Significance of chloride penetration controlling parameters in concrete: Ensemble methods

Research output: Contribution to journalArticleScientificpeer-review

7 Citations (Scopus)

Abstract

Conventional chloride ingress prediction models rely on simplified assumptions, leading to inaccurate estimations. Reasonable simplifications can be achieved if and only if the effects of all interacting variables are clearly known. In this work, ensemble methods to discover significant parameters that control chloride ingress using long-term field data is developed and presented. The models are trained using dataset consisting of variables describing the concrete mix ingredients, fresh and hardened properties, field conditions as well as chloride profiles. The results analyses confirm that the models are able to determine the optimal subset of the influential variables that best predicts the chloride profile from the input dataset.
Original languageEnglish
Pages (from-to)9-23
JournalConstruction and Building Materials
Volume139
DOIs
Publication statusPublished - 15 May 2017
MoE publication typeA1 Journal article-refereed

Keywords

  • reinforced concrete
  • chloride ingress
  • corrosion
  • durability
  • simplified models
  • modelling
  • ensemble methods
  • variable importance analysis
  • machine learninhg

Fingerprint Dive into the research topics of 'Significance of chloride penetration controlling parameters in concrete: Ensemble methods'. Together they form a unique fingerprint.

Cite this