An adaptive mixture prior in Bayesian convolutional autoencoder for early detecting anomalous degradation behaviors in lithium-ion batteries
Accurate and timely detection of anomalies in lithium-ion batteries is crucial for ensuring their reliability and safety. Complex degradation patterns and limited availability of labeled data pose significant challenges in identifying abnormal behaviors in battery usage. This paper proposes an unsup...
Uloženo v:
| Vydáno v: | Reliability engineering & system safety Ročník 259; s. 110926 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.07.2025
|
| Témata: | |
| ISSN: | 0951-8320 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Accurate and timely detection of anomalies in lithium-ion batteries is crucial for ensuring their reliability and safety. Complex degradation patterns and limited availability of labeled data pose significant challenges in identifying abnormal behaviors in battery usage. This paper proposes an unsupervised adaptive mixture distribution-based Bayesian convolutional autoencoder (AMDBCAE) method for detecting anomalous degradation behaviors in lithium-ion batteries at earlier cycles of reliability test. As the prior for the model parameters, we propose a mixture of the Laplace and Student’s t distributions by taking uncertainties in the weights of the convolutional network and their heavy-tailed characteristics into account. Using a modified form of the Bayes by backprop algorithm, the parameter of mixture proportion is adaptively updated to capture diverse and complex degradation patterns in battery degradation data more efficiently. Extracted latent features are then processed through unsupervised clustering algorithms to identify abnormal degradation behaviors of lithium-ion batteries. The analyses of two real-world lithium-ion battery datasets demonstrate the efficiency and accuracy of the proposed unsupervised framework with limited number of testing data. The proposed method addresses the limitations of manual feature extraction and the need for extensive experimental knowledge by leveraging the adaptive BCAE model to automatically extract latent features as a virtual health indicator in sparse data environments.
•Aim to detect anomalies of lithium-ion batteries at earlier stages of cycling test.•Address the limitations of manual feature extraction in a sparse data environment.•Propose an unsupervised adaptive Bayesian convolutional autoencoder (BCAE) method.•Propose a mixture of the Laplace and Student’s t distributions as the prior. |
|---|---|
| AbstractList | Accurate and timely detection of anomalies in lithium-ion batteries is crucial for ensuring their reliability and safety. Complex degradation patterns and limited availability of labeled data pose significant challenges in identifying abnormal behaviors in battery usage. This paper proposes an unsupervised adaptive mixture distribution-based Bayesian convolutional autoencoder (AMDBCAE) method for detecting anomalous degradation behaviors in lithium-ion batteries at earlier cycles of reliability test. As the prior for the model parameters, we propose a mixture of the Laplace and Student’s t distributions by taking uncertainties in the weights of the convolutional network and their heavy-tailed characteristics into account. Using a modified form of the Bayes by backprop algorithm, the parameter of mixture proportion is adaptively updated to capture diverse and complex degradation patterns in battery degradation data more efficiently. Extracted latent features are then processed through unsupervised clustering algorithms to identify abnormal degradation behaviors of lithium-ion batteries. The analyses of two real-world lithium-ion battery datasets demonstrate the efficiency and accuracy of the proposed unsupervised framework with limited number of testing data. The proposed method addresses the limitations of manual feature extraction and the need for extensive experimental knowledge by leveraging the adaptive BCAE model to automatically extract latent features as a virtual health indicator in sparse data environments.
•Aim to detect anomalies of lithium-ion batteries at earlier stages of cycling test.•Address the limitations of manual feature extraction in a sparse data environment.•Propose an unsupervised adaptive Bayesian convolutional autoencoder (BCAE) method.•Propose a mixture of the Laplace and Student’s t distributions as the prior. |
| ArticleNumber | 110926 |
| Author | Chae, Sun Geu Bae, Suk Joo |
| Author_xml | – sequence: 1 givenname: Sun Geu orcidid: 0009-0003-1952-1957 surname: Chae fullname: Chae, Sun Geu email: sgchae@psm.hanyang.ac.kr – sequence: 2 givenname: Suk Joo orcidid: 0000-0002-9938-7406 surname: Bae fullname: Bae, Suk Joo email: sjbae@hanyang.ac.kr |
| BookMark | eNp9kMtOwzAQRb0oEm3hB1j5BxLsvCOxKRUvqRIbWFtTZ9K6SuzKdiL6D3w0DmXFoquRZuZc6Z4FmWmjkZA7zmLOeHF_iC06FycsyWPOWZ0UMzJndc6jKk3YNVk4d2CMZXVezsn3SlNo4OjViLRXX36wSI9WGUuVpo9wQqdAU2n0aLrBK6OhozB4g1qaBi1twyeC7U60QY_SK72joE0PnRlc2O1siJ84usU9jCHYTcmd8ns19NHvAbxHq9DdkKsWOoe3f3NJPp-fPtav0eb95W292kQyZcxH27aElCPLGGZNhXVRQdnWvJaQbDlWpazaLAvrOi1Ca0yKNGdt1jKs0qooZJYuSXLOldY4Z7EVoXEP9iQ4E5NDcRCTQzE5FGeHAar-QVL532beguouow9nFEOpUaEVTqogEBtlgzLRGHUJ_wHI5pWC |
| CitedBy_id | crossref_primary_10_1016_j_ress_2025_111462 crossref_primary_10_1016_j_ress_2025_111115 crossref_primary_10_1016_j_energy_2025_138229 |
| Cites_doi | 10.1016/j.est.2016.01.003 10.1016/j.jclepro.2019.05.401 10.1038/s41586-020-1994-5 10.1016/j.apenergy.2023.120841 10.1016/j.ress.2023.109603 10.1038/35104644 10.1016/j.jpowsour.2020.228964 10.1016/j.compeleceng.2022.108095 10.1016/j.ress.2024.109978 10.1016/j.apenergy.2022.120204 10.1109/TIE.2018.2880701 10.1109/TSMCC.2009.2014642 10.1016/j.nanoen.2017.12.006 10.1016/j.jpowsour.2011.03.101 10.1016/j.ress.2023.109753 10.1038/s41560-019-0356-8 10.1155/2012/395838 10.1016/j.energy.2021.121022 10.1109/TIE.2020.2972468 10.1016/j.jpowsour.2014.10.009 10.1016/j.est.2018.05.002 10.1109/MIM.2008.4579269 10.1016/j.jpowsour.2019.03.008 10.1016/j.jenvman.2020.110500 10.1016/j.est.2018.07.003 10.1016/j.egyai.2020.100006 10.1016/j.ress.2022.108978 10.1016/j.ress.2018.11.013 10.1109/TTE.2023.3304670 10.1016/j.est.2020.101710 10.1109/TIE.2017.2733475 10.1016/j.ress.2022.108717 10.1016/j.ress.2022.108758 10.1016/j.apenergy.2014.04.013 10.1016/j.apenergy.2021.118172 10.1149/2.F10223IF 10.1016/j.ress.2022.108482 10.1016/j.ress.2024.110014 10.36001/phmconf.2016.v8i1.2587 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ress.2025.110926 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| ExternalDocumentID | 10_1016_j_ress_2025_110926 S0951832025001292 |
| GroupedDBID | --K --M .~1 0R~ 123 1B1 1~. 1~5 29P 4.4 457 4G. 5VS 7-5 71M 8P~ 9JN 9JO AABNK AACTN AAEDT AAEDW AAFJI AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXKI AAXUO ABEFU ABFNM ABJNI ABMAC ABMMH ABTAH ABWVN ABXDB ACDAQ ACGFS ACIWK ACNNM ACRLP ACRPL ADBBV ADEZE ADMUD ADNMO ADTZH AEBSH AECPX AEIPS AEKER AENEX AFJKZ AFRAH AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AIEXJ AIKHN AITUG AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOMHK ASPBG AVARZ AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC 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 SPCBC SSB SSO SST SSZ T5K TN5 WUQ XPP ZMT ZY4 ~G- 9DU AATTM AAYWO AAYXX ACLOT ACVFH ADCNI AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP APXCP CITATION EFKBS EFLBG SPC ~HD |
| ID | FETCH-LOGICAL-c300t-bf7a31e040e4d8e968a7f919ca2b1e87c8f44e96936951e26350f4f0e83866c43 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001435735500001&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 |
| IngestDate | Sat Nov 29 08:07:14 EST 2025 Tue Nov 18 22:12:20 EST 2025 Sat Mar 22 15:52:45 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Latent features Reliability test Deep autoencoder Unsupervised clustering Virtual health indicator |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c300t-bf7a31e040e4d8e968a7f919ca2b1e87c8f44e96936951e26350f4f0e83866c43 |
| ORCID | 0000-0002-9938-7406 0009-0003-1952-1957 |
| ParticipantIDs | crossref_primary_10_1016_j_ress_2025_110926 crossref_citationtrail_10_1016_j_ress_2025_110926 elsevier_sciencedirect_doi_10_1016_j_ress_2025_110926 |
| PublicationCentury | 2000 |
| PublicationDate | July 2025 2025-07-00 |
| PublicationDateYYYYMMDD | 2025-07-01 |
| PublicationDate_xml | – month: 07 year: 2025 text: July 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Reliability engineering & system safety |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Deutschen, Gasser, Schaller, Siehr (b3) 2018; 19 Bach, Schuster, Fleder (b20) 2016; 5 Blundell, Cornebise, Kavukcuoglu, Wierstra (b40) 2015 Zhu, Chen, Peng, Ye (b47) 2022; 228 Beaulieu, Jha, Garnier, Cerbah (b35) 2022; Vol. 7 Saxena, Kang, Xing, Pecht (b59) 2018 Bai, Tan, Wang (b33) 2019; 233 Neal, Hinton (b48) 1998 Goebel, Saha, Saxena, Celaya, Christophersen (b16) 2008; 11 González-Muñiz, Diaz, Cuadrado, García-Pérez (b39) 2022; 224 Fortuin, Garriga-Alonso, Ober (b42) 2021 Sarve, Phadke (b12) 2023; 14 Hu Y, Palmé T, Fink O. Deep health indicator extraction: A method based on auto-encoders and extreme learning machines. In: Annual conference of the PHM society. Vol. 8, 2016. Sohn, Byun, Lee (b31) 2022; 328 Smith, Saxon, Keyser, Lundstrom, Cao, Roc (b18) 2017 Li, Liu, Mei (b7) 2018 Ester, Kriegel, Sander, Xu (b52) 1996; Vol. 96 Guo, Feng, Sun (b15) 2024; 245 Maddison, Tarlow, Minka (b50) 2014 Lee, Jo, Kwon, Pecht (b26) 2020; 68 Jang, Gu, Poole (b49) 2016 Attia, Grover, Jin (b55) 2020; 578 Severson, Attia, Jin (b54) 2019; 4 Che, Zheng, Forest, Sui, Hu, Teodorescu (b57) 2024; 241 Bae, Xi (b34) 2022; 226 Cheng, Wang, He (b22) 2021; 232 Park, Baek, Jeong, Bae (b24) 2009; 39 Xue, Li, Zhang, Shen, Chen, Liu (b29) 2021; 482 Wang, Chen, Zhang, Zhu (b19) 2023; 336 Salimans, Kingma, Welling (b41) 2015 Zhang (b44) 2018 Ng, Jordan, Weiss (b53) 2001 Ni, Ji, Feng, Zhang, Lin, Zheng (b38) 2024; 242 Lin, You, Wang, Wu (b6) 2023; 230 Barrera, Bond, Bradley (b13) 2022; 31 Catelani, Ciani, Grasso, Patrizi, Reatti (b9) 2022 Guo, Wang, Li (b36) 2024; 245 Sun, Han, Wang (b30) 2022; 307 Li, Min, Zhang (b32) 2022; 2022 Capasso, Veneri (b10) 2014; 136 Ranzato, Huang, Boureau, LeCun (b45) 2007 Alias, Mohamad (b5) 2015; 274 Xiong, Zhang, He, Zhou, Pecht (b14) 2017; 65 Santhanagopalan, White (b21) 2012; 2012 Fang, Chen, Zhou (b28) 2022; 102 Diao, Naqvi, Pecht (b25) 2020; 32 Ke, Jiang, Zhu (b56) 2023; 10 Johnson, Kotz, Balakrishnan (b46) 1995 Tarascon, Armand (b4) 2001; 414 LeCun, Boser, Denker (b43) 1989 Liu, Li, Zhu (b8) 2018; 44 Zhang, Lee (b17) 2011; 196 Yu, Deng, Yu, Deng (b51) 2016; vol. 1 Fermín-Cueto, McTurk, Allerhand (b58) 2020; 1 Gandoman, Ahmadi, Van den Bossche (b11) 2019; 183 Li, Wang, Yan (b27) 2019; 421 Lee, Kwon, Pecht (b23) 2018; 66 Mossali, Picone, Gentilini, Rodrìguez, Pérez, Colledani (b2) 2020; 264 Kwasi-Effah, Rabczuk (b1) 2018; 18 Li (10.1016/j.ress.2025.110926_b32) 2022; 2022 Bach (10.1016/j.ress.2025.110926_b20) 2016; 5 Sun (10.1016/j.ress.2025.110926_b30) 2022; 307 Liu (10.1016/j.ress.2025.110926_b8) 2018; 44 LeCun (10.1016/j.ress.2025.110926_b43) 1989 Deutschen (10.1016/j.ress.2025.110926_b3) 2018; 19 Bae (10.1016/j.ress.2025.110926_b34) 2022; 226 Severson (10.1016/j.ress.2025.110926_b54) 2019; 4 Smith (10.1016/j.ress.2025.110926_b18) 2017 Yu (10.1016/j.ress.2025.110926_b51) 2016; vol. 1 Lin (10.1016/j.ress.2025.110926_b6) 2023; 230 Wang (10.1016/j.ress.2025.110926_b19) 2023; 336 Ranzato (10.1016/j.ress.2025.110926_b45) 2007 Blundell (10.1016/j.ress.2025.110926_b40) 2015 Che (10.1016/j.ress.2025.110926_b57) 2024; 241 Xue (10.1016/j.ress.2025.110926_b29) 2021; 482 Sohn (10.1016/j.ress.2025.110926_b31) 2022; 328 Xiong (10.1016/j.ress.2025.110926_b14) 2017; 65 Alias (10.1016/j.ress.2025.110926_b5) 2015; 274 Lee (10.1016/j.ress.2025.110926_b23) 2018; 66 Barrera (10.1016/j.ress.2025.110926_b13) 2022; 31 Diao (10.1016/j.ress.2025.110926_b25) 2020; 32 Zhang (10.1016/j.ress.2025.110926_b44) 2018 Johnson (10.1016/j.ress.2025.110926_b46) 1995 Goebel (10.1016/j.ress.2025.110926_b16) 2008; 11 Sarve (10.1016/j.ress.2025.110926_b12) 2023; 14 Tarascon (10.1016/j.ress.2025.110926_b4) 2001; 414 Maddison (10.1016/j.ress.2025.110926_b50) 2014 Jang (10.1016/j.ress.2025.110926_b49) 2016 Guo (10.1016/j.ress.2025.110926_b36) 2024; 245 Ni (10.1016/j.ress.2025.110926_b38) 2024; 242 Salimans (10.1016/j.ress.2025.110926_b41) 2015 Li (10.1016/j.ress.2025.110926_b7) 2018 Bai (10.1016/j.ress.2025.110926_b33) 2019; 233 González-Muñiz (10.1016/j.ress.2025.110926_b39) 2022; 224 Capasso (10.1016/j.ress.2025.110926_b10) 2014; 136 Ke (10.1016/j.ress.2025.110926_b56) 2023; 10 Fortuin (10.1016/j.ress.2025.110926_b42) 2021 Fermín-Cueto (10.1016/j.ress.2025.110926_b58) 2020; 1 Ester (10.1016/j.ress.2025.110926_b52) 1996; Vol. 96 Lee (10.1016/j.ress.2025.110926_b26) 2020; 68 Kwasi-Effah (10.1016/j.ress.2025.110926_b1) 2018; 18 Neal (10.1016/j.ress.2025.110926_b48) 1998 Saxena (10.1016/j.ress.2025.110926_b59) 2018 Li (10.1016/j.ress.2025.110926_b27) 2019; 421 Santhanagopalan (10.1016/j.ress.2025.110926_b21) 2012; 2012 Catelani (10.1016/j.ress.2025.110926_b9) 2022 Fang (10.1016/j.ress.2025.110926_b28) 2022; 102 Attia (10.1016/j.ress.2025.110926_b55) 2020; 578 Zhu (10.1016/j.ress.2025.110926_b47) 2022; 228 Gandoman (10.1016/j.ress.2025.110926_b11) 2019; 183 Zhang (10.1016/j.ress.2025.110926_b17) 2011; 196 Park (10.1016/j.ress.2025.110926_b24) 2009; 39 10.1016/j.ress.2025.110926_b37 Mossali (10.1016/j.ress.2025.110926_b2) 2020; 264 Ng (10.1016/j.ress.2025.110926_b53) 2001 Cheng (10.1016/j.ress.2025.110926_b22) 2021; 232 Guo (10.1016/j.ress.2025.110926_b15) 2024; 245 Beaulieu (10.1016/j.ress.2025.110926_b35) 2022; Vol. 7 |
| References_xml | – volume: 241 year: 2024 ident: b57 article-title: Predictive health assessment for lithium-ion batteries with probabilistic degradation prediction and accelerating aging detection publication-title: Reliab Eng Syst Saf – volume: 10 year: 2023 ident: b56 article-title: Early prediction of knee point and knee capacity for fast-charging lithium-ion battery with uncertainty quantification and calibration publication-title: IEEE Trans Transp Electrification – volume: 224 year: 2022 ident: b39 article-title: Health indicator for machine condition monitoring built in the latent space of a deep autoencoder publication-title: Reliab Eng Syst Saf – volume: vol. 1 year: 2016 ident: b51 article-title: Gaussian mixture models publication-title: Automatic speech recognition – volume: 328 year: 2022 ident: b31 article-title: Two-stage deep learning for online prediction of knee-point in Li-ion battery capacity degradation publication-title: Appl Energy – volume: 136 start-page: 921 year: 2014 end-page: 930 ident: b10 article-title: Experimental analysis on the performance of lithium based batteries for road full electric and hybrid vehicles publication-title: Appl Energy – year: 2021 ident: b42 article-title: Bayesian neural network priors revisited – volume: 183 start-page: 1 year: 2019 end-page: 16 ident: b11 article-title: Status and future perspectives of reliability assessment for electric vehicles publication-title: Reliab Eng Syst Saf – volume: 232 year: 2021 ident: b22 article-title: Remaining useful life and state of health prediction for lithium batteries based on empirical mode decomposition and a long and short memory neural network publication-title: Energy – year: 2016 ident: b49 article-title: Categorical reparameterization with gumbel-softmax – volume: 32 year: 2020 ident: b25 article-title: Early detection of anomalous degradation behavior in lithium-ion batteries publication-title: J Energy Storage – volume: 421 start-page: 56 year: 2019 end-page: 67 ident: b27 article-title: Prognostic health condition for lithium battery using the partial incremental capacity and Gaussian process regression publication-title: J Power Sources – volume: 102 year: 2022 ident: b28 article-title: Fault diagnosis for cell voltage inconsistency of a battery pack in electric vehicles based on real-world driving data publication-title: Comput Electr Eng – volume: 414 start-page: 359 year: 2001 end-page: 367 ident: b4 article-title: Issues and challenges facing rechargeable lithium batteries publication-title: Nat – year: 2018 ident: b7 article-title: Predicting smartphone battery life based on comprehensive and real-time usage data – volume: 578 start-page: 397 year: 2020 end-page: 402 ident: b55 article-title: Closed-loop optimization of fast-charging protocols for batteries with machine learning publication-title: Nat – start-page: 4062 year: 2017 end-page: 4068 ident: b18 article-title: Life prediction model for grid-connected Li-ion battery energy storage system publication-title: 2017 American control conference – volume: 66 start-page: 7310 year: 2018 end-page: 7315 ident: b23 article-title: Reduction of Li-ion battery qualification time based on prognostics and health management publication-title: IEEE Trans Ind Electron – volume: 19 start-page: 113 year: 2018 end-page: 119 ident: b3 article-title: Modeling the self-discharge by voltage decay of a NMC/graphite lithium-ion cell publication-title: J Energy Storage – volume: 230 year: 2023 ident: b6 article-title: Battery health prognosis with gated recurrent unit neural networks and hidden Markov model considering uncertainty quantification publication-title: Reliab Eng Syst Saf – year: 1995 ident: b46 article-title: Continuous univeriate distributions – volume: 65 start-page: 1526 year: 2017 end-page: 1538 ident: b14 article-title: A double-scale, particle-filtering, energy state prediction algorithm for lithium-ion batteries publication-title: IEEE Trans Ind Electron – year: 2018 ident: b44 article-title: A better autoencoder for image: Convolutional autoencoder publication-title: ICONIP17-dCEC – volume: 245 year: 2024 ident: b15 article-title: Integrated assessment of reliability and health status of multi-microgrids based on multiagent publication-title: Reliab Eng Syst Saf – start-page: 1 year: 2007 end-page: 8 ident: b45 article-title: Unsupervised learning of invariant feature hierarchies with applications to object recognition publication-title: 2007 IEEE conference on computer vision and pattern recognition – volume: 196 start-page: 6007 year: 2011 end-page: 6014 ident: b17 article-title: A review on prognostics and health monitoring of Li-ion battery publication-title: J Power Sources – volume: 11 start-page: 33 year: 2008 end-page: 40 ident: b16 article-title: Prognostics in battery health management publication-title: IEEE Instrum Meas Mag – volume: 39 start-page: 480 year: 2009 end-page: 485 ident: b24 article-title: Dual features functional support vector machines for fault detection of rechargeable batteries publication-title: IEEE Trans Syst Man Cybern C: Appl Rev – volume: 228 year: 2022 ident: b47 article-title: Bayesian deep-learning for RUL prediction: An active learning perspective publication-title: Reliab Eng Syst Saf – volume: 14 start-page: 1 year: 2023 end-page: xx ident: b12 article-title: A survey on techniques of remaining useful life assessment for predictive maintenance of the system publication-title: Int J Comput Digit Syst – volume: Vol. 96 start-page: 226 year: 1996 end-page: 231 ident: b52 article-title: A density-based algorithm for discovering clusters in large spatial databases with noise publication-title: KDD – volume: Vol. 7 start-page: 193 year: 2022 end-page: 199 ident: b35 article-title: Unsupervised prognostics based on deep virtual health index prediction publication-title: PHM society European conference – start-page: 14 year: 2001 ident: b53 article-title: On spectral clustering: Analysis and an algorithm publication-title: Adv Neural Inf Process Syst – volume: 482 year: 2021 ident: b29 article-title: Fault diagnosis and abnormality detection of lithium-ion battery packs based on statistical distribution publication-title: J Power Sources – volume: 1 year: 2020 ident: b58 article-title: Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells publication-title: Energy AI – volume: 31 start-page: 69 year: 2022 ident: b13 article-title: Next-generation aviation Li-ion battery technologies—enabling electrified aircraft publication-title: Electrochem Soc Interface – volume: 307 year: 2022 ident: b30 article-title: Detection of voltage fault in the battery system of electric vehicles using statistical analysis publication-title: Appl Energy – volume: 44 start-page: 164 year: 2018 end-page: 173 ident: b8 article-title: Towards wearable electronic devices: A quasi-solid-state aqueous lithium-ion battery with outstanding stability, flexibility, safety and breathability publication-title: Nano Energy – volume: 2022 year: 2022 ident: b32 article-title: A novel method for lithium-ion battery fault diagnosis of electric vehicle based on real-time voltage publication-title: Wirel Commun Mob Comput – start-page: 2 year: 1989 ident: b43 article-title: Handwritten digit recognition with a back-propagation network publication-title: Adv Neural Inf Process Syst – volume: 226 year: 2022 ident: b34 article-title: Learning of physical health timestep using the LSTM network for remaining useful life estimation publication-title: Reliab Eng Syst Saf – volume: 264 year: 2020 ident: b2 article-title: Lithium-ion batteries towards circular economy: A literature review of opportunities and issues of recycling treatments publication-title: J Env Manag – volume: 2012 year: 2012 ident: b21 article-title: Quantifying cell-to-cell variations in lithium ion batteries publication-title: Int J Electrochem – volume: 233 start-page: 429 year: 2019 end-page: 445 ident: b33 article-title: Study on distributed lithium-ion power battery grouping scheme for efficiency and consistency improvement publication-title: J Clean Prod – start-page: 1613 year: 2015 end-page: 1622 ident: b40 article-title: Weight uncertainty in neural network publication-title: International conference on machine learning – volume: 245 year: 2024 ident: b36 article-title: A hybrid prognosis scheme for rolling bearings based on a novel health indicator and nonlinear Wiener process publication-title: Reliab Eng Syst Saf – volume: 242 year: 2024 ident: b38 article-title: Data-driven bearing health management using a novel multi-scale fused feature and gated recurrent unit publication-title: Reliab Eng Syst Saf – reference: Hu Y, Palmé T, Fink O. Deep health indicator extraction: A method based on auto-encoders and extreme learning machines. In: Annual conference of the PHM society. Vol. 8, 2016. – volume: 4 start-page: 383 year: 2019 end-page: 391 ident: b54 article-title: Data-driven prediction of battery cycle life before capacity degradation publication-title: Nat Energy – start-page: 1218 year: 2015 end-page: 1226 ident: b41 article-title: Markov chain Monte Carlo and variational inference: Bridging the gap publication-title: International conference on machine learning – volume: 68 start-page: 2659 year: 2020 end-page: 2666 ident: b26 article-title: Capacity-fading behavior analysis for early detection of unhealthy Li-ion batteries publication-title: IEEE Trans Ind Electron – volume: 274 start-page: 237 year: 2015 end-page: 251 ident: b5 article-title: Advances of aqueous rechargeable lithium-ion battery: A review publication-title: J Power Sources – start-page: 1 year: 2018 end-page: 6 ident: b59 article-title: Anomaly detection during lithium-ion battery qualification testing publication-title: 2018 IEEE international conference on prognostics and health management – start-page: 27 year: 2014 ident: b50 article-title: A* sampling publication-title: Adv Neural Inf Process Syst – volume: 336 year: 2023 ident: b19 article-title: Dynamic early recognition of abnormal lithium-ion batteries before capacity drops using self-adaptive quantum clustering publication-title: Appl Energy – start-page: 82 year: 2022 end-page: 87 ident: b9 article-title: Remaining useful life estimation for electric vehicle batteries using a similarity-based approach publication-title: 2022 IEEE international workshop on metrology for automotive – start-page: 355 year: 1998 end-page: 368 ident: b48 article-title: A view of the EM algorithm that justifies incremental, sparse, and other variants publication-title: Learning in graphical models – volume: 5 start-page: 212 year: 2016 end-page: 223 ident: b20 article-title: Nonlinear aging of cylindrical lithium-ion cells linked to heterogeneous compression publication-title: J Energy Storage – volume: 18 start-page: 308 year: 2018 end-page: 315 ident: b1 article-title: Dimensional analysis and modelling of energy density of lithium-ion battery publication-title: J Energy Storage – volume: 5 start-page: 212 year: 2016 ident: 10.1016/j.ress.2025.110926_b20 article-title: Nonlinear aging of cylindrical lithium-ion cells linked to heterogeneous compression publication-title: J Energy Storage doi: 10.1016/j.est.2016.01.003 – start-page: 82 year: 2022 ident: 10.1016/j.ress.2025.110926_b9 article-title: Remaining useful life estimation for electric vehicle batteries using a similarity-based approach – volume: 233 start-page: 429 year: 2019 ident: 10.1016/j.ress.2025.110926_b33 article-title: Study on distributed lithium-ion power battery grouping scheme for efficiency and consistency improvement publication-title: J Clean Prod doi: 10.1016/j.jclepro.2019.05.401 – volume: 578 start-page: 397 issue: 7795 year: 2020 ident: 10.1016/j.ress.2025.110926_b55 article-title: Closed-loop optimization of fast-charging protocols for batteries with machine learning publication-title: Nat doi: 10.1038/s41586-020-1994-5 – volume: 336 year: 2023 ident: 10.1016/j.ress.2025.110926_b19 article-title: Dynamic early recognition of abnormal lithium-ion batteries before capacity drops using self-adaptive quantum clustering publication-title: Appl Energy doi: 10.1016/j.apenergy.2023.120841 – volume: 241 year: 2024 ident: 10.1016/j.ress.2025.110926_b57 article-title: Predictive health assessment for lithium-ion batteries with probabilistic degradation prediction and accelerating aging detection publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2023.109603 – volume: 414 start-page: 359 issue: 6861 year: 2001 ident: 10.1016/j.ress.2025.110926_b4 article-title: Issues and challenges facing rechargeable lithium batteries publication-title: Nat doi: 10.1038/35104644 – volume: 482 year: 2021 ident: 10.1016/j.ress.2025.110926_b29 article-title: Fault diagnosis and abnormality detection of lithium-ion battery packs based on statistical distribution publication-title: J Power Sources doi: 10.1016/j.jpowsour.2020.228964 – volume: vol. 1 year: 2016 ident: 10.1016/j.ress.2025.110926_b51 article-title: Gaussian mixture models – volume: 102 year: 2022 ident: 10.1016/j.ress.2025.110926_b28 article-title: Fault diagnosis for cell voltage inconsistency of a battery pack in electric vehicles based on real-world driving data publication-title: Comput Electr Eng doi: 10.1016/j.compeleceng.2022.108095 – volume: 245 year: 2024 ident: 10.1016/j.ress.2025.110926_b15 article-title: Integrated assessment of reliability and health status of multi-microgrids based on multiagent publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2024.109978 – volume: 328 year: 2022 ident: 10.1016/j.ress.2025.110926_b31 article-title: Two-stage deep learning for online prediction of knee-point in Li-ion battery capacity degradation publication-title: Appl Energy doi: 10.1016/j.apenergy.2022.120204 – year: 1995 ident: 10.1016/j.ress.2025.110926_b46 – volume: 66 start-page: 7310 issue: 9 year: 2018 ident: 10.1016/j.ress.2025.110926_b23 article-title: Reduction of Li-ion battery qualification time based on prognostics and health management publication-title: IEEE Trans Ind Electron doi: 10.1109/TIE.2018.2880701 – volume: 39 start-page: 480 issue: 4 year: 2009 ident: 10.1016/j.ress.2025.110926_b24 article-title: Dual features functional support vector machines for fault detection of rechargeable batteries publication-title: IEEE Trans Syst Man Cybern C: Appl Rev doi: 10.1109/TSMCC.2009.2014642 – volume: 14 start-page: 1 issue: 1 year: 2023 ident: 10.1016/j.ress.2025.110926_b12 article-title: A survey on techniques of remaining useful life assessment for predictive maintenance of the system publication-title: Int J Comput Digit Syst – volume: 44 start-page: 164 year: 2018 ident: 10.1016/j.ress.2025.110926_b8 article-title: Towards wearable electronic devices: A quasi-solid-state aqueous lithium-ion battery with outstanding stability, flexibility, safety and breathability publication-title: Nano Energy doi: 10.1016/j.nanoen.2017.12.006 – volume: 196 start-page: 6007 issue: 15 year: 2011 ident: 10.1016/j.ress.2025.110926_b17 article-title: A review on prognostics and health monitoring of Li-ion battery publication-title: J Power Sources doi: 10.1016/j.jpowsour.2011.03.101 – start-page: 1 year: 2007 ident: 10.1016/j.ress.2025.110926_b45 article-title: Unsupervised learning of invariant feature hierarchies with applications to object recognition – volume: Vol. 7 start-page: 193 year: 2022 ident: 10.1016/j.ress.2025.110926_b35 article-title: Unsupervised prognostics based on deep virtual health index prediction – volume: 242 year: 2024 ident: 10.1016/j.ress.2025.110926_b38 article-title: Data-driven bearing health management using a novel multi-scale fused feature and gated recurrent unit publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2023.109753 – volume: 4 start-page: 383 issue: 5 year: 2019 ident: 10.1016/j.ress.2025.110926_b54 article-title: Data-driven prediction of battery cycle life before capacity degradation publication-title: Nat Energy doi: 10.1038/s41560-019-0356-8 – start-page: 2 year: 1989 ident: 10.1016/j.ress.2025.110926_b43 article-title: Handwritten digit recognition with a back-propagation network publication-title: Adv Neural Inf Process Syst – volume: 2012 year: 2012 ident: 10.1016/j.ress.2025.110926_b21 article-title: Quantifying cell-to-cell variations in lithium ion batteries publication-title: Int J Electrochem doi: 10.1155/2012/395838 – volume: 232 year: 2021 ident: 10.1016/j.ress.2025.110926_b22 article-title: Remaining useful life and state of health prediction for lithium batteries based on empirical mode decomposition and a long and short memory neural network publication-title: Energy doi: 10.1016/j.energy.2021.121022 – volume: 68 start-page: 2659 issue: 3 year: 2020 ident: 10.1016/j.ress.2025.110926_b26 article-title: Capacity-fading behavior analysis for early detection of unhealthy Li-ion batteries publication-title: IEEE Trans Ind Electron doi: 10.1109/TIE.2020.2972468 – volume: 274 start-page: 237 year: 2015 ident: 10.1016/j.ress.2025.110926_b5 article-title: Advances of aqueous rechargeable lithium-ion battery: A review publication-title: J Power Sources doi: 10.1016/j.jpowsour.2014.10.009 – volume: 18 start-page: 308 year: 2018 ident: 10.1016/j.ress.2025.110926_b1 article-title: Dimensional analysis and modelling of energy density of lithium-ion battery publication-title: J Energy Storage doi: 10.1016/j.est.2018.05.002 – year: 2018 ident: 10.1016/j.ress.2025.110926_b44 article-title: A better autoencoder for image: Convolutional autoencoder – volume: 11 start-page: 33 issue: 4 year: 2008 ident: 10.1016/j.ress.2025.110926_b16 article-title: Prognostics in battery health management publication-title: IEEE Instrum Meas Mag doi: 10.1109/MIM.2008.4579269 – start-page: 355 year: 1998 ident: 10.1016/j.ress.2025.110926_b48 article-title: A view of the EM algorithm that justifies incremental, sparse, and other variants – year: 2018 ident: 10.1016/j.ress.2025.110926_b7 – volume: 421 start-page: 56 year: 2019 ident: 10.1016/j.ress.2025.110926_b27 article-title: Prognostic health condition for lithium battery using the partial incremental capacity and Gaussian process regression publication-title: J Power Sources doi: 10.1016/j.jpowsour.2019.03.008 – year: 2016 ident: 10.1016/j.ress.2025.110926_b49 – volume: 264 year: 2020 ident: 10.1016/j.ress.2025.110926_b2 article-title: Lithium-ion batteries towards circular economy: A literature review of opportunities and issues of recycling treatments publication-title: J Env Manag doi: 10.1016/j.jenvman.2020.110500 – volume: 19 start-page: 113 year: 2018 ident: 10.1016/j.ress.2025.110926_b3 article-title: Modeling the self-discharge by voltage decay of a NMC/graphite lithium-ion cell publication-title: J Energy Storage doi: 10.1016/j.est.2018.07.003 – year: 2021 ident: 10.1016/j.ress.2025.110926_b42 – start-page: 1218 year: 2015 ident: 10.1016/j.ress.2025.110926_b41 article-title: Markov chain Monte Carlo and variational inference: Bridging the gap – start-page: 4062 year: 2017 ident: 10.1016/j.ress.2025.110926_b18 article-title: Life prediction model for grid-connected Li-ion battery energy storage system – start-page: 1613 year: 2015 ident: 10.1016/j.ress.2025.110926_b40 article-title: Weight uncertainty in neural network – volume: 1 year: 2020 ident: 10.1016/j.ress.2025.110926_b58 article-title: Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells publication-title: Energy AI doi: 10.1016/j.egyai.2020.100006 – volume: 230 year: 2023 ident: 10.1016/j.ress.2025.110926_b6 article-title: Battery health prognosis with gated recurrent unit neural networks and hidden Markov model considering uncertainty quantification publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2022.108978 – volume: 183 start-page: 1 year: 2019 ident: 10.1016/j.ress.2025.110926_b11 article-title: Status and future perspectives of reliability assessment for electric vehicles publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2018.11.013 – volume: 2022 year: 2022 ident: 10.1016/j.ress.2025.110926_b32 article-title: A novel method for lithium-ion battery fault diagnosis of electric vehicle based on real-time voltage publication-title: Wirel Commun Mob Comput – start-page: 27 year: 2014 ident: 10.1016/j.ress.2025.110926_b50 article-title: A* sampling publication-title: Adv Neural Inf Process Syst – volume: 10 issue: 2 year: 2023 ident: 10.1016/j.ress.2025.110926_b56 article-title: Early prediction of knee point and knee capacity for fast-charging lithium-ion battery with uncertainty quantification and calibration publication-title: IEEE Trans Transp Electrification doi: 10.1109/TTE.2023.3304670 – volume: 32 year: 2020 ident: 10.1016/j.ress.2025.110926_b25 article-title: Early detection of anomalous degradation behavior in lithium-ion batteries publication-title: J Energy Storage doi: 10.1016/j.est.2020.101710 – volume: 65 start-page: 1526 issue: 2 year: 2017 ident: 10.1016/j.ress.2025.110926_b14 article-title: A double-scale, particle-filtering, energy state prediction algorithm for lithium-ion batteries publication-title: IEEE Trans Ind Electron doi: 10.1109/TIE.2017.2733475 – volume: 226 year: 2022 ident: 10.1016/j.ress.2025.110926_b34 article-title: Learning of physical health timestep using the LSTM network for remaining useful life estimation publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2022.108717 – volume: 228 year: 2022 ident: 10.1016/j.ress.2025.110926_b47 article-title: Bayesian deep-learning for RUL prediction: An active learning perspective publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2022.108758 – volume: 136 start-page: 921 year: 2014 ident: 10.1016/j.ress.2025.110926_b10 article-title: Experimental analysis on the performance of lithium based batteries for road full electric and hybrid vehicles publication-title: Appl Energy doi: 10.1016/j.apenergy.2014.04.013 – volume: 307 year: 2022 ident: 10.1016/j.ress.2025.110926_b30 article-title: Detection of voltage fault in the battery system of electric vehicles using statistical analysis publication-title: Appl Energy doi: 10.1016/j.apenergy.2021.118172 – volume: 31 start-page: 69 issue: 3 year: 2022 ident: 10.1016/j.ress.2025.110926_b13 article-title: Next-generation aviation Li-ion battery technologies—enabling electrified aircraft publication-title: Electrochem Soc Interface doi: 10.1149/2.F10223IF – volume: 224 year: 2022 ident: 10.1016/j.ress.2025.110926_b39 article-title: Health indicator for machine condition monitoring built in the latent space of a deep autoencoder publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2022.108482 – volume: Vol. 96 start-page: 226 year: 1996 ident: 10.1016/j.ress.2025.110926_b52 article-title: A density-based algorithm for discovering clusters in large spatial databases with noise – start-page: 14 year: 2001 ident: 10.1016/j.ress.2025.110926_b53 article-title: On spectral clustering: Analysis and an algorithm publication-title: Adv Neural Inf Process Syst – volume: 245 year: 2024 ident: 10.1016/j.ress.2025.110926_b36 article-title: A hybrid prognosis scheme for rolling bearings based on a novel health indicator and nonlinear Wiener process publication-title: Reliab Eng Syst Saf doi: 10.1016/j.ress.2024.110014 – start-page: 1 year: 2018 ident: 10.1016/j.ress.2025.110926_b59 article-title: Anomaly detection during lithium-ion battery qualification testing – ident: 10.1016/j.ress.2025.110926_b37 doi: 10.36001/phmconf.2016.v8i1.2587 |
| SSID | ssj0004957 |
| Score | 2.4808593 |
| Snippet | Accurate and timely detection of anomalies in lithium-ion batteries is crucial for ensuring their reliability and safety. Complex degradation patterns and... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 110926 |
| SubjectTerms | Deep autoencoder Latent features Reliability test Unsupervised clustering Virtual health indicator |
| Title | An adaptive mixture prior in Bayesian convolutional autoencoder for early detecting anomalous degradation behaviors in lithium-ion batteries |
| URI | https://dx.doi.org/10.1016/j.ress.2025.110926 |
| Volume | 259 |
| WOSCitedRecordID | wos001435735500001&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 issn: 0951-8320 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0004957 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FlgMcEE9RXtoDN8uRH-vHHgMqjwpVHArKzVqv18IlWUdpUqV_AfGjmX3aLVDRAxfLWtuTlefzeLL-5huEXrcpbSDNyMOkoUVIEk7Cus4EPO4qElLetLoXwddPxfFxOZ_Tz5PJD1cLc74opCx3O7r6r66GMXC2Kp29gbu9URiAfXA6bMHtsP0nx89kwBq20pSgZbfTXwhW607zzoM37ELosknFNrfTUGoB202vFC2VsITWANeyx41QXxhMFWO_ZAvFlm2UuITpw-RL_DWlFtL5b912GeoDWrTT0ROd_LdYdEYU_CIQgwqixp7Rkw7OWGtlSSzjwBKHZPBebIc1Vzv6PTjq-_GqRZJ5huuw_BiHEE2icSROrDi4iaVKC9VU0_8W5s2Kw-lUrUhMlfnpcPJlTe0r7zrPQHTkttNK2aiUjcrYuIX2kyKjEOT3Zx8P50dDlS01urFu5rYEy7AFr87kz2nOKHU5uY_u2f8ceGaw8gBNhHyI7o6UKB-hnzOJHWqwRQ3WqMGdxA41-BJq8Ag1GFCDNWqwRw32qMEj1GCPGmV5hBrsUfMYfXl3ePL2Q2gbdYQ8jaJNWLcFS2MB7wNBmlLQvGRFS2PKWVLHoix42RICw6p5ZBYLpX8UtaSNRJmWec5J-gTtyV6KpwjXDYG7yArGOSVM5HWa5bxlvIHgEdU8O0Cxu68Vtyr2qpnKovq7Rw9Q4K9ZGQ2Xa8_OnLsqm4Wa7LIC9F1z3bMb_cpzdGd4LF6gvc16K16i2_x8052tX1no_QJDNbBS |
| 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=An+adaptive+mixture+prior+in+Bayesian+convolutional+autoencoder+for+early+detecting+anomalous+degradation+behaviors+in+lithium-ion+batteries&rft.jtitle=Reliability+engineering+%26+system+safety&rft.au=Chae%2C+Sun+Geu&rft.au=Bae%2C+Suk+Joo&rft.date=2025-07-01&rft.issn=0951-8320&rft.volume=259&rft.spage=110926&rft_id=info:doi/10.1016%2Fj.ress.2025.110926&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ress_2025_110926 |
| 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 |