Four-layer perceptron approach for strength prediction of UHPC

•A model for predicting the compressive strength of UHPC was developed.•The model considers the inclusion of several SCM as component of UHPC.•The model can be used regardless the maximum size of the aggregate.•VPD and cement content are the most important factors in improving UHPC’s strength.•The m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Construction & building materials Jg. 256; S. 119465
1. Verfasser: Abellán-García, Joaquín
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 30.09.2020
Schlagworte:
Compressive strength
Maximum size of aggregate
MLP
Olden algorithm
Resilient back-propagation algorithm
SCM
UHPC
MLP
Olden algorithm
UHPC
Resilient back-propagation algorithm
Maximum size of aggregate
Compressive strength
SCM
ISSN:0950-0618, 1879-0526
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•A model for predicting the compressive strength of UHPC was developed.•The model considers the inclusion of several SCM as component of UHPC.•The model can be used regardless the maximum size of the aggregate.•VPD and cement content are the most important factors in improving UHPC’s strength.•The model can be used to predict the properties of new mixtures with good accuracy. This research is aimed to develop a four-layer multi-layer-perceptron (MLP) model for predicting the compressive strength of ultra-high-performance concrete (UHPC), regardless of the combination of a wide range of supplementary cementitious materials (SCM) or the maximum size of aggregate used. UHPC is a high-tech type of concrete resulted of the mixture of several constituents. Therefore, the effect of each component and their interactions on compressive strength is more difficult to understand than in conventional concrete. A total of 210 own experimental campaign data added to 717 published work throughout the world data were used for training purposes by using the R-code language. To analyze the relationships between the UHPC’s components and strength, the Olden algorithm was used. The interpretation of both the statistical performance metrics and the results of Olden’s sensitivity analysis indicated that the proposed model was an efficient approach for predicting the compressive strength of UHPC. The trained MLP model can be used for forecasting the compressive strength for a given UHPC mixture design in quick time without performing any trial.
ISSN:0950-0618
1879-0526
DOI:10.1016/j.conbuildmat.2020.119465