skip to main content
Idioma:
Tipo de recurso Mostra resultados com: Mostra resultados com: Índice

Machine learning approach for investigating chloride diffusion coefficient of concrete containing supplementary cementitious materials

Quan Tran, Van

Construction & building materials, 2022-04, Vol.328, p.127103, Article 127103 [Periódico revisado por pares]

Elsevier Ltd

Texto completo disponível

Citações Citado por
  • Título:
    Machine learning approach for investigating chloride diffusion coefficient of concrete containing supplementary cementitious materials
  • Autor: Quan Tran, Van
  • Assuntos: Cementitious materials ; Chloride diffusion coefficient ; Concrete ; Durability design ; Machine learning
  • É parte de: Construction & building materials, 2022-04, Vol.328, p.127103, Article 127103
  • Descrição: •An extensive number of Machine Learning algorithms using default hyperparameter are proposed to estimate the coefficient of chloride diffusion of concrete including Supplementary Cementitious Materials (SCMs).•Gradient Boosting algorithm is the most effective Machine Learning algorithm for chloride diffusion coefficient prediction.•SHAP, Individual Conditional Expectation and Partial Dependence Plot 2D quantify factors’ influence on the chloride diffusion coefficient. Chloride diffusion coefficient is an important durability indicator in durability design of concrete structure according to performance-based approach. However, this indicator is difficult to anticipate and design due to a variety of factors such as mix design of concrete, the replacement of supplemental cementitious materials (SCMs), and binder selection. This study proposes an extensive number of machine learning algorithms to predict the chloride diffusion coefficient of concrete containing Supplementary Cementitious Materials (SCMs) such as silica fume, ground granulated blast furnace slag, and fly ash. A database containing nine input variables is created, eight machine learning models consisting of Support Vector Machine (SVM), Extreme Learning Machine (ELM), K-Nearest Neighbors (KNN), Light Gradient Boosting (LGB), Extreme Gradient Boosting (XGB), Random Forest (RF), Gradient Boosting (GB), AdaBoost (AdB) are evaluated via performance criteria such as Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), coefficient of correlation ® and Root Mean Square Error (RMSE). Gradient Boosting model has highest performance in prediction of chloride diffusion coefficient. SHapley Additive exPlanations (SHAP), Individual Conditional Expectation ICE and Partial Dependence Plot PDP 2D allow the most influential inputs to be identified, quantify the influence of input variables on chloride diffusion of concrete. Selection of the best ML algorithm Gradient Boosting is useful to develop a dependable soft computing tool in durability design of concrete structure including the mix design optimization and binder selection.
  • Editor: Elsevier Ltd
  • Idioma: Inglês
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.