Dwarf mongoose-tree-based analysis for estimating the frost durability of recycled aggregate concrete

A promising approach to enhancing sustainability within the construction industry is the development of recycled aggregate concrete ( RAC ), which involves substituting natural aggregates with recycled materials. This innovative material not only reduces the environmental impact associated with the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Multiscale and Multidisciplinary Modeling, Experiments and Design Jg. 7; H. 6; S. 6305 - 6321
Hauptverfasser: Zhang, Lingtong, Zhang, Qinling, Liang, Sheng, Zhang, Dong, Chen, Dongjie
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 01.11.2024
Schlagworte:
Characterization and Evaluation of Materials
Engineering
Mathematical Applications in the Physical Sciences
Mechanical Engineering
Numerical and Computational Physics
Original Paper
Simulation
Solid Mechanics
Dwarf mongoose algorithm
Concrete
Cold climate
Recycled aggregate
Frost durability
ISSN:2520-8160, 2520-8179
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A promising approach to enhancing sustainability within the construction industry is the development of recycled aggregate concrete ( RAC ), which involves substituting natural aggregates with recycled materials. This innovative material not only reduces the environmental impact associated with the extraction and processing of natural aggregates but also promotes the circular economy by repurposing waste materials. Evaluating the frost durability of RAC through the Durability Factor (D f ) is critical for several reasons in the realms of construction and civil engineering. This study investigates the frost durability of recycled aggregate concrete ( RAC ) by utilizing data mining techniques to predict the durability factor (D f ) in cold regions. The necessity for this research arises from the growing need for sustainable construction practices, particularly through the use of recycled materials. We employed least square support vector regression ( LSSVR ) and Random Forest ( RF ) analysis to assess the frost resistance of RAC, focusing on key input parameters such as concrete components, recycled aggregate characteristics, treatment processes, and air-entraining agents. Our findings reveal that the RF model, enhanced by the dwarf mongoose algorithm ( RFDM ), outperforms the LSSVR model (LSDM) in both the training and testing phases. Specifically, the RFDM achieved a training deviation of approximately 40% and a testing variance of around 20%, indicating its superior predictive accuracy. The RFDM model's lower error indicators demonstrate its reliability and effectiveness compared to LSSVR , making it a preferred choice for predicting the D f of RAC in frigid conditions. This study not only contributes to understanding the frost resistance of RAC but also highlights the advantages of using advanced data mining techniques in civil engineering applications.
ISSN:2520-8160
2520-8179
DOI:10.1007/s41939-024-00577-2