Properties prediction of environmentally friendly ultra-high-performance concrete using artificial neural networks

Abstract

Ultra-high-performance concrete (UHPC) results from the mixture of several constituents, leading to a highly complex material in both, fresh and hardened state. The higher number of constituents, together with a higher number of possible combinations, relative proportioning and characteristics, makes the behavior of this type of concrete more difficult to predict. The objective of the research is to build four analytical models, based on artificial neural networks (ANN), to predict the 1-day, 7-day, and 28-day compressive strengths and slump flow. Recycled glass powder milled to different particle size, fluid catalytic cracking residue (FCC) and different particle size limestone powder was used as partial replacements for Portland cement and silica fume. The ANN models predicted the 1-day, 7day, and 28-day compressive strengths and slump flow of the test set with prediction error values (RMSE) of 2.400 MPa, 2.638 MPa, 2.064 MPa and 7.245 mm respectively. The results indicated that the developed ANN models are an efficient tool for predicting the slump flow and compressive strengths of UHPC while incorporating silica fume, limestone powder, recycled glass powder and FCC.

Comparación de modelación por Inteligencia Artificial y Regresión Multivariable del comportamiento a flexión del UHPFRC

“…Para aplicaciones más complejas se usan las arquitecturas de perceptrón multicapa feed-forward [2,3].…”

“…En los últimos años la investigación sobre concretos especiales de alto desempeño ha sufrido un importante progreso [1][2][3]. Entre éstos cabrían destacar los concretos de ultra alto desempeño reforzados con fibras (UHPFRC por sus siglas en inglés).…”

“…Una dosificación típica de UHPFRC contiene cemento tipo Portland, micro sílice, harina de cuarzo, arena fina silícea, superplastificante reductor de agua de alto rango (HRWR), y fibras metálicas [13][14][15]. Sin embargo, en los últimos tiempos se ha hecho especial hincapié en el desarrollo de mezclas que incorporen diferentes materiales cementantes suplementarios en sustitución parcial del cemento, humo de sílice y total de harina de cuarzo [1,2,5].…”

Application of artificial neural networks and multiple linear regression on local bond stress equation of UHPC and reinforcing steel bars

“…They indicated that the effect of each principal material or additive on concrete behavior can be logically evaluated by the ANN methodology. The research works of Abellán et al 32 – 34 have focused on combining different methods of neural networks, data mining, multi-objective optimization, and design of experiments (DOE). They studied how to improve the compressive strength over 150 MPa by using local raw materials in Colombia, while reducing the content of silica admixture.…”

Ultra-high-performance concrete with local high unburned carbon fly ash

“…DYNA, 88(216), pp. 38-47, January -March, 2021 reaction, combined with the use of superplasticizer to reduce the water-to-cementitious materials ratio [1][2][3]. These extremely low porosity and low permeability characteristics of ultra-high-performance concrete (UHPC) give it enhanced durability and mechanical properties over other types of concrete, such as normal concrete and high strength concrete Components and its implication in cost.…”