Physics-informed modeling of splitting tensile strength of recycled aggregate concrete using advanced machine learning

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 28, 2025

Physics-informed modeling (PIM) using advanced machine learning (ML) represents a paradigm shift in the field of concrete technology, offering potent blend scientific rigor and computational efficiency. By harnessing synergies between physics-based principles data-driven algorithms, PIM-ML not only streamlines design process but also enhances reliability sustainability structures. As research continues to refine these models validate their performance, adoption promises revolutionize how materials are engineered, tested, utilized construction projects worldwide. In this work, an extensive literature review, which produced global representative database for splitting tensile strength (Fsp) recycled aggregate concrete, was indulged. The studied components such as C, W, NCAg, PL, RCAg_D, RCAg_P, RCAg_wa, Vf, F_type were measured tabulated. collected 257 records partitioned into training set 200 (80%) validation 57 (20%) line with more reliable partitioning database. Five techniques created "Weka Data Mining" software version 3.8.6 applied predict Fsp Hoffman & Gardener method performance metrics used evaluate sensitivity variables ML models, respectively. results show Kstar model demonstrates highest level among achieving exceptional accuracy R2 0.96 Accuracy 94%. Its RMSE MAE both low at 0.15 MPa, indicating minimal deviations predicted actual values. Additional WI (0.99), NSE (0.96), KGE (0.96) further confirm model's superior efficiency consistent making it most dependable tool practical applications. Also analysis shows that Water content (W) exerts significant impact 40%, demonstrating amount water mix is critical factor optimal strength. This underscores need careful management balance workability sustainable production. Coarse natural (NCAg) has substantial 38%, its essential role maintaining structural integrity mix.

Language: Английский

Performance optimization of hybrid nano-engineered geopolymer binders-based ultra-high-performance concrete

Nano-Structures & Nano-Objects, Journal Year: 2025, Volume and Issue: 42, P. 101469 - 101469

Published: March 12, 2025

Language: Английский

Hybrid Machine Learning Based Strength and Durability Predictions of Polypropylene Fiber-Reinforced Graphene Oxide Based High-Performance Concrete

Iranian Journal of Science and Technology Transactions of Civil Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 19, 2025

Language: Английский