Machine Learning Techniques in Concrete Mix Design

Abstract

Concrete mix design is a complex and multistage process in which we try to find the best composition of ingredients to create good performing concrete. In contemporary literature, as well as in state-of-the-art corporate practice, there are some methods of concrete mix design, from which the most popular are methods derived from The Three Equation Method. One of the most important features of concrete is compressive strength, which determines the concrete class. Predictable compressive strength of concrete is essential for concrete structure utilisation and is the main feature of its safety and durability. Recently, machine learning is gaining significant attention and future predictions for this technology are even more promising. Data mining on large sets of data attracts attention since machine learning algorithms have achieved a level in which they can recognise patterns which are difficult to recognise by human cognitive skills. In our paper, we would like to utilise state-of-the-art achievements in machine learning techniques for concrete mix design. In our research, we prepared an extensive database of concrete recipes with the according destructive laboratory tests, which we used to feed the selected optimal architecture of an artificial neural network. We have translated the architecture of the artificial neural network into a mathematical equation that can be used in practical applications.

Numerical Modelling of Thermal Insulation of Reinforced Concrete Ceilings with Complex Cross-Sections

“…For this reason, the thickness of the foamed polystyrene layer has to be added to obtain the U max coefficient values required for the first and third cases. In these calculations, 0.045 W/(m 2 •K) was adopted as the calculation value of the thermal conductivity coefficient for foamed polystyrene [11]. The obtained results are summarized in Tables 11 and 12.…”

“…The heat transfer coefficient can be determined by conducting tests (nondestructive, laboratory) or by making calculations. Nondestructive testing methods are currently developing very dynamically [4][5][6][7] based on advanced mathematical models, including artificial intelligence [8,9] and machine learning [10][11][12]. However, conducting such tests usually requires the use of specialized equipment [13,14].…”

Mixture Optimization of Recycled Aggregate Concrete Using Hybrid Machine Learning Model

“…ML techniques have also been employed for mixture design and optimization. Concrete mixture design is the process of selecting the appropriate quantitative proportions of concrete ingredients [ 17 ]. From a computational point of view, mixture optimization is the process of minimizing a prior defined objective function [ 18 ].…”

Concrete Compressive Strength under Changing Environmental Conditions during Placement Processes

“…The ultimate durability of concrete depends to a large extent on the contractor that is responsible for the placement and curing process, whose activity is also described by normal provisions and good practices [ 8 ]. Concrete placement is an essential part of the technological process of concrete production and is preceded by the following steps: concrete mix design [ 9 , 10 , 11 , 12 ], concrete mix fabrication, and transportation to the construction site. Transportation and placement are especially vulnerable to environmental conditions, such as temperature and precipitation.…”