Compressive strength and elastic modulus of RBAC: An analysis of existing data and an artificial intelligence based prediction

Created by W.Langdon from gp-bibliography.bib Revision:1.7686

@Article{LIN:2023:cscm,

• author = "Lang Lin and Jinjun Xu and Jialiang Yuan and Yong Yu",
• title = "Compressive strength and elastic modulus of {RBAC:} An analysis of existing data and an artificial intelligence based prediction",
• journal = "Case Studies in Construction Materials",
• volume = "18",
• pages = "e02184",
• year = "2023",
• ISSN = "2214-5095",
• DOI = "doi:10.1016/j.cscm.2023.e02184",
• URL = "https://www.sciencedirect.com/science/article/pii/S2214509523003649",
• keywords = "genetic algorithms, genetic programming, Recycled brick aggregate concrete (RBAC), Compressive strength, Elastic modulus, Artificial neural network, ANN, Multigene genetic programming",
• abstract = "In recent years crushing waste brick to produce recycled brick aggregates (RBAs) has become a viable solution for reducing environmental pollution and addressing the natural resource shortage in civil engineering. To promote the widespread use of the recycled brick aggregate concrete (RBAC) in construction, this study analyzes existing test results on the attributes of RBAs and the compressive mechanical behaviors of RBAC. The review results indicate significant differences and variabilities in the characteristics of RBAs compared to natural coarse aggregates and recycled concrete coarse aggregates. RBAs have the highest absorption capacity and crushing index among the three aggregates, leading to changes in the compressive failure mechanism and a decline in the mechanical properties of RBAC. Additionally, it is also observed that existing formulas do not adequately account for the deterioration of the compressive mechanical properties of RBAC. To tackle this problem, artificial intelligence (AI) approaches including artificial neural network and multigene genetic programming are used to develop precise models for predicting the compressive strength and elastic modulus of RBAC. It is found that RBAC's these two mechanical indexes are mainly influenced by the standard strength of cement paste, water-to-cement ratio, sand-to-aggregate mass ratio, RBA replacement ratio and mass-weighted water absorption ratio of coarse aggregates. The AI models developed in this study accurately capture the trends of these factors and offer desirable predictive results",

}

Genetic Programming entries for Lang Lin Jinjun Xu Jialiang Yuan Yong Yu

Citations