frederick (10.1016/j.ress.2021.107961_b22) 2007 de Oliveira da Costa (10.1016/j.ress.2021.107961_b36) 2020; 195 Arias Chao (10.1016/j.ress.2021.107961_b14) 2019; 10 Arias Chao (10.1016/j.ress.2021.107961_b25) 2015 Saxena (10.1016/j.ress.2021.107961_b46) 2008 10.1016/j.ress.2021.107961_b47 Mo (10.1016/j.ress.2021.107961_b50) 2021 10.1016/j.ress.2021.107961_b40 Li (10.1016/j.ress.2021.107961_b38) 2019; 182 Ji (10.1016/j.ress.2021.107961_b42) 2020; 20 Ellefsen (10.1016/j.ress.2021.107961_b35) 2019; 7 Willard (10.1016/j.ress.2021.107961_b16) 2020 Borguet (10.1016/j.ress.2021.107961_b31) 2012 Arias Chao (10.1016/j.ress.2021.107961_b23) 2021; 6 Fink (10.1016/j.ress.2021.107961_b13) 2020; 92 Biggio (10.1016/j.ress.2021.107961_b12) 2020; 3 Turner (10.1016/j.ress.2021.107961_b30) 2010 Bolander (10.1016/j.ress.2021.107961_b1) 2009 Kiranyaz (10.1016/j.ress.2021.107961_b41) 2019 Nascimento (10.1016/j.ress.2021.107961_b18) 2019 Walsh (10.1016/j.ress.2021.107961_b56) 2004 Kantas (10.1016/j.ress.2021.107961_b32) 2015; 30 Saxena (10.1016/j.ress.2021.107961_b45) 2010 Wen (10.1016/j.ress.2021.107961_b51) 2019; 16 Zhang (10.1016/j.ress.2021.107961_b17) 2017 Narwariya (10.1016/j.ress.2021.107961_b52) 2020 Razak (10.1016/j.ress.2021.107961_b54) 2013 Kingma (10.1016/j.ress.2021.107961_b43) 2015 Palazuelos (10.1016/j.ress.2021.107961_b48) 2020; 234 Yu (10.1016/j.ress.2021.107961_b9) 2020; 199 Saxena (10.1016/j.ress.2021.107961_b11) 2008 Rutter (10.1016/j.ress.2021.107961_b33) 2009; 104 Julier (10.1016/j.ress.2021.107961_b29) 1997 Sacks (10.1016/j.ress.2021.107961_b27) 1989; 4 Khan (10.1016/j.ress.2021.107961_b5) 2018; 107 10.1016/j.ress.2021.107961_b4 Shi (10.1016/j.ress.2021.107961_b10) 2021; 205 10.1016/j.ress.2021.107961_b20 Jia (10.1016/j.ress.2021.107961_b21) 2018 Kennedy (10.1016/j.ress.2021.107961_b26) 2001; 63 Tian (10.1016/j.ress.2021.107961_b34) 2020 Alet (10.1016/j.ress.2021.107961_b53) 2020 Li (10.1016/j.ress.2021.107961_b6) 2018; 172 Glorot (10.1016/j.ress.2021.107961_b44) 2010 Crassidis (10.1016/j.ress.2021.107961_b28) 2011 Roth (10.1016/j.ress.2021.107961_b24) 2005 de Oliveira da Costa (10.1016/j.ress.2021.107961_b7) 2019; 10 Yang (10.1016/j.ress.2021.107961_b39) 2019; 9 10.1016/j.ress.2021.107961_b19 Wang (10.1016/j.ress.2021.107961_b37) 2021; 68 Listou Ellefsen (10.1016/j.ress.2021.107961_b8) 2019; 183 Daigle (10.1016/j.ress.2021.107961_b3) 2013; 43 Rai (10.1016/j.ress.2021.107961_b15) 2020; 8 Saravanamuttoo (10.1016/j.ress.2021.107961_b55) 2001 Xu (10.1016/j.ress.2021.107961_b49) 2020; 20 10.1016/j.ress.2021.107961_b57 |
| References_xml | – volume: 20 year: 2020 ident: b42 article-title: Remaining useful life prediction of airplane engine based on PCA–BLSTM publication-title: Sensors – volume: 63 start-page: 425 year: 2001 end-page: 464 ident: b26 article-title: Bayesian calibration of computer models publication-title: J R Stat Soc Ser B Stat Methodol – start-page: 8360 year: 2019 end-page: 8364 ident: b41 article-title: 1-D convolutional neural networks for signal processing applications publication-title: 2019 IEEE international conference on acoustics, speech and signal processing – volume: 43 start-page: 535 year: 2013 end-page: 546 ident: b3 article-title: Model-based prognostics with concurrent damage progression processes publication-title: IEEE Trans Syst Man Cybern A – year: 2020 ident: b16 article-title: Integrating physics-based modeling with machine learning: A survey – volume: 234 start-page: 151 year: 2020 end-page: 167 ident: b48 article-title: A novel deep capsule neural network for remaining useful life estimation publication-title: Proc. Inst. Mech. Eng. O – volume: 182 start-page: 208 year: 2019 end-page: 218 ident: b38 article-title: Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction publication-title: Reliab Eng Syst Saf – year: 2015 ident: b25 article-title: Calibration and uncertainty quantification of gas turbine performance models publication-title: Proceedings of the ASME turbo expo, vol. 7A – reference: Pasa GD, de Medeiros IP, Yoneyama T. Operating condition-invariant neural network-based prognostics methods applied on turbofan aircraft engines. In: Proceedings of the annual conference of the PHM society, vol. 11, no. 1. 2019. – start-page: 1 year: 2021 end-page: 10 ident: b50 article-title: Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit publication-title: J Intell Manuf – year: 2020 ident: b53 article-title: Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time – start-page: 423 year: 2013 end-page: 514 ident: b54 article-title: 11 - Gas turbine performance modelling, analysis and optimisation publication-title: Modern gas turbine systems – year: 2012 ident: b31 article-title: Variations on the Kalman filter for enhanced performance monitoring of gas turbine engines – volume: 8 start-page: 71050 year: 2020 end-page: 71073 ident: b15 article-title: Driven by data or derived through physics? A review of hybrid physics guided machine learning techniques with cyber-physical system (CPS) focus publication-title: IEEE Access – year: 2004 ident: b56 article-title: Gas Turbine Performance – start-page: 249 year: 2010 end-page: 256 ident: b44 article-title: Understanding the difficulty of training deep feedforward neural networks – volume: 6 start-page: 5 year: 2021 ident: b23 article-title: Aircraft engine run-to-failure dataset under real flight conditions for prognostics and diagnostics publication-title: Data – volume: 68 start-page: 663 year: 2021 end-page: 671 ident: b37 article-title: Missing-class-robust domain adaptation by unilateral alignment publication-title: IEEE Trans Ind Electron – start-page: 3 year: 2018 ident: b21 article-title: Physics guided recurrent neural networks for modeling dynamical systems: Application to monitoring water temperature and quality in lakes – volume: 20 year: 2020 ident: b49 article-title: Dilated convolution neural network for remaining useful life prediction publication-title: J Comput Inf Sci Eng – volume: 199 year: 2020 ident: b9 article-title: An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme publication-title: Reliab Eng Syst Saf – volume: 3 start-page: 88 year: 2020 ident: b12 article-title: Prognostics and health management of industrial assets: Current progress and road ahead publication-title: Front Artif Intell – year: 2015 ident: b43 article-title: Adam: A method for stochastic optimization publication-title: 3rd international conference on learning representations - Conference Track Proceedings – volume: 92 year: 2020 ident: b13 article-title: Potential, challenges and future directions for deep learning in prognostics and health management applications publication-title: Eng Appl Artif Intell – volume: 30 start-page: 328 year: 2015 end-page: 351 ident: b32 article-title: On particle methods for parameter estimation in state-space models publication-title: Statist Sci – start-page: 182 year: 1997 end-page: 193 ident: b29 article-title: New extension of the Kalman filter to nonlinear systems publication-title: Signal processing, sensor fusion, and target recognition VI, vol. 3068 – year: 2010 ident: b45 article-title: Metrics for offline evaluation of prognostic performance publication-title: Int J Progn Health Manag – year: 2008 ident: b11 article-title: Turbofan engine degradation simulation data set – year: 2009 ident: b1 article-title: Physics-based remaining useful life prediction for aircraft engine bearing prognosis – reference: Yucesan YA, Viana FAC. Wind turbine main bearing fatigue life estimation with physics-informed neural networks. In: Annual conference of the PHM society, vol. 11, no. 1. p. 1–14. 2019. – reference: Schwabacher M, Goebel K. A survey of artificial intelligence for prognostics. In: Association for the advancement of artificial intelligence AAAI fall symposium 2007. 2007. p. 107–14. – start-page: 541 year: 2005 end-page: 548 ident: b24 article-title: Probabilistic matching of turbofan engine performance models to test data publication-title: Proceedings of the ASME turbo expo, vol. 1 – volume: 4 start-page: 409 year: 1989 end-page: 423 ident: b27 article-title: Design and analysis of computer experiments publication-title: Statist Sci – volume: 9 start-page: 4813 year: 2019 ident: b39 article-title: A novel deep learning approach for machinery prognostics based on time windows publication-title: Appl Sci – year: 2001 ident: b55 article-title: Gas turbine theory – start-page: 178 year: 2010 end-page: 183 ident: b30 article-title: Model based learning of sigma points in unscented Kalman filtering publication-title: Proceedings of the 2010 IEEE international workshop on machine learning for signal processing – volume: 107 start-page: 241 year: 2018 end-page: 265 ident: b5 article-title: A review on the application of deep learning in system health management publication-title: Mech Syst Signal Process – reference: Malhotra P, TV V, Ramakrishnan A, Anand G, Vig L, Agarwal P et al. Multi-sensor prognostics using an unsupervised health index based on LSTM encoder-decoder. In: 1st ACM SIGKDD workshop on machine learning for prognostics and health management. San Francisco: 2016. p. 10. – year: 2011 ident: b28 publication-title: Optimal estimation of dynamic systems – volume: 183 start-page: 240 year: 2019 end-page: 251 ident: b8 article-title: Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture publication-title: Reliab Eng Syst Saf – reference: Dourado A, Viana FAC. Physics-informed neural networks for corrosion-fatigue prognosis. In: Annual conference of the PHM society, vol. 11, no. 1. 2019. – reference: , URL – volume: 16 start-page: 862 year: 2019 end-page: 880 ident: b51 article-title: A new ensemble residual convolutional neural network for remaining useful life estimation publication-title: Math Biosci Eng – reference: May R, Csank J, Lavelle T, Litt J, Guo T-H. A high-fidelity simulation of a generic commercial aircraft engine and controller. In: 46th AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit. p. 6630. – volume: 10 start-page: 1 year: 2019 end-page: 19 ident: b14 article-title: Hybrid deep fault detection and isolation: Combining deep neural networks and system performance models publication-title: Int J Progn Health Manag – volume: 2 start-page: 1 year: 2011 end-page: 16 ident: b2 article-title: A model-based prognostics approach applied to pneumatic valves publication-title: Int J Progn Health Manag – volume: 205 year: 2021 ident: b10 article-title: A dual-LSTM framework combining change point detection and remaining useful life prediction publication-title: Reliab Eng Syst Saf – year: 2020 ident: b52 article-title: Graph neural networks for leveraging industrial equipment structure: An application to remaining useful life estimation – volume: 10 year: 2019 ident: b7 article-title: Attention and long short-term memory network for remaining useful lifetime predictions of turbofan engine degradation publication-title: Int J Progn Health Manag – volume: 195 year: 2020 ident: b36 article-title: Remaining useful lifetime prediction via deep domain adaptation publication-title: Reliab Eng Syst Saf – volume: 104 start-page: 1338 year: 2009 end-page: 1350 ident: b33 article-title: Bayesian calibration of microsimulation models publication-title: J Amer Statist Assoc – reference: . – year: 2007 ident: b22 article-title: User’s guide for the commercial modular aero-propulsion system simulation (C-MAPSS) – year: 2020 ident: b34 article-title: Real-time model calibration with deep reinforcement learning – volume: 7 start-page: 71563 year: 2019 end-page: 71575 ident: b35 article-title: Validation of data-driven labeling approaches using a novel deep network structure for remaining useful life predictions publication-title: IEEE Access – start-page: 1740 year: 2019 end-page: 1747 ident: b18 article-title: Fleet prognosis with physics-informed recurrent neural networks publication-title: Structural health monitoring 2019 - Proceedings of the 12th international workshop on structural health monitoring, vol. 2 – volume: 172 start-page: 1 year: 2018 end-page: 11 ident: b6 article-title: Remaining useful life estimation in prognostics using deep convolution neural networks publication-title: Reliab Eng Syst Saf – start-page: 1 year: 2008 end-page: 9 ident: b46 article-title: Damage propagation modeling for aircraft engine run-to-failure simulation publication-title: 2008 international conference on prognostics and health management – start-page: 4042 year: 2017 end-page: 4047 ident: b17 article-title: Remaining useful life estimation of lithium-ion batteries based on thermal dynamics publication-title: 2017 american control conference – volume: 9 start-page: 4813 issue: 22 year: 2019 ident: 10.1016/j.ress.2021.107961_b39 article-title: A novel deep learning approach for machinery prognostics based on time windows publication-title: Appl Sci doi: 10.3390/app9224813 – year: 2020 ident: 10.1016/j.ress.2021.107961_b34 – volume: 4 start-page: 409 issue: 4 year: 1989 ident: 10.1016/j.ress.2021.107961_b27 article-title: Design and analysis of computer experiments publication-title: Statist Sci – year: 2020 ident: 10.1016/j.ress.2021.107961_b53 – start-page: 1740 year: 2019 ident: 10.1016/j.ress.2021.107961_b18 article-title: Fleet prognosis with physics-informed recurrent neural networks – year: 2020 ident: 10.1016/j.ress.2021.107961_b16 – start-page: 182 year: 1997 ident: 10.1016/j.ress.2021.107961_b29 article-title: New extension of the Kalman filter to nonlinear systems – volume: 3 start-page: 88 year: 2020 ident: 10.1016/j.ress.2021.107961_b12 article-title: Prognostics and health management of industrial assets: Current progress and road ahead publication-title: Front Artif Intell doi: 10.3389/frai.2020.578613 – volume: 195 year: 2020 ident: 10.1016/j.ress.2021.107961_b36 article-title: Remaining useful lifetime prediction via deep domain adaptation publication-title: Reliab Eng Syst Saf – volume: 172 start-page: 1 year: 2018 ident: 10.1016/j.ress.2021.107961_b6 article-title: Remaining useful life estimation in prognostics using deep convolution neural networks publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2017.11.021 – ident: 10.1016/j.ress.2021.107961_b20 doi: 10.36001/phmconf.2019.v11i1.807 – volume: 30 start-page: 328 issue: 3 year: 2015 ident: 10.1016/j.ress.2021.107961_b32 article-title: On particle methods for parameter estimation in state-space models publication-title: Statist Sci doi: 10.1214/14-STS511 – volume: 10 start-page: 1 year: 2019 ident: 10.1016/j.ress.2021.107961_b14 article-title: Hybrid deep fault detection and isolation: Combining deep neural networks and system performance models publication-title: Int J Progn Health Manag – volume: 183 start-page: 240 year: 2019 ident: 10.1016/j.ress.2021.107961_b8 article-title: Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2018.11.027 – start-page: 4042 year: 2017 ident: 10.1016/j.ress.2021.107961_b17 article-title: Remaining useful life estimation of lithium-ion batteries based on thermal dynamics – year: 2011 ident: 10.1016/j.ress.2021.107961_b28 – start-page: 178 year: 2010 ident: 10.1016/j.ress.2021.107961_b30 article-title: Model based learning of sigma points in unscented Kalman filtering – volume: 8 start-page: 71050 year: 2020 ident: 10.1016/j.ress.2021.107961_b15 article-title: Driven by data or derived through physics? A review of hybrid physics guided machine learning techniques with cyber-physical system (CPS) focus publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2987324 – year: 2001 ident: 10.1016/j.ress.2021.107961_b55 – ident: 10.1016/j.ress.2021.107961_b4 – volume: 20 issue: 2 year: 2020 ident: 10.1016/j.ress.2021.107961_b49 article-title: Dilated convolution neural network for remaining useful life prediction publication-title: J Comput Inf Sci Eng doi: 10.1115/1.4045293 – year: 2009 ident: 10.1016/j.ress.2021.107961_b1 – year: 2007 ident: 10.1016/j.ress.2021.107961_b22 – volume: 234 start-page: 151 issue: 1 year: 2020 ident: 10.1016/j.ress.2021.107961_b48 article-title: A novel deep capsule neural network for remaining useful life estimation publication-title: Proc. Inst. Mech. Eng. O – volume: 16 start-page: 862 issue: 2 year: 2019 ident: 10.1016/j.ress.2021.107961_b51 article-title: A new ensemble residual convolutional neural network for remaining useful life estimation publication-title: Math Biosci Eng doi: 10.3934/mbe.2019040 – year: 2008 ident: 10.1016/j.ress.2021.107961_b11 – volume: 6 start-page: 5 issue: 1 year: 2021 ident: 10.1016/j.ress.2021.107961_b23 article-title: Aircraft engine run-to-failure dataset under real flight conditions for prognostics and diagnostics publication-title: Data doi: 10.3390/data6010005 – start-page: 1 year: 2021 ident: 10.1016/j.ress.2021.107961_b50 article-title: Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit publication-title: J Intell Manuf – volume: 199 year: 2020 ident: 10.1016/j.ress.2021.107961_b9 article-title: An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2020.106926 – volume: 205 year: 2021 ident: 10.1016/j.ress.2021.107961_b10 article-title: A dual-LSTM framework combining change point detection and remaining useful life prediction publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2020.107257 – start-page: 3 year: 2018 ident: 10.1016/j.ress.2021.107961_b21 – start-page: 541 year: 2005 ident: 10.1016/j.ress.2021.107961_b24 article-title: Probabilistic matching of turbofan engine performance models to test data – year: 2012 ident: 10.1016/j.ress.2021.107961_b31 – volume: 43 start-page: 535 issue: 3 year: 2013 ident: 10.1016/j.ress.2021.107961_b3 article-title: Model-based prognostics with concurrent damage progression processes publication-title: IEEE Trans Syst Man Cybern A doi: 10.1109/TSMCA.2012.2207109 – volume: 107 start-page: 241 year: 2018 ident: 10.1016/j.ress.2021.107961_b5 article-title: A review on the application of deep learning in system health management publication-title: Mech Syst Signal Process doi: 10.1016/j.ymssp.2017.11.024 – volume: 63 start-page: 425 issue: 3 year: 2001 ident: 10.1016/j.ress.2021.107961_b26 article-title: Bayesian calibration of computer models publication-title: J R Stat Soc Ser B Stat Methodol doi: 10.1111/1467-9868.00294 – volume: 182 start-page: 208 year: 2019 ident: 10.1016/j.ress.2021.107961_b38 article-title: Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2018.11.011 – year: 2015 ident: 10.1016/j.ress.2021.107961_b25 article-title: Calibration and uncertainty quantification of gas turbine performance models – ident: 10.1016/j.ress.2021.107961_b57 – volume: 10 year: 2019 ident: 10.1016/j.ress.2021.107961_b7 article-title: Attention and long short-term memory network for remaining useful lifetime predictions of turbofan engine degradation publication-title: Int J Progn Health Manag – ident: 10.1016/j.ress.2021.107961_b40 doi: 10.36001/phmconf.2019.v11i1.786 – volume: 92 year: 2020 ident: 10.1016/j.ress.2021.107961_b13 article-title: Potential, challenges and future directions for deep learning in prognostics and health management applications publication-title: Eng Appl Artif Intell doi: 10.1016/j.engappai.2020.103678 – start-page: 249 year: 2010 ident: 10.1016/j.ress.2021.107961_b44 – ident: 10.1016/j.ress.2021.107961_b47 – volume: 2 start-page: 1 year: 2011 ident: 10.1016/j.ress.2021.107961_b2 article-title: A model-based prognostics approach applied to pneumatic valves publication-title: Int J Progn Health Manag – year: 2004 ident: 10.1016/j.ress.2021.107961_b56 – volume: 104 start-page: 1338 issue: 488 year: 2009 ident: 10.1016/j.ress.2021.107961_b33 article-title: Bayesian calibration of microsimulation models publication-title: J Amer Statist Assoc doi: 10.1198/jasa.2009.ap07466 – ident: 10.1016/j.ress.2021.107961_b19 doi: 10.36001/phmconf.2019.v11i1.814 – year: 2020 ident: 10.1016/j.ress.2021.107961_b52 – volume: 20 issue: 16 year: 2020 ident: 10.1016/j.ress.2021.107961_b42 article-title: Remaining useful life prediction of airplane engine based on PCA–BLSTM publication-title: Sensors doi: 10.3390/s20164537 – start-page: 423 year: 2013 ident: 10.1016/j.ress.2021.107961_b54 article-title: 11 - Gas turbine performance modelling, analysis and optimisation – year: 2015 ident: 10.1016/j.ress.2021.107961_b43 article-title: Adam: A method for stochastic optimization – start-page: 8360 year: 2019 ident: 10.1016/j.ress.2021.107961_b41 article-title: 1-D convolutional neural networks for signal processing applications – year: 2010 ident: 10.1016/j.ress.2021.107961_b45 article-title: Metrics for offline evaluation of prognostic performance publication-title: Int J Progn Health Manag – start-page: 1 year: 2008 ident: 10.1016/j.ress.2021.107961_b46 article-title: Damage propagation modeling for aircraft engine run-to-failure simulation – volume: 68 start-page: 663 issue: 1 year: 2021 ident: 10.1016/j.ress.2021.107961_b37 article-title: Missing-class-robust domain adaptation by unilateral alignment publication-title: IEEE Trans Ind Electron doi: 10.1109/TIE.2019.2962438 – volume: 7 start-page: 71563 year: 2019 ident: 10.1016/j.ress.2021.107961_b35 article-title: Validation of data-driven labeling approaches using a novel deep network structure for remaining useful life predictions publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2920297 |
| SSID | ssj0004957 |
| Score | 2.70571 |
| Snippet | Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability... |
| SourceID | swepub proquest crossref elsevier |
| SourceType | Open Access Repository Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 107961 |
| SubjectTerms | Algorithms Artificial neural networks CMAPSS Datasets Deep learning Drift och underhållsteknik Flight conditions Hybrid model Learning algorithms Machine learning Mathematical models Neural networks Operation and Maintenance Parameters Physics Prognostics Reliability engineering Safety critical Training Turbofan engines |
| Title | Fusing physics-based and deep learning models for prognostics |
| URI | https://dx.doi.org/10.1016/j.ress.2021.107961 https://www.proquest.com/docview/2619670695 https://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87121 |
| Volume | 217 |
| WOSCitedRecordID | wos000702360100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-0836 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004957 issn: 1879-0836 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6hlAMcEE8RWpAPcIqM4ufuHiNoeUmFQ0G5rez1OEqJ7Ci2Ufvvmd1ZOwZKVQ5crGhjx9bMl_HM7Mw3jL00lCcF2n0_1VmJAUpU-DIWpV-IAu0hxOikCDtsgp-eiuVSfnFj7ho7ToBXlbi4kNv_qmpcQ2Wb1tl_UPfwo7iAn1HpeES14_FGij_pbPhPKYvGN68pS8c6KwC2_ZSIFY3AsWQMtkarqi1h89hXNdXKxOJ9OYM9baEFCxFAz5qsdDwiBJp11pgN_Jq6gKoOhvqNT93mu7kzbfFDuwfluxo1TD1C2XqAE4bIZunzZpWNExPhKEtpJphb2uuxmQ2pR_MPk03Zg_PXJruA8XoY4BKXxNB-BRX22_W3hap3K7VpO4XRniEROAg5xkUTdrD4cLz8uG-LlUT0ik6kj4bL9sb2T-b6p6jU7_db_81HGccgY15Z64uc3Wf3XBDhLUj5D9gtqB6yuyNqyUfMwcD7BQYewsAzMPB6GHgEAw9h4I1g8Jh9PTk-e_Ped6MyfI0BeutnSRRK4PE8N3VrkQ7nUS4jYTZdg4AXeQqQl2kMXGipy0QKACFAR6nGcDbOIXrCJlVdwVPmBToJE13EZcbLuASexVwWAedZVEYxBHLKgl44SjseeTPOZKP6gsFzZQSqjEAVCXTKZsM1W2JRufbspJe5cn4g-XcKMXPtdUe9gpT7Q-L3Kb5j-DyVyZS9IqUNj3A1np7d8LxDdsfAnvJxR2zS7jp4zm7rH-262b1wYPwJZCOVug |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Fusing+physics-based+and+deep+learning+models+for+prognostics&rft.jtitle=Reliability+engineering+%26+system+safety&rft.au=Arias+Chao%2C+Manuel&rft.au=Kulkarni%2C+Chetan&rft.au=Goebel%2C+Kai&rft.au=Fink%2C+Olga&rft.date=2022&rft.issn=1879-0836&rft.volume=217&rft_id=info:doi/10.1016%2Fj.ress.2021.107961&rft.externalDocID=oai_DiVA_org_ltu_87121 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0951-8320&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0951-8320&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0951-8320&client=summon |