Damage tolerance reliability analysis combining Kriging regression and support vector machine classification - Université de technologie de Compiègne Access content directly
Journal Articles Engineering Fracture Mechanics Year : 2019

Damage tolerance reliability analysis combining Kriging regression and support vector machine classification

Paul Beaucaire
  • Function : Author
Loïc Debeugny
  • Function : Author
Jean-Pierre Lefebvre
  • Function : Author
Caroline Sainvitu
  • Function : Author
Piotr Breitkopf
Eric Wyart
  • Function : Author

Abstract

Damage tolerance analysis associates a Fracture Mechanical model with the Failure Assessment Diagram to defi ne the state of a space engine component. The reliability analysis treats the variability of numerical models assessing the probability of failure within Linear Elastic Fracture Mechanics (LEFM) hypotheses. However, these models, while providing quantitative information in the safe domain, give only qualitative information for failed components. This work proposes an original methodology to combine Kriging regression and the Support Vector Machine classifi cation along with transition criteria between both approaches. To accurately describe the limit state, we de ne a spefici c enrichment strategy. The efficiency of the proposed methodology is illustrated on reference test cases.
Fichier principal
Vignette du fichier
S0013794418303680.pdf (439.42 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03328337 , version 1 (25-10-2021)

Licence

Attribution - NonCommercial

Identifiers

Cite

Rudy Chocat, Paul Beaucaire, Loïc Debeugny, Jean-Pierre Lefebvre, Caroline Sainvitu, et al.. Damage tolerance reliability analysis combining Kriging regression and support vector machine classification. Engineering Fracture Mechanics, 2019, 216, pp.106514. ⟨10.1016/j.engfracmech.2019.106514⟩. ⟨hal-03328337⟩
38 View
66 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More