SwePub
Sök i LIBRIS databas

  Utökad sökning

WFRF:(Girolami M.)
 

Sökning: WFRF:(Girolami M.) > Hierarchical Bayesi...

  • Bull, L. A.The British Library, London, UK (författare)

Hierarchical Bayesian modeling for knowledge transfer across engineering fleets via multitask learning

  • Artikel/kapitelEngelska2023

Förlag, utgivningsår, omfång ...

  • 2022-08-08
  • Wiley,2023
  • printrdacarrier

Nummerbeteckningar

  • LIBRIS-ID:oai:DiVA.org:su-209703
  • https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-209703URI
  • https://doi.org/10.1111/mice.12901DOI

Kompletterande språkuppgifter

  • Språk:engelska
  • Sammanfattning på:engelska

Ingår i deldatabas

Klassifikation

  • Ämneskategori:ref swepub-contenttype
  • Ämneskategori:art swepub-publicationtype

Anmärkningar

  • A population-level analysis is proposed to address data sparsity when building predictive models for engineering infrastructure. Utilizing an interpretable hierarchical Bayesian approach and operational fleet data, domain expertise is naturally encoded (and appropriately shared) between different subgroups, representing (1) use-type, (2) component, or (3) operating condition. Specifically, domain expertise is exploited to constrain the model via assumptions (and prior distributions) allowing the methodology to automatically share information between similar assets, improving the survival analysis of a truck fleet (15% and 13% increases in predictive log-likelihood of hazard) and power prediction in a wind farm (up to 82% reduction in the standard deviation of maximum output prediction). In each asset management example, a set of correlated functions is learnt over the fleet, in a combined inference, to learn a population model. Parameter estimation is improved when subfleets are allowed to share correlated information at different levels in the hierarchy; the (averaged) reduction in standard deviation for interpretable parameters in the survival analysis is 70%, alongside 32% in wind farm power models. In turn, groups with incomplete data automatically borrow statistical strength from those that are data-rich. The statistical correlations enable knowledge transfer via Bayesian transfer learning, and the correlations can be inspected to inform which assets share information for which effect (i.e., parameter). Successes in both case studies demonstrate the wide applicability in practical infrastructure monitoring, since the approach is naturally adapted between interpretable fleet models of different in situ examples.

Ämnesord och genrebeteckningar

Biuppslag (personer, institutioner, konferenser, titlar ...)

  • Di Francesco, D.The British Library, London, UK (författare)
  • Dhada, M.University of Cambridge, Cambridge, UK (författare)
  • Steinert, O.Scania CV, ScaniaAB, Södertälje, Sweden (författare)
  • Lindgren, TonyStockholms universitet,Institutionen för data- och systemvetenskap(Swepub:su)tonyn (författare)
  • Parlikad, A. K.University of Cambridge, Cambridge, UK (författare)
  • Duncan, A. B.The British Library, London, UK; Imperial College London, London, UK (författare)
  • Girolami, M.The British Library, London, UK; University of Cambridge, Cambridge, UK (författare)
  • The British Library, London, UKUniversity of Cambridge, Cambridge, UK (creator_code:org_t)

Sammanhörande titlar

  • Ingår i:Computer-Aided Civil and Infrastructure Engineering: Wiley38:7, s. 821-8481093-96871467-8667

Internetlänk

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy