Article

Model-Based Adaptive Machine Learning Approach in

Concrete Mix Design
Patryk Ziolkowski 1,*, Maciej Niedostatkiewicz 1 and Shao-Bo Kang 2,3

1 Faculty of Civil and Environmental Engineering, Gdansk University of Technology,

Gabriela Narutowicza 11/12, 80-233 Gdansk, Poland; mniedost@[Link]
2 School of Civil Engineering, Chongqing University, Chongqing 400045, China; kang0119@[Link]

3 Key Laboratory of New Technology for Construction of Cities in Mountain Area, Chongqing University,

Chongqing 400045, China

* Correspondence: patziolk@[Link]; Tel.: +48-58-347-2385

Abstract: Concrete mix design is one of the most critical issues in concrete technology. This process
aims to create a concrete mix which helps deliver concrete with desired features and quality. Con-
temporary requirements for concrete concern not only its structural properties, but also increasingly
its production process and environmental friendliness, forcing concrete producers to use both chem-
ically and technologically complex concrete mixtures. The concrete mix design methods currently
used in engineering practice are joint analytical and laboratory procedures derived from the Three
Equation Method and do not perform well enough for the needs of modern concrete technology.
This often causes difficulties in predicting the final properties of the designed mix and leads to pre-
cautionary oversizing of concrete properties for fear of not providing the required parameters. A
new approach that would make it possible to predict the newly designed concrete mix properties is
highly desirable. The answer to this challenge can be methods based on machine learning, which
have been intensively developed in recent years, especially in predicting concrete compressive
Citation: Ziolkowski, P.;
strength. Machine learning-based methods have been more or less successful in predicting concrete
Niedostatkiewicz, M.; Kang, S.-B.
compressive strength, but they do not reflect well the variability that characterises the currently
Model-Based Adaptive Machine
used concrete mixes. A new adaptive solution that allows estimating concrete compressive strength
Learning Approach in Concrete Mix
Design. Materials 2021, 14, 1661.
on the basis of the concrete mix main ingredient composition by including two observations for a
[Link] given batch of concrete is proposed herein. In presented study, a machine learning model was built
with a deep neural network architecture, trained on an extensive database of concrete recipes, and
Academic Editors: Łukasz Sadowski translated into a mathematical formula. Testing on four concrete mix recipes was performed, which
and Qing-feng Liu were calculated according to contemporary design methods (Bolomey and Fuller method), and a
comparative analysis was conducted. It was found out that the new algorithm performs signifi-
Received: 30 January 2021 cantly better than that without adaptive features trained on the same dataset. The presented algo-
Accepted: 24 March 2021 rithm can be used as a concrete strength checking tool for the concrete mix design process.
Published: 28 March 2021

Keywords: applied machine learning; concrete; concrete mix design; concrete strength prediction;
Publisher’s Note: MDPI stays neu-
data mining
tral with regard to jurisdictional
claims in published maps and insti-
tutional affiliations.

1. Introduction
Concrete mix is a mixture of cement, water, and fine-grained and coarse-grained ag-
Copyright: © 2021 by the authors. Li- gregate, as well as additives and admixtures. Additives and admixtures are designed to
censee MDPI, Basel, Switzerland. improve the chemical characteristics and performance parameters of concrete, especially
This article is an open access article compressive strength, durability, and workability. One can distinguish many such sup-
distributed under the terms and con- plements, including accelerating admixtures, admixtures for improved fresh concrete
ditions of the Creative Commons At- properties, durability-enhancing admixtures, fibers for concrete strengthening, set-retard-
tribution (CC BY) license ([Link]
ing admixtures, and water-reducing admixtures. The concrete mix’s appropriate design
[Link]/licenses/by/4.0/).
is one of the most critical issues in the construction process, which is considered on many

Materials 2021, 14, 1661. [Link] [Link]/journal/materials

Materials 2021, 14, 1661 2 of 32

levels. The concrete mix must be designed economically. This means that it must allow
obtaining the desired properties at the lowest possible cost of raw materials. A concrete
mixture is dedicated to a specific technological process, where properties such as worka-
bility or cement setting speed are vital. Subsequently, there are environmental conditions
related to precipitation, temperature during concreting, the distance from the construction
site, and the traffic volume. The composition of the concrete mix significantly depends on
the assumed construction specification resulting from the construction design, in which it
is assumed, for example, the compressive strength of concrete, or environmental aggres-
sion, such as chloride ingression. The last important factor determining the composition
of the concrete mix is ecological considerations, which have recently gained particular
importance. There are currently many solutions to reduce the carbonation of concrete,
such as admixtures of graphene nanoparticles [1].
In conclusion, it can be said that designing a concrete mix comes down to the appro-
priate selection of the proportions of the primary and secondary components in order to
obtain concrete with the desired properties. During the technological process of concrete
production, the concrete mix is transported to the construction site and placed in the con-
crete formwork; then, the process of concrete hardening and gaining strength occurs. The
hydration of the cement initiates the concrete hardening process. Cement hydration is an
exothermic chemical reaction that occurs when cement comes in contact with water. After
starting the hydration process, the cement forms tobermorite gel, hydroxide, and other
ingredients, which enhance adhesion between the fine-grained and coarse-grained aggre-
gate. Throughout this process, hydration products continuously deposit on the cement
grains and fill the area occupied by the water. The final stage of the hydration process is
when all water molecules are bound, or there is no more unreacted cement. Hardened
concrete obtains partial compressive strength a few days after the hydration process starts,
and most of compressive strength after around 28 days (some types of concrete reach their
full strength later) [2–4]. The amount of water needed to hydrate the cement entirely var-
ies between 20% and 25% by weight, not including the water trapped in the pores [5,6]. In
keeping with Power’s model, the water required to hydrate cement is 42% by weight [7,8].
Concrete mix design methods, which are currently used in engineering practice, derive
from solutions developed over a dozen years ago and are based on an estimation of con-
crete mortar strength for bending [9–11]. The practical application of these methods is
laborious and ineffective, and it does not consider the chemical complexity and variability
of modern concrete mixtures.
The presented field needs new technological solutions that will face current chal-
lenges, and the answer might lay in machine learning-based methods that are more or less
successful in predicting concrete compressive strength; however, they do not reflect well
the variability of new chemically complex concrete mixes. This paper presents a novel
adaptive approach that allows estimating concrete compressive strength on the basis of
the concrete mix main ingredient composition by including two observations for a given
batch of concrete. The proposed solution is a deep neural network with 46 hidden neu-
rons, clustered in seven layers. The machine learning model was built, trained on an ex-
tensive database of concrete recipes, and translated into a mathematical formula. Testing
on four concrete mix recipes was performed, which were also calculated according to the
Bolomey and Fuller method, and a comparative analysis was conducted. The presented
algorithm can be used as a concrete strength checking tool for the concrete mix design
process. Machine learning is part of a rapidly developing field of knowledge, within the
broader domain of artificial intelligence. It enables systems to automatically learn and im-
prove from experience without direct programming and specific tasks. There are many
different approaches to machine learning, among which the most popular are artificial
neural networks (ANNs), with many branches such as deep neural networks (DNNs), re-
current neural networks (RNNs), and convolutional neural networks (CNNs). There are
also other approaches, such as gene expression programming (GEP) and multi expression
programming (MEP) [12–14]. The basic unit of an ANN is an artificial neuron, grouped
Materials 2021, 14, 1661 3 of 32

into clusters. A single artificial neuron can be treated as a recitative information carrier,
just like a human neuron excitably conducts an electrical signal. Artificial neurons in the
network somewhat mimic the behavior of the human brain. The clusters of neurons are
grouped into layers. The ANN typically includes at least three layers, an input layer, a
hidden layer, and an output layer. The input and output layers consist of input neurons
and output neurons, respectively. These neurons represent the variables that we want to
introduce into the algorithm and the variables resulting from the algorithm’s execution.
The neurons process the input data with the appropriate weight in the hidden layer and
provide the output by the activation function. Depending on the type, specificity, amount
of data, and machine learning architecture, hidden layers may function differently. In
some methods, the input variable’s weight is assigned randomly, and, in others, the
weight is meticulously calibrated by backpropagation. There is also a weight control
mechanism, called the “learning rule”. It can be said that a greater number of hidden lay-
ers allows ANNs to solve more difficult problems, but more computing power and time
will be needed for calculations. ANNs are taught how to solve a problem upon being fed
examples. ANNs are proven effective in finding patterns that would be difficult for hu-
man recognition. A deep neural network (DNN) is an artificial neural network (ANN)
with multiple layers of hidden neurons, and it is characterized by a high level of complex-
ity [15–18].

2. Concrete Mix Design and Machine Learning

2.1. Contemporary Engineering Practice in Concrete Mix Design
Concrete mix design is a complex issue, often requiring extensive knowledge of con-
crete technology and vast experience. The main task in the design process is to select appro-
priate material compositions to obtain a concrete mix with desired properties, both in the
form of a fresh mix during transport and concreting and in the form of hardened concrete.
Specific properties can be expected at each stage of the concrete structure manufacturing
process. Several features characterize concrete performance, such as plasticity, durability,
compressive strength, and modulus of elasticity. The properties mentioned above have dif-
ferent priorities at different times; for example, adequate compressive strength is essential
from the point of view of designed ultimate limit state, while adequate durability is essential
in an aggressive environment [19–22]. Designing a mix with the improper specification can
have many serious consequences; therefore, concrete mix producers fearing failure to meet
the appropriate criteria often deliberately augment its parameters beyond designed values.
This leads to the phenomenon called “concrete superstrength”, which on the surface may
seem beneficial, because, for example, in a case of concrete compressive strength, the
strength of concrete is higher; however, the disturbed stiffness of the structure may cause
the structure to behave differently than envisaged by the designer [23].
Corporate engineering practice varies across the world, while also sharing significant
similarities. In the European Union, the norm governing concrete technology issues is “EN
206 Concrete: Specification, performance, production, and conformity”, while the design
of concrete structures is described in the standard “EN 1992-1-1: Eurocode 2: Design of
concrete structures”. There are equivalents and national appendices for each standard,
e.g., in Great Britain, the BS EN 206: 2013 + A1: 2016 standard is used, while, in Poland,
the PN-EN 206 + A1: 2016-12 standard is used. Depending on the member state of the
European Union, various methods of designing concrete mix are popular. In Poland, the
methods of Bukowski, Eyman, Klaus, Kopycinski and Paszkowski are most often used,
along with the so-called double coating method [24]. On the other hand, in the United
States of America, Bolomey, Fuller, and the 0.45 power gradation chart methods are the
most popular. Most of these methods are derived from the so-called “Three Equations
Method”, a merged experimental–analytical approach [11,25,26]. The experimental–ana-
lytical approach means that we need to calculate the volume of ingredients needed by an
analytical method and validate it using destructive laboratory tests. This method allows
Materials 2021, 14, 1661 4 of 32

us to determine the amount of cement, water, and aggregate by weight per unit volume,
using three equations of consistency, strength, and water-tightness. Consistency Equation
(1) is incorporated into the water-demand formula, which helps to find the desired con-
sistency.
𝑊 = C ∙ 𝑤 + K ∙ 𝑤 [l], (1)

where 𝑊 is the amount of water in 1 m3 of concrete, expressed in units of volume (in this
case, L), C represents the weight of cement in 1 m3 of concrete, expressed in kg, 𝑤 is a
cement–water demand index which denotes the amount of water in 1 dm3 that should be
added to 1 kg of a given class of cement, expressed in L/kg, K corresponds to the weight
of aggregate in 1 m3 of concrete, expressed in kg, and 𝑤 is an aggregate–water demand
index which denotes the amount of water in 1 dm3 that should be added to 1 kg of dry
aggregate of a certain fraction to obtain the desired consistency, expressed in L/kg. The
cement–water demand index and aggregate–water demand index depend on the grain
size, shape, surface roughness, proportion in a given composition, and required con-
sistency of the concrete mix. The water demand for concrete additives and admixtures is
considered by adding it to aggregate or cement depending on the grain size. The cement–
water and aggregate–water demand indices were developed by Stern and Bolomey
[27,28]. The next equation is called the concrete compressive strength equation, which
comes in two versions, Bolomey and Feret. This equation describes the relationship be-
tween the compressive strength of concrete and parameters such as the water–cement ra-
tio and the grade of cement and aggregate. Equation (2) is the Feret version of the concrete
compressive strength equation. Equation (3) is the Bolomey version of the concrete com-
pressive strength equation.

𝑓 =𝐴 + 𝑝 − 𝑎 [MPa], (2)

𝑓 =𝐴 , ± 𝑎 [MPa], (3)

where 𝑓 is a medium concrete compressive strength, expressed in MPa, and 𝐴, 𝐴 , are

coefficients that depend on the type and strength class of the aggregate and the strength
class of the cement. The coefficient 𝐴 is taken when C/W < 2.5 and 𝐴 is taken when C /
W > 2.5. 𝐶 represents the weight of cement in 1 m3 of concrete, expressed in kg, 𝑊 rep-
resents the amount of water in 1 m3 of concrete, expressed in L; 𝑝 is the amount of air in
1 m3 of concrete, expressed in dm3, and 𝑎 is a numerical value depending on the quality
of cement and aggregate, and it can be taken as a constant equal to 0.5. The 𝑎 value is
positive when the water–cement ratio is greater than or equal to 2.5 and negative when
the water–cement ratio is less than 2.5. The Feret equation is valid when the aggregate
strength is lower than the grout strength and applies to porous concrete. Lastly, Equation
(4) is called the water-tightness equation, which tells us that the volume sum of the indi-
vidual components is equal to the entire concrete mix volume.

+ + 𝑊 = 1000 [dm3], (4)

where 𝑊 refers to the amount of water in 1 m3 of concrete, expressed in L, 𝐶 represents

the weight of cement in 1 m3 of concrete, expressed in kg, 𝜌 is the cement density in
kg/dm3, 𝐾 is the weight of cement in 1 m3 of concrete, expressed in kg, and 𝜌 is the ag-
gregate density in kg/dm3. The quantitative composition of the concrete mix, considered
as the amount of cement, water, and aggregate in 1 m3 of mixture, can be calculated using
the equations described above. The Three Equations Method has certain boundary condi-
tions. The concrete mix porosity should not exceed 0.002 of the mix volume without air-
entraining admixtures or 0.008 of the mix volume using air-entraining admixtures.
The entire process of concrete mix design consists of the following stages: determin-
ing the initial assumptions, determining the required properties of hardened concrete and
Materials 2021, 14, 1661 5 of 32

fresh concrete mix, selecting and evaluating the components of the concrete mix, design-
ing the mix composition, checking the technical characteristics of the fresh concrete mix
and hardened concrete in a laboratory, and preparing a working recipe. During the for-
mulation of initial assumptions, several factors need to be considered, such as the concrete
mix’s intended use, which depends on properties of the newly designed structure, includ-
ing the location, amount of reinforcement, and geometric characteristics of the cross-sec-
tion. The primary technical characteristics of fresh concrete mix are the bulk density, con-
sistency, and air content, whereas those for hardened concrete are the frost resistance, fire
resistance, and class of concrete compressive strength. It is necessary to analyze the tech-
nological process, as well as assess the conditions of concrete maturation and the method
of compacting fresh concrete mix. The concrete exposure class, which corresponds to the
degree and type of environmental aggression and additional properties, such as concrete
tightness, should also be specified. It is necessary to determine maximum aggregate di-
ameter and mix workability. The concrete mix components should be selected and evalu-
ated, including the proper type of cement, appropriate water, and aggregate quality, char-
acterized by the relevant standards. After designing the concrete mix composition and
laboratory tests, the last part of the process is preparing a working recipe for 1 m3 of con-
crete mix. It is also vital to consider the recipe changes that may result from the dampness
of the aggregate and adapt it to individual conditions, such as the capacity of a transport
vehicle [29,30].

2.2. Machine Learning in Prediction of Concrete Features

Machine learning is used in many science areas, from forecasting real-estate prices to
identifying conditions on the basis of computed tomography images. One of these areas
is civil and structural engineering. In civil and structural engineering, machine learning is
used in structural health monitoring, crack detection, life-cycle cost analysis, prediction of
soil compression coefficient, and many more. In forecasting concrete properties, research
focuses on predicting a concrete’s compressive strength, which is one of the most critical
parameters of concrete and defines its class.
The challenge in predicting concrete strength by machine learning was first described
by Yeh et al. [31] in 1998. Using seven input variables, they performed ANN and linear
regression to predict the strength of high-strength concrete. Yeh et al. trained their algo-
rithm on many concrete samples, but they were not filtered in terms of content. Their
analysis took into account the concrete samples in the maturing phase, even those that
were 3 days old, which may have significantly distorted the results.
In 2003, the topic was developed further by Seung-Chang Lee [32]. He utilized a mod-
ular network architecture, which consisted of five ANNs with unique architectures. These
unique architectures corresponded to concrete in different maturation phases up until
achieving full concrete strength. To estimate the number of neurons in the input layer, he
used the parameter condensation technique. Seung-Chang Lee claimed that the conden-
sation and weighing techniques he used are useful in finding optimal network perfor-
mance. However, since his ANN models the maturation process from the moment after
pouring to reaching full strength, it has no practical application. From an engineering
practice point of view, the focus should be on concrete that has reached its full or most of
its strength.
In 2005, Hola J. and Schabowicz K. [33,34] presented an attractive nondestructive
concrete strength assessment approach. They used an ANN model trained not on the con-
crete mix composition, but on the data collected by nondestructive concrete testing equip-
ment. Their database contained ultrasonic wave velocity, reflection number, hardness,
pull-out strength, concrete age, and bulk density. To obtain the laboratory results, they
tested concrete compressive strength samples with a 28 day strength of 24–105 MPa. They
created the ANN with eight hidden neurons grouped in one layer, using the Levenberg–
Marquardt training method. The authors claimed that the average concrete compressive
strength compared between the ANN and nondestructive tests was similar.
Materials 2021, 14, 1661 6 of 32

In 2006, Gupta et al. [35] proposed using a neural-expert system to predict the com-
pressive strength of high-performance concrete. In their method, Gupta et al. focused on
training the algorithm using example inferences and used a multilayer ANN trained with
generalized backpropagation for interval training patterns. This may lead to algorithm
training based on patterns with insignificant variables. They also used input variables of
completely different metrics not strictly related to the recipe, such as curing time, and
focused on basics such as the concrete mix composition, which may have an unclear effect
on results. The neural-expert system in concrete compressive strength prediction was also
discussed by Dac-Khuong Bui et al. [36], where they focused on the practical application
of this approach.
In 2018, Fangming Deng et al. [37] introduced deep learning to the subject. Fangming
Deng et al. for algorithm training purposes prepared a database of recycled concrete sam-
ples. Their database provided five input variables, such as fly ash replacement, recycled
coarse-grained aggregate replacement ratio, recycled fine-grained aggregate replacement
ratio, and water–cement ratio, used to train the machine learning algorithm. They decided
not to train the algorithm on the concrete mix composition with a direct amount of indi-
vidual components, but on the several ratios, which they referred to as deep features. In
this study, a similar approach was used by introducing feature scaling. They used Softmax
regression to look for a suitable prediction model. Fangming Deng et al. claimed that the
introduction of deep learning compared to ANN provided better generalization capabili-
ties, superior efficiency, and higher precision. However, this was not apparent and should
be the subject of more extensive research. First, convolution neural networks are compu-
tationally expensive, as evidenced by the author’s adoption of a limited database. They
used 74 samples in comparison to the 741 samples in this analysis. The limited number of
samples may result in underfitting, which means that the model does not properly repre-
sent the modeled phenomenon. A similar level of accuracy between artificial neural net-
works and deep neural networks was presented by Hosein Naderpour et al. [38] in his
study from 2018.
In 2019, Ziolkowski P. et al. [16] presented an algorithm, which supports designing a
concrete mix by predicting the strength of concrete based on the composition of the con-
crete mix. The algorithm gave a quite right prediction of concrete mix strength. However,
the paper’s algorithm gave a weak approximation for the high-strength spectrum of 40
MPa and above. It was also poorly able to predict the properties of mixtures with concrete
additives and admixtures. Other essential parameters that contribute to proper concrete
performance, such as durability, which is vital to maintain the service quality of structure
in time, were not recognized in the study [39].
In 2020, Adil M. et al. [40] presented a paper in which they studied the effect of the
number of neurons and layers in ANN for generalized concrete mix design. They used
ANN with 17 inputs, such as the specific gravity of concrete mix ingredients, dry density
of aggregates, type of cement and mineral admixtures, water–cement ratio, modulus of
elasticity, and tensile and compressive strength of concrete, as well as five outputs, such
as cement, water, and fine-grained and coarse-grained aggregate content. The authors ar-
gued that this network performed best with one or two hidden layers. It is an entirely
different approach to a large number of previous works, where the technical parameters
of concrete were predicted on the basis of the composition ratio.
In 2020, Nunez I. et al. [41] presented a study in which they built a machine learning
model to predict the recycled aggregate concrete compressive strength and optimize the
concrete mix design process. A reliable optimization method for concrete mix design is
especially significant for recycled aggregate concrete, due to its variability and lack of
proper compressive strength estimation formulas. The authors developed three distinc-
tive machine learning models, namely, the Gaussian processes model, recurrent neural
network model, and gradient boosted regression trees model, and they claimed to achieve
robust predictive performance. They obtained the best performance using the gradient
boosted regression trees model.
Materials 2021, 14, 1661 7 of 32

In 2020, Marani A. et al. [42] presented a solution to predict the compressive strength
of ultra-high-performance concrete using a machine learning algorithm. They trained
their algorithm on a database of 810 samples gathered from open-access sources. The da-
tabase consisted of 15 variables that were taken as input data. The authors used an unu-
sual technique, whereby, thanks to their database, they generated 6513 plausible synthetic
data samples using tabular generative adversarial networks. Such a large pool of data
allowed for robust training of their machine learning model. The authors found that their
model trained on synthetic data achieved outstanding predictive performance when
tested on the primary dataset.

3. Materials and Methods

3.1. Essentials
Most of the solutions described in the literature that could support the concrete mix
design process consist of predicting the concrete compressive strength as a function of the
concrete mix composition or basic technical parameters. The previously mentioned ap-
proaches could be improved by introducing an algorithm calibrated for a specific batch of
concrete. This is essential for several reasons, the most important of which is the chemical
complexity caused by various concrete admixtures, which is currently a standard. There
are many different concrete admixtures, such as accelerating admixtures, admixtures for
improved fresh concrete properties, durability-enhancing admixtures, fibers for concrete
strengthening, set-retarding admixtures, water-reducing admixtures, and novel additions
of nanomaterials such as graphene. These admixtures can significantly affect the obtained
concrete parameters, especially compressive strength. It is also difficult to predict how a
mixture with many different admixtures or admixtures produced by different manufac-
turers will behave in service. The second reason concerns the variability caused by the use
of raw materials from different manufacturers, from different mining sources, and char-
acterized by different properties. The variability can manifest itself on many levels, from
the shape of the coarse aggregate to the presence of clay in the fine-grained aggregate. The
algorithm’s primary task is to estimate concrete compressive strength as a function of the
concrete mix composition calibrated by two observations. Observation encompasses the
complete concrete recipe, along with compressive strength for a given type of concrete.
The algorithm uses two recipes for a given concrete and tries to estimate the third recipe’s
concrete compressive strength.
In current considerations, the database from a previous study [16] was used. The col-
lected database serves as a basis for training the DNN with respect to the dependencies
between individual input variables and the output variable. The data collection is exten-
sive and includes various concrete mix recipes and laboratory tests results. The concrete
mix recipes included in the database have been designed to be built into concrete struc-
tures of various dimensions, purposes, and functions. Some of them also contain admix-
tures of various origins and purposes, such as binding retardants, plasticizers, and work-
ability boosters. Due to the abovementioned factors, some differences are challenging to
predict between recipes of concrete mixes. Tested samples were standardized concrete
cylinders with 15 cm diameter. Noncylindrical samples were converted into cylindrical
following valid norms [43]. The samples were made from ordinary Portland cement. The
aggregate size in the dataset did not exceed 20 mm. The parameters that were adopted are
presented in Table 1.
Materials 2021, 14, 1661 8 of 32

Table 1. The parameters adopted in the dataset.

Compressive
Parameter Strength after 28 Cement Water Sand 0–2 mm Aggregate above 2 mm Water–Cement Ratio
days
Codename cs_28 cement water fine_grained_aggregate coarse_aggregate water_cement_ratio
Type Target Input Input Input Input Input
The 28 day compres-
Content of cement Content of water Content of fine-grained Content of coarse-grained
sive strength of con-
added to the mix- added to the aggregate added to the aggregate with a size more
Description crete that is consid- Water-to-cement ratio.
ture, expressed in mixture, ex- mixture, expressed in than 2 mm, added to the
ered to have most of
kg. pressed in L. kg. mixture, expressed in kg.
its strength.

The parameters presented in Table 1 are divided into two groups. The inputs refer to
the input variables, such as cement, water, fine-grained and coarse-grained aggregate, and
water–cement ratio. The target refers to the output variable, which is the concrete com-
pressive strength. In these considerations, there is a general assumption that concrete
achieves its designed compressive strength after 28 days. Such an assumption was made
because, after the concrete mix fabrication, the cement hydration process begins, which
progresses over time and increases the concrete’s strength until it reaches full strength.
According to general knowledge, this process takes around 28 days (for some types of
concrete, this time is longer). Before the indicated time, the concrete has partial strength.
The samples in which the compressive strength test was performed earlier than 28 days
were removed from the database. Table 2 presents the maximal, minimal, mean, median,
and dominant value for each variable.

Table 2. Value ranges of database input variables.

Input variable Minimum Maximum Mean Median Dominant
Cement 86.00 kg/m3 540.00 kg/m3 278.00 kg/m3 275.00 kg/m3 425.00 kg/m3
Water 121.80 kg/m3 247.00 kg/m3 182.42 kg/m3 185.00 kg/m3 192.00 kg/m3
Fine-grained aggregate (sand 0–2
372.00 kg/m3 1329.00 kg/m3 768.55 kg/m3 777.80 kg/m3 594.00 kg/m3
mm)
Coarse aggregate (aggregate
597.00 kg/m3 1490.00 kg/m3 969.08 kg/m3 967.00 kg/m3 932.00 kg/m3
above 2 mm)
Water–cement ratio 0.27 1.88 0.76 0.69 0.45

It is recommended to operate only within the limits set by range values for each input
variable. Since the DNN is trained on a specific dataset, going beyond the range values
can lead to the wrong results. The study did not directly analyze the effects of using con-
crete additives and admixtures. Their influence is accounted for indirectly by including
two observations if they affect the target variable. Many other processes influence hard-
ened concrete properties, such as the curing process, but their influence was not consid-
ered in this study. It is assumed that the quality control of the production of concrete mix
and concrete was sufficient. As a result of this research, a trained DNN was obtained,
translated into the source code, and interpreted as an equation, defining the 28 day com-
pressive strength of concrete as a function of the 17 parameters. Of these, 12 parameters
relate to the two recipes (cement, water, fine-grained and coarse-grained aggregate, wa-
ter–cement ratio, and concrete compressive strength). The remaining five parameters de-
scribe the recipe for calculating the desired target value. A hyperbolic tangent was used
for hidden layers as the activation function and a linear tangent was used for the output
layer. The practical application of the presented solution in the concrete mix design pro-
cess is presented in Figure 1.
Materials 2021, 14, 1661 9 of 32

Figure 1. Flowchart presenting the practical application of the MAFM21 (Machine-learning Adaptive Forecasting Model
2021)-based formula in the concrete mix design process.

Later in this paper, the designed algorithm is referred to as MAFM21 (Machine-learn-

ing Adaptive Forecasting Model 2021). In the comparative analysis presented below, we
used the machine learning algorithm developed in the previous research [16]. This algo-
rithm was built using a different model but was trained on the same dataset. It estimated
the compressive strength of hardened concrete on the basis of the amount and composi-
tion of main concrete mix components. Later, this algorithm is referred to as MLM19 (Ma-
chine Learning Model 2019).

3.2. Results and Discussion

The dataset was divided into three subsets to perform DNN training, namely, train-
ing, selection, and testing datasets. These three datasets have distinct functions. The train-
ing dataset is used to feed the DNN, the selection dataset helps to adjust the hyperparam-
eters of DNN, and the testing dataset serves as a tool to assess the DNN’s effectiveness.
The whole database had 741 records, whereby the training dataset had 440 records (59%),
the selection dataset had 146 records (20%), and the testing dataset had 146 records (20%).
There were nine records (1%) excluded from the analysis as univariate outliers, with a
maximum distance from the center of the dataset defined as three times the median value
for each variable. This is a less conservative approach than n used in the previous study,
where about 11% of the records were excluded. In Figure 2, scatter plots illustrating the
concrete’s compressive strength related to the individual input variables are presented.
Materials 2021, 14, 1661 10 of 32

(A) (B)

(C) (D)

(E)
Figure 2. The scatter plots of target variable vs. input variables. The full compressive strength of concrete is on the vertical
axis, expressed in MPa. The horizontal axis is the material content, expressed in kg for cement, fine-grained aggregate,
and coarse-grained aggregate and L for water: (A) cement; (B) water; (C) fine-grained aggregate (sand 0–2 mm); (D) coarse-
grained aggregate (aggregate above 2 mm); (E) water–cement ratio.

The initial DNN architecture comprised 17 input variables that refer to the 17 princi-
pal components and introduce one target output. The initial architecture contained three
hidden layers, representing the complexity of the model. A DNN includes principal com-
ponents, perceptron neurons, scaling neurons, and unscaling neurons. In the analysis, the
feature scaling was used, hence the scaling and unscaling neurons. Two recipes were
Materials 2021, 14, 1661 11 of 32

treated as observations by introducing into the equation a set of input variables represent-
ing cement, water, fine-grained and coarse-grained aggregate, water–cement ratio, and
concrete compressive strength. These two recipes generated 12 input variables. The re-
maining five input variables corresponded to the composition of the third recipe for which
it was tried to predict the concrete compressive strength. The input variables (cement,
water, fine_grained_aggregate, coarse_aggregate, water_cement_ratio) presented in Ta-
ble 1 corresponded with the input neurons. The target variable (cs_28) was associated with
the output neuron. To find a proper training rate, the Broyden–Fletcher–Goldfarb–Shanno
algorithm [44–49] was used. Next, to look for a quasi-Newton training direction, the Brent
method [50–53] was applied. For analytical purposes, a linear correlation and a correlation
matrix were assessed and calculated. Input contribution calculations were performed,
where training inputs were selectively eliminated and the output results were inspected,
whereby lower and higher input contribution values mean that the variable gave a lower
or higher contribution to the results, respectively. The presented analysis indicated that
the water–cement ratio had an immense contribution to the results. Since two observa-
tions were used with one actual recipe for predicting concrete compressive strength, every
variable gave a slightly different contribution, which followed the overall pattern for each
concrete mix ingredient. Feature correlation analysis was performed to show the relation-
ship between the searched output variable of the compressive strength and the individual
input variables, as presented in Figure 3. It can be seen that the water–cement ratio and
the cement amount significantly impact the concrete strength. The significance of the wa-
ter–cement ratio and the amount of cement for concrete compressive strength was also
confirmed in literature by various researchers [54]. In these considerations, the main focus
is on the effect of concrete mix composition on concrete compressive strength.

Figure 3. Feature correlation heatmap.

However, it should be noted that the strength of concrete is influenced by several

other factors, primarily related to the environmental conditions and technological process
of concrete production. The first important aspect is proper concrete curation after the
built-in process. Improper concrete curation can significantly deteriorate the properties of
concrete, especially its durability. Another vital issue is concreting during unfavorable
weather conditions, mainly concrete freezing in the early stage of the hydration process
Materials 2021, 14, 1661 12 of 32

and too high shrinkage due to drying during high temperatures. Considering environ-
mental factors, one must refer to adverse environmental aggression, which harms the
quality of concrete, for example, a high risk of carbonation [55] and chloride aggression in
coastal regions. Concrete additives and admixtures also play an essential role in facilitat-
ing the technological process of concrete production and are widely used. The origin,
shape, and texture of aggregate impact the workability and durability of concrete, but
their influence is more significant on fresh concrete than hardened concrete [56]. Moreo-
ver, a grading and size distribution of aggregate determines the paste requirement for
workable concrete [57]. In this analysis, several factors were not considered, such as the
technological process, environmental factors, and raw material properties, assuming that
the quality of obtained concrete samples was at an appropriate level, while all results de-
viating significantly from the mean values in the dataset were removed, treating them as
univariate outliers.
The dataset had many input variables. Principal component analysis (PCA) was used
to keep critical information while reducing input variables in a smaller feature space.
Thanks to this method, among other things, it was possible to reduce the data dimension-
ality by feature extraction. The PCA uses auxiliary variables to explain most of the varia-
bility in the dataset [58–62]. One of the critical aspects when building an optimal DNN
model is implementing the order selection algorithm. These algorithms help to minimize
the loss of acquired data and find the most suitable DNN model with an optimal number
of neurons which will match the data. In this study, an incremental order algorithm [63–
68] was used. Figure 4 shows the training and selection loss history for various subsets
from the incremental order algorithm performance within 10 iterations.

Figure 4. The loss history from incremental order algorithm execution, within 10 iterations, where
the green line is the training loss and the purple line is the selection loss. Loss is on the vertical
axis and order is on the horizontal axis.

The final architecture of the adopted DNN is presented in Figure 5. The final DNN
model had seven hidden layers, 17 inputs, and one output. The model contained principal
components (blue), perceptron neurons (red), scaling neurons (green), and unscaling neu-
rons (yellow). The final DNN architecture should be the most optimal model for a given
task.
Materials 2021, 14, 1661 13 of 32

Figure 5. Final architecture of deep neural network (DNN) that was used. The figure shows the
DNN architecture, which includes principal components (blue), perceptron neurons (red), and
scaling and unscaling layers. The scaling neurons are green, and unscaling neurons are yellow.
Abbreviations: C—cement; W—water; FA—fine-grained aggregate; CA—coarse-grained aggre-
gate; WC—water–cement ratio; CS—the full concrete compressive strength; FO—first observation;
SO—second observation.

The developed DNN had one target variable, the concrete compressive strength, with
the 17 input variables representing two observation recipes and one recipe for the targeted
value. Input variables expressed several concrete mix characteristics, such as cement, wa-
ter, fine-grained and coarse-grained aggregate content, and water–cement ratio. The DNN
was translated into a mathematical formula, presented as Equation (5), along with auxil-
iary Equations (A6)–(A49). Equation (5) refers to the 28 day strength of concrete, which
can be considered as the full strength of concrete. The equation was optimized and sim-
plified. The principal components were drawn into the equation.

𝑓 = 40.6152864 − 100.2590155 ∙ tanh 0.0630459 − 0.928083 ∙ 𝑎𝑥 − 2.03459 ∙ 𝑎𝑥 + 1.21399 ∙

(5)
𝑎𝑥 + 1.17276 ∙ 𝑎𝑥 − 0.56805 ∙ 𝑎𝑥 + 0.191161 ∙ 𝑎𝑥 [MPa].
The variables 𝐶 , 𝑊 , 𝐹𝐴 , 𝐶𝐴 , 𝐶𝑊 , 𝐶𝑆 , 𝐶 , 𝑊 , 𝐹𝐴 , 𝐶𝐴 , 𝐶𝑊 ,
𝐶𝑆 , 𝐶, 𝑊, 𝐹𝐴, 𝐶𝐴, and 𝑊𝐶 used in Equations (A40)–(A49) denote the cement (𝐶), wa-
ter (𝑊), fine-grained aggregate (𝐹𝐴), coarse aggregate (𝐶𝐴), water–cement ratio (𝑊𝐶), and
concrete strength (𝐶𝑆). The first six variables represent the composition of the first obser-
vation recipe (𝐹𝑂). The subsequent six variables represent the composition of the second
observation recipe (𝑆𝑂). The last five variables describe the actual concrete recipe for
which the compressive strength was calculated. Units are expressed in kg/m3 or l/m3 for
variables C, W, FA, and CA. Variable WC is a numerical ratio that is a dimensionless
value. There were 36 auxiliary formulas, with Equations (A6) through (A39) containing
variables with the index 𝑎𝑥, which are the auxiliary variables presented in five layers,
each with 6–10 variables. Equations (A6)–(A49) are presented in Appendix A.
The comparative analysis was prepared, which included a comparison of the
MAFM21 algorithm with the MLM19 algorithm from 2019 presented in [16], which was
trained on the same dataset but was built using a different model. Four concrete mix rec-
ipes were tested, designed according to the Bolomey and Fuller design methods, which
are standard concrete mix design approaches. The first recipe was a standard mix consist-
ing of cement, water, and fine-grained and coarse-grained aggregate with a plasticizer
(lignosulfonate) and superplasticizer (polycarboxylate ether). The second recipe was a
Materials 2021, 14, 1661 14 of 32

standard mix with plasticizer (lignosulfonate), superplasticizer (polycarboxylate ether),

and air entrainer (tensides). The third was a standard mix with superplasticizer (polycar-
boxylate ether), retarder (phosphate), and air entrainer (tensides). The fourth was a stand-
ard mix with plasticizer (lignosulfonate) and superplasticizer (naphthalene). The recipes
were prepared for 1 m3 of concrete designed as a concrete slab, with a plastic slump (which
gives a lower value than the usual water–cement ratio), direct pouring with little environ-
mental aggression, no special desired finishing, no special ambient conditions when cast-
ing, air content at 2.5%, and 20 mm maximum grain diameter. The following materials
were adopted for the design: network water, ordinary Portland cement, natural sand,
limestone gravel 4/10 mm, and limestone gravel 10/20 mm. Combinations of admixtures
commonly used in engineering practice were selected. The exact composition of the de-
signed mixtures is presented in Table 3 (Bolomey method) and Table 4 (Fuller method).
Two similar recipes designed for a given compressive strength were used as observations
to calculate the concrete compressive strength using the MAFM21 algorithm.

Table 3. Tested concrete mix recipes designed according to Bolomey formula.

Limestone Gravel Water–Ce-
Designed Concrete Com- Natural Sand Limestone Gravel 4/10
Cement (kg/m3) Water (L/m3) 10/20 ment Ratio
pressive Strength (kg/m3) (kg/m3)
(kg/m3) (-)
Recipe #1—standard mix + plasticizer (lignosulfonate) + superplasticizer (polycarboxylate ether)
10 177.09 57.56 1106.54 525.32 681.00 0.325
15 204.57 66.49 1059.83 531.08 674.29 0.325
20 232.05 75.42 1014.45 535.33 667.74 0.325
25 259.53 84.35 968.28 540.54 661.04 0.325
30 287.01 88.17 930.22 547.64 658.12 0.307
35 314.49 91.12 892.82 555.61 656.02 0.290
40 341.97 94.16 855.60 563.45 653.64 0.275
45 369.45 97.26 818.51 570.86 651.40 0.263
50 396.93 100.41 781.08 578.63 649.00 0.253
Recipe #2—standard mix + plasticizer (lignosulfonate) + superplasticizer (polycarboxylate ether) + air entrainer (tensides)
10 178.26 57.93 1105.90 527.60 677.03 0.325
15 205.58 66.81 1060.69 532.11 670.39 0.325
20 233.33 75.83 1015.00 536.35 663.75 0.325
25 261.47 84.98 968.79 540.62 656.93 0.325
30 288.63 88.67 929.92 549.20 654.18 0.307
35 315.36 91.38 894.37 556.25 652.29 0.290
40 343.21 94.50 856.65 564.08 649.89 0.275
45 371.42 97.78 817.79 572.16 647.64 0.263
50 399.12 100.97 780.12 580.04 645.11 0.253
Recipe #3—standard mix + superplasticizer (polycarboxylate ether) + retarder (phosphate) + air entrainer (tensides)
10 176.46 57.35 1107.69 526.38 677.27 0.325
15 203.84 66.25 1062.94 530.80 670.17 0.325
20 231.22 75.15 1016.61 536.10 663.75 0.325
25 258.60 84.05 971.48 540.13 657.40 0.325
30 285.99 87.86 932.98 548.07 654.22 0.307
35 313.37 90.80 896.19 555.60 652.09 0.290
40 340.75 93.82 859.54 562.61 650.09 0.275
45 368.13 96.92 821.81 571.15 647.48 0.263
50 395.51 100.05 784.51 578.91 645.11 0.253
Recipe #4—standard mix + plasticizer (lignosulfonate) + superplasticizer (naphthalene)
10 179.00 58.17 998.39 369.05 947.31 0.325
15 206.77 67.20 1058.77 532.40 675.41 0.325
20 234.55 76.23 1012.64 537.16 668.59 0.325
25 262.32 85.26 966.36 542.02 661.83 0.325
30 290.10 89.12 925.90 547.94 652.76 0.307
35 317.88 92.10 890.13 553.89 650.72 0.290
40 345.65 95.17 850.22 564.03 648.42 0.275
45 373.43 98.31 812.49 571.92 646.00 0.263
50 401.20 101.49 774.79 579.60 643.63 0.253
Materials 2021, 14, 1661 15 of 32

Table 4. Tested concrete mix recipes designed according to Fuller formula.

Limestone Gravel Water–Ce-
Designed CC of Concrete Natural Sand Limestone Gravel 4/10
Cement (kg/m3) Water (L/m3) 10/20 ment Ratio
Mix (kg/m3) (kg/m3)
(kg/m3) (-)
Recipe #1—standard mix + plasticizer (lignosulfonate) + superplasticizer (polycarboxylate ether)
10 177.09 57.56 1056.81 566.37 702.13 0.325
15 204.57 66.49 1035.14 554.76 687.74 0.325
20 232.05 75.42 1013.48 543.14 673.34 0.325
25 259.53 84.35 991.81 531.54 658.95 0.325
30 287.01 88.17 976.42 523.29 648.72 0.307
35 314.49 91.12 962.09 515.61 639.20 0.290
40 341.97 94.16 947.66 507.87 629.61 0.275
45 369.45 97.26 933.15 500.10 619.97 0.263
50 396.93 100.41 918.57 492.29 610.29 0.253
Recipe #2—standard mix + plasticizer (lignosulfonate) + superplasticizer (polycarboxylate ether) + air entrainer (tensides)
10 178.26 57.93 1055.89 565.88 696.32 0.325
15 205.58 66.81 1034.35 554.33 682.12 0.325
20 233.33 75.83 1012.47 542.61 667.69 0.325
25 261.47 84.98 990.29 530.72 653.06 0.325
30 288.63 88.67 975.18 522.62 643.10 0.307
35 315.36 91.38 961.44 515.26 634.04 0.290
40 343.21 94.50 946.76 507.39 624.36 0.275
45 371.42 97.78 931.75 499.34 614.45 0.263
50 399.12 100.97 917.04 491.47 604.76 0.253
Recipe #3—standard mix + superplasticizer (polycarboxylate ether) + retarder (phosphate) + air entrainer (tensides)
10 176.46 57.35 1057.31 566.64 697.26 0.325
15 203.84 66.25 1035.72 555.07 683.02 0.325
20 231.22 75.15 1014.13 543.50 668.79 0.325
25 258.60 84.05 992.55 531.93 654.55 0.325
30 285.99 87.86 977.20 523.71 644.44 0.307
35 313.37 90.80 962.93 516.06 635.02 0.290
40 340.75 93.82 948.55 508.35 625.54 0.275
45 368.13 96.92 934.09 500.60 616.00 0.263
50 395.51 100.05 919.57 492.82 606.43 0.253
Recipe #4—standard mix + plasticizer (lignosulfonate) + superplasticizer (naphthalene)
10 179.00 58.17 1055.30 565.56 701.13 0.325
15 206.77 67.20 1033.41 553.83 686.59 0.325
20 234.55 76.23 1011.51 542.09 672.04 0.325
25 262.32 85.26 989.61 530.36 657.49 0.325
30 290.10 89.12 974.05 522.20 642.36 0.307
35 317.88 92.10 959.57 514.25 632.80 0.290
40 345.65 95.17 944.98 506.44 623.18 0.275
45 373.43 98.31 930.32 498.58 613.51 0.263
50 401.20 101.49 915.59 490.68 603.80 0.253

Gradings and fitting curves for each designed concrete recipe are presented in Ap-
pendix B. The comparative analysis of errors is shown in Figure 6.
Materials 2021, 14, 1661 16 of 32

(A) (B)

(C) (D)

Figure 6. Comparison between designed concrete compressive strength and calculated concrete compressive strength ac-
cording to MLM19 (Machine Learning Model 2019) and MAFM21 formulas for four recipes calculated according to the
Bolomey and Fuller methods. (A) Recipe #1—standard mix + plasticizer (lignosulfonate) + superplasticizer (polycarbox-
ylate ether); (B) Recipe #2—standard mix + plasticizer (lignosulfonate) + superplasticizer (polycarboxylate ether) + air
entrainer (tensides); (C) Recipe #3—standard mix + superplasticizer (polycarboxylate ether) + retarder (phosphate) + air
entrainer (tensides); (D) Recipe #4—standard mix + plasticizer (lignosulfonate) + superplasticizer (naphthalene).

The comparative analysis of errors is presented in Figure 7.

Materials 2021, 14, 1661 17 of 32
Materials 2021, 14, 1661 18 of 32

Figure 7. Errors in the comparison between designed concrete compressive strength and calculated concrete compressive
strength according to MLM19 and MAFM21 formulas for four recipes designed according to the Bolomey and Fuller
methods. MAE—mean absolute error; MSE—mean squared error; RMSE—root-mean-squared error.

It can be seen in Figure 6 that the MAFM21 algorithm presented the best fit for mix-
tures designed according to Bolomey. Good convergence was especially visible for higher
strength levels above 30 MPa. MAFM21 was also characterized as a good fit for mixtures
designed according to Fuller in the lower ranges, below 20 MPa. However, there was some
underestimation in the range from about 25 MPa to 40 MPa, depending on the mixture. It
should also be noted that MAFM21 was more volatile than MLM19. For mixture number
four, there was even considerable mismatch for 10 MPa. MLM19 had low resilience for
high-strength recipes, whereas MAFM21 performed better in that spectrum. The statisti-
cal analysis of the errors presented in Figure 7 showed some interesting findings. Figure
7 shows that the MAFM21 algorithm was characterized by a similar level of mean absolute
error (MAE), mean squared error (MSE), and root-mean-squared error (RMSE) for Fuller
mixtures compared to MLM19 and significantly lower MAE, MSE, and RMSE values for
Bolomey mixtures. Figure 7 presents almost a twofold decrease in MAE and RMSE for the
Bolomey mix and a slight decrease in these errors for the Fuller mix for the first and second
recipes. A significant difference can be noted looking at MSE, where, for the mixture ac-
cording to the Fuller method, the error was on a similar level, whereas, for the mixture
according to the Bolomey method, the error was five times smaller in favor of the
MAFM21 algorithm. MAFM21 in the third recipe gave an even lower level of MAE, MSE,
and RMSE for the Bolomey mixture; however, in this case, MLM19 had a lower MSE for
the Fuller mix. Recipe four had a higher MSE for the MAFM21 Bolomey mix than the third
recipe, but it was still significantly lower than the Bolomey mixture for MLM19. The
MAFM21 algorithm for the fourth recipe also performed better in terms of MAE, MSE,
and RMSE for Fuller mixes. It should be noted that the presented solution is still experi-
mental, and it does not consider some key issues, such as the technological process and
durability.

4. Summary and Conclusions

One of the most critical issues in the concrete structure manufacturing technological
process is to obtain predictable properties of both fresh concrete mix and hardened con-
crete. Manufacturers of concrete mix are obliged to guarantee the appropriate properties
of concrete delivered to the construction site. However, obtaining the appropriate con-
crete properties at all stages of the production process is difficult, especially when chemi-
cally complex additives and admixtures for concrete are present. Therefore, the properties
of concrete mixes are often oversized, which can lead to very unfavorable phenomena.
For example, increasing concrete strength more than the designed value may cause
changes in the structure’s stiffness and lead to so-called concrete superstrength [23]. Pre-
dicting the properties of concrete is a complex issue, while most of the solutions used in
engineering practice are approximate methods that, especially in recent years, due to the
rapid development of materials engineering, have become outdated. Predictive analytics
is an area of knowledge dealing with predicting all kinds of phenomena, properties, and
trends. The most popular applications are economics, mathematics, and medicine. One of
the most promising branches in predictive analytics is machine learning, which has ac-
quired particular attention in recent years due to the significant development of technol-
ogy. It could be used to significantly improve the process of concrete mix design.
Materials 2021, 14, 1661 19 of 32

The primary goal of this research was to introduce machine learning to the concrete
mix design process and pave the way for new quality in this area of science. The MAFM21
algorithm can improve the ability to predict concrete technical parameters by including
two observations. This adaptive approach allows us to predict the concrete mix behavior
depending on its unique characteristics. Concrete mixes used in engineering practice have
a very diverse composition. Designing a separate model for each specific composition of
the concrete mix may turn out to be impractical and, in the long run, could be an obstacle
to its widespread implementation. The core of the presented study was to develop an op-
timal deep neural network architecture and train it using an extensive database of concrete
mix recipes with corresponding laboratory destructive tests. The developed algorithm es-
timates the concrete mix compressive strength according to its composition. The database
used for training had 741 records, whereby the training dataset had 440 records (59%), the
selection dataset had 146 records (20%), and the testing dataset had 146 records (20%).
Nine records (1%) were excluded from the analysis as univariate outliners, with a maxi-
mum distance from the center of the dataset defined as three times the median value for
each variable. The initially adopted DNN model had 17 input variables, 17 principal com-
ponents, four hidden neurons, and one target output. The final DNN architecture had 17
input variables, 17 principal components, 46 hidden neurons, clustered into seven layers,
and one target output. The applicable training rate and the step for the quasi-Newton
training direction were calculated using the Broyden–Fletcher–Goldfarb–Shanno algo-
rithm and the Brent method, respectively. The feature correlation analysis revealed that
the most significant impact on concrete strength was the water–cement ratio and cement
content. The dimensionality reduction was performed using principal component analy-
sis. An incremental order algorithm was used to find the optimal number of neurons in
DNN and minimize loss. The DNN source code was translated into a mathematical equa-
tion, which was then optimized and simplified. The final equation had 44 auxiliary equa-
tions. This method was tested on four concrete mix recipes, calculated according to con-
temporary design methods (Bolomey and Fuller method) and a comparative analysis of
the new MAFM21 algorithm with the algorithm developed in 2019 MLM19 was con-
ducted by analyzing the root-mean-squared error (RMSE), mean absolute error (MAE),
and mean squared error (MSE). The conducted tests allowed us to see how MAFA21 com-
plied with the methods used in engineering practice, and whether the adaptive approach
performed better than the previous MLM19 algorithm trained on the same dataset.
The comparative analysis brought us a number of findings. The MAFM21 algorithm
was more volatile, but had significantly lower RMSE, MAE, and MSE than MLM19 for
mixtures designed according to the Bolomey method. MAFM21 gave slightly lower
RMSE, MAE, and MSE for mixtures designed according to the Fuller method depending
on the tested mixture. MAFM21 had the best fit for Bolomey mixes, characterized by par-
ticularly good convergence for higher strength levels above 30 MPa. MAFM21 performed
well in lower ranges (below 20 MPa) for mixtures designed according to Fuller. MLM19
had low resilience for high-strength recipes, whereas MAFM21 performed better in that
spectrum. The presented approach has boundary conditions and does not fully reflect all
the relationships between the components of concrete mix and concrete properties. This
issue requires further research. However, the results presented in this paper give hope for
broader use of this method in engineering practice. Future research should extend the
method’s use in the concrete mix design process by predicting other properties of fresh
concrete mixtures and hardened concrete, such as durability, consistency, air content, and
service life estimation. It would also be vital to create a more comprehensive approach for
concrete mix optimization.

Author Contributions: Conceptualization, P.Z.; methodology, P.Z.; software, P.Z.; validation, P.Z.;
formal analysis, P.Z.; investigation, P.Z.; resources, P.Z.; data curation, P.Z.; writing—original draft
preparation, P.Z.; writing—review and editing, P.Z. and S.-B.K.; visualization, P.Z.; supervision,
Materials 2021, 14, 1661 20 of 32

P.Z. and S.-B.K.; project administration, P.Z. and M.N.; funding acquisition, P.Z. All authors read
and agreed to the published version of the manuscript.
Funding: This study was financed by grant no. 037628 supporting young researchers at the Faculty
of Civil and Environmental Engineering, Gdansk University of Technology.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: No new data were created or analyzed in this study. Data sharing is
not applicable to this article.
Acknowledgments: The author wishes to acknowledge every institution which provided data and
tools to conduct this study.
Conflicts of Interest: The authors declare no conflicts of interest.

Appendix A
Appendix A contains the auxiliary Equations (A6)–(A49) that are part of the main
Equation (5).
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.112106 + 0.345284 ∙ 𝑎𝑥 + 0.312406 ∙ 𝑎𝑥 + 0.357058 ∙ 𝑎𝑥 − 0.149771 ∙ 𝑎𝑥 + (A6)
0.405909 ∙ 𝑎𝑥 − 0.246462 ∙ 𝑎𝑥 − 0.307179 ∙ 𝑎𝑥 + 0.329967 ∙ 𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.10355 + 0.836911 ∙ 𝑎𝑥 + 0.902282 ∙ 𝑎𝑥 + 0.699127 ∙ 𝑎𝑥 + 0.00914586 ∙ 𝑎𝑥 +
0.853297 ∙ 𝑎𝑥 − 0.594561 ∙ 𝑎𝑥 − 0.475542 ∙ 𝑎𝑥 + 0.687024 ∙ 𝑎𝑥 . (A7)
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.00550484 + 0.0706381 ∙ 𝑎𝑥 + 1.37087 ∙ 𝑎𝑥 − 0.489375 ∙ 𝑎𝑥 + 0.766119 ∙ 𝑎𝑥 −
(A8)
0.76727 ∙ 𝑎𝑥 + 0.0118196 ∙ 𝑎𝑥 + 0.34148 ∙ 𝑎𝑥 + 0.0277991 ∙ 𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.0484762 + 0.207462 ∙ 𝑎𝑥 − 1.17439 ∙ 𝑎𝑥 + 0.599398 ∙ 𝑎𝑥 + 0.884247 ∙ 𝑎𝑥 +
(A9)
1.09625 ∙ 𝑎𝑥 − 0.181395 ∙ 𝑎𝑥 + 0.544369 ∙ 𝑎𝑥 − 0.0457279 ∙ 𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.0185739 + 0.114457 ∙ 𝑎𝑥 + 0.193903 ∙ 𝑎𝑥 + 0.266349 ∙ 𝑎𝑥 + 0.0349446 ∙ 𝑎𝑥 +
(A10)
0.360525 ∙ 𝑎𝑥 − 0.0275735 ∙ 𝑎𝑥 − 0.114269 ∙ 𝑎𝑥 − 0.0457279 ∙ 𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.162456 − 0.200818 ∙ 𝑎𝑥 − 0.111272 ∙ 𝑎𝑥 − 0.0271401 ∙ 𝑎𝑥 + 0.0839329 ∙ 𝑎𝑥
+ 0.0074793 ∙ 𝑎𝑥 + 0.0810916 ∙ 𝑎𝑥 + 0.0938168 ∙ 𝑎𝑥 − 0.0128759 ∙ 𝑎𝑥 . (A11)

𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.304087 − 0.93554 ∙ 𝑎𝑥 − 0.332438 ∙ 𝑎𝑥 − 0.735927 ∙ 𝑎𝑥 + 0.114776 ∙ 𝑎𝑥 −

0.210384 ∙ 𝑎𝑥 + 0.156608 ∙ 𝑎𝑥 − 0.378972 ∙ 𝑎𝑥 + 0.203964 ∙ 𝑎𝑥 − 0.149654 ∙ 𝑎𝑥 + 0.431182 ∙ (A12)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.237625 − 0.062685 ∙ 𝑎𝑥 + 0.492318 ∙ 𝑎𝑥 + 0.0000816928 ∙ 𝑎𝑥 + 0.393211 ∙ 𝑎𝑥 +
0.767934 ∙ 𝑎𝑥 + 0.246462 ∙ 𝑎𝑥 − 0.421343 ∙ 𝑎𝑥 + 0.223478 ∙ 𝑎𝑥 − 0.669725 ∙ 𝑎𝑥 − 1.02597 ∙ (A13)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.329438 + 0.0174092 ∙ 𝑎𝑥 + 0.65158 ∙ 𝑎𝑥 + 0.301201 ∙ 𝑎𝑥 + 0.675368 ∙ 𝑎𝑥 +
0.00703462 ∙ 𝑎𝑥 + 0.280539 ∙ 𝑎𝑥 + 0.502622 ∙ 𝑎𝑥 − 0.326401 ∙ 𝑎𝑥 + 0.570339 ∙ 𝑎𝑥 + 0.682099 ∙ (A14)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.133381 − 0.108074 ∙ 𝑎𝑥 − 0.411905 ∙ 𝑎𝑥 + 0.0102024 ∙ 𝑎𝑥 − 0.0754423 ∙ 𝑎𝑥 +
0.564025 ∙ 𝑎𝑥 − 0.0710046 ∙ 𝑎𝑥 − 0.121997 ∙ 𝑎𝑥 − 0.674816 ∙ 𝑎𝑥 − 0.363496 ∙ 𝑎𝑥 + 0.490389 ∙ (A15)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.0712822 + 0.369538 ∙ 𝑎𝑥 − 0.982137 ∙ 𝑎𝑥 + 0.0487879 ∙ 𝑎𝑥 − 0.00170483 ∙ 𝑎𝑥 −
0.389693 ∙ 𝑎𝑥 − 0.96266 ∙ 𝑎𝑥 + 0.704598 ∙ 𝑎𝑥 − 0.555597 ∙ 𝑎𝑥 + 0.252501 ∙ 𝑎𝑥 + 0.713304 ∙ (A16)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.165274 + 0.530625 ∙ 𝑎𝑥 + 0.000449785 ∙ 𝑎𝑥 − 0.268531 ∙ 𝑎𝑥 + 0.365822 ∙ 𝑎𝑥 −
0.239763 ∙ 𝑎𝑥 + 0.220901 ∙ 𝑎𝑥 − 0.233759 ∙ 𝑎𝑥 − 0.651051 ∙ 𝑎𝑥 − 0.329246 ∙ 𝑎𝑥 − 0.258471 ∙ (A17)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.141672 − 0.0391891 ∙ 𝑎𝑥 − 0.0704693 ∙ 𝑎𝑥 − 0.175119 ∙ 𝑎𝑥 + 0.716787 ∙ 𝑎𝑥 −
0.146807 ∙ 𝑎𝑥 − 0.389877 ∙ 𝑎𝑥 + 0.246424 ∙ 𝑎𝑥 + 0.377645 ∙ 𝑎𝑥 − 0.0800747 ∙ 𝑎𝑥 + 0.682193 ∙ (A18)
𝑎𝑥 .
Materials 2021, 14, 1661 21 of 32

𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.167999 + 0.880357 ∙ 𝑎𝑥 + 0.0174599 ∙ 𝑎𝑥 + 0.203427 ∙ 𝑎𝑥 − 0.629281 ∙ 𝑎𝑥 −

0.484972 ∙ 𝑎𝑥 − 0.166586 ∙ 𝑎𝑥 − 0.303889 ∙ 𝑎𝑥 − 0.150484 ∙ 𝑎𝑥 − 0.38319 ∙ 𝑎𝑥 + 0.18877 ∙ (A19)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.583476 + 0.257305 ∙ 𝑎𝑥 + 0.39606 ∙ 𝑎𝑥 + 0.625066 ∙ 𝑎𝑥 − 0.265241 ∙ 𝑎𝑥 −
0.59034 ∙ 𝑎𝑥 − 0.521324 ∙ 𝑎𝑥 − 0.278803 ∙ 𝑎𝑥 + 0.393518 ∙ 𝑎𝑥 − 0.715381 ∙ 𝑎𝑥 − 0.134194 ∙ (A20)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.4261 + 0.634804 ∙ 𝑎𝑥 − 0.121212 ∙ 𝑎𝑥 − 0.289991 ∙ 𝑎𝑥 + 0.609914 ∙ 𝑎𝑥 +
0.0439993 ∙ 𝑎𝑥 − 0.451075 ∙ 𝑎𝑥 + 0.334219 ∙ 𝑎𝑥 − 0.0891551 ∙ 𝑎𝑥 − 0.584922 ∙ 𝑎𝑥 + 0.306643 ∙ (A21)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.10659 − 0.615507 ∙ 𝑎𝑥 − 0.0443891 ∙ 𝑎𝑥 − 0.0848592 ∙ 𝑎𝑥 + 0.456915 ∙ 𝑎𝑥 +
0.142345 ∙ 𝑎𝑥 − 0.439859 ∙ 𝑎𝑥 + 0.12741 ∙ 𝑎𝑥 + 0.202291 ∙ 𝑎𝑥 − 0.184254 ∙ 𝑎𝑥 − 0.466343 ∙ (A22)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.150688 + 0.0475739 ∙ 𝑎𝑥 + 0.411486 ∙ 𝑎𝑥 − 0.748264 ∙ 𝑎𝑥 + 0.0760448 ∙ 𝑎𝑥 −
0.00419205 ∙ 𝑎𝑥 − 0.269192 ∙ 𝑎𝑥 − 0.139757 ∙ 𝑎𝑥 − 0.481452 ∙ 𝑎𝑥 − 0.61357 ∙ 𝑎𝑥 − 0.51427 ∙ (A23)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.257212 + 0.25639 ∙ 𝑎𝑥 + 0.277878 ∙ 𝑎𝑥 + 0.102443 ∙ 𝑎𝑥 + 0.666715 ∙ 𝑎𝑥 −
0.401726 ∙ 𝑎𝑥 + 0.281977 ∙ 𝑎𝑥 − 0.215321 ∙ 𝑎𝑥 + 0.303246 ∙ 𝑎𝑥 − 0.405421 ∙ 𝑎𝑥 + (A24)
0.000360402 ∙ 𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.212833 + 0.403199 ∙ 𝑎𝑥 + 0.341386 ∙ 𝑎𝑥 − 0.293033 ∙ 𝑎𝑥 + 0.149875 ∙ 𝑎𝑥 −
0.0625897 ∙ 𝑎𝑥 − 0.104747 ∙ 𝑎𝑥 + 0.747322 ∙ 𝑎𝑥 − 0.0410873 ∙ 𝑎𝑥 − 0.381452 ∙ 𝑎𝑥 + 0.557865 ∙ (A25)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.13612 + 0.070754 ∙ 𝑎𝑥 − 0.141931 ∙ 𝑎𝑥 + 0.317007 ∙ 𝑎𝑥 + 0.473061 ∙ 𝑎𝑥 +
0.971685 ∙ 𝑎𝑥 + 0.674186 ∙ 𝑎𝑥 − 0.117296 ∙ 𝑎𝑥 + 0.165819 ∙ 𝑎𝑥 + 0.0580616 ∙ 𝑎𝑥 − 0.549804 ∙ (A26)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.241159 − 0.150599 ∙ 𝑎𝑥 − 0.31649 ∙ 𝑎𝑥 − 1.04636 ∙ 𝑎𝑥 + 0.242558 ∙ 𝑎𝑥 +
0.241968 ∙ 𝑎𝑥 − 0.110343 ∙ 𝑎𝑥 + 0.158529 ∙ 𝑎𝑥 − 0.0196748 ∙ 𝑎𝑥 + 0.296961 ∙ 𝑎𝑥 + 0.184 ∙ (A27)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.110104 − 0.820008 ∙ 𝑎𝑥 − 0.540616 ∙ 𝑎𝑥 − 0.263387 ∙ 𝑎𝑥 + 0.00700437 ∙ 𝑎𝑥 −
0.592159 ∙ 𝑎𝑥 + 0.27605 ∙ 𝑎𝑥 − 0.0406511 ∙ 𝑎𝑥 − 0.484756 ∙ 𝑎𝑥 − 0.426393 ∙ 𝑎𝑥 − 0.31372 ∙ (A28)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.127382 − 0.615599 ∙ 𝑎𝑥 − 0.281532 ∙ 𝑎𝑥 + 0.488731 ∙ 𝑎𝑥 − 0.730324 ∙ 𝑎𝑥 +
0.859829 ∙ 𝑎𝑥 + 0.45729 ∙ 𝑎𝑥 − 0.441791 ∙ 𝑎𝑥 − 0.616392 ∙ 𝑎𝑥 − 0.371053 ∙ 𝑎𝑥 − 0.603444 ∙ (A29)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.03503 + 1.17792 ∙ 𝑎𝑥 + 0.536391 ∙ 𝑎𝑥 − 0.694888 ∙ 𝑎𝑥 + 0.488167 ∙ 𝑎𝑥 +
0.724072 ∙ 𝑎𝑥 − 0.0434757 ∙ 𝑎𝑥 + 0.190797 ∙ 𝑎𝑥 + 0.316145 ∙ 𝑎𝑥 + 0.33833 ∙ 𝑎𝑥 + 0.224688 ∙ (A30)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.219872 − 0.139292 ∙ 𝑎𝑥 + 0.498359 ∙ 𝑎𝑥 + 0.184706 ∙ 𝑎𝑥 + 0.506286 ∙ 𝑎𝑥 −
0.179573 ∙ 𝑎𝑥 + 0.177916 ∙ 𝑎𝑥 − 0.105241 ∙ 𝑎𝑥 − 0.461557 ∙ 𝑎𝑥 + 0.365369 ∙ 𝑎𝑥 + 0.341493 ∙ (A31)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.441113 + 0.585713 ∙ 𝑎𝑥 + 0.710594 ∙ 𝑎𝑥 + 0.000187878 ∙ 𝑎𝑥 + 0.694946 ∙ 𝑎𝑥 −
0.0253969 ∙ 𝑎𝑥 + 0.0666956 ∙ 𝑎𝑥 + 0.78373 ∙ 𝑎𝑥 − 0.150309 ∙ 𝑎𝑥 + 0.0361135 ∙ 𝑎𝑥 + 0.529901 ∙ (A32)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.277789 + 0.00996534 ∙ 𝑎𝑥 + 0.311853 ∙ 𝑎𝑥 − 0.515361 ∙ 𝑎𝑥 − 1.21524 ∙ 𝑎𝑥 −
0.483273 ∙ 𝑎𝑥 + 0.0458816 ∙ 𝑎𝑥 + 0.680251 ∙ 𝑎𝑥 − 0.47257 ∙ 𝑎𝑥 − 0.377953 ∙ 𝑎𝑥 − 0.0153472 ∙ (A33)
𝑎𝑥 .
Materials 2021, 14, 1661 22 of 32

𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.0365425 + 0.000522626 ∙ 𝑎𝑥 + 0.186409 ∙ 𝑎𝑥 + 0.625137 ∙ 𝑎𝑥 − 1.29349 ∙ 𝑎𝑥 +

0.441413 ∙ 𝑎𝑥 − 0.654638 ∙ 𝑎𝑥 + 0.203844 ∙ 𝑎𝑥 + 0.186017 ∙ 𝑎𝑥 + 0.162006 ∙ 𝑎𝑥 + 0.335084 ∙ (A34)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.117201 + 0.131572 ∙ 𝑎𝑥 − 0.359282 ∙ 𝑎𝑥 + 0.389462 ∙ 𝑎𝑥 + 0.0835228 ∙ 𝑎𝑥 +
0.513271 ∙ 𝑎𝑥 + 0.0913045 ∙ 𝑎𝑥 + 1.07162 ∙ 𝑎𝑥 − 0.0790713 ∙ 𝑎𝑥 − 0.423777 ∙ 𝑎𝑥 − 0.258301 ∙ (A35)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.187318 − 0.593468 ∙ 𝑎𝑥 − 0.457257 ∙ 𝑎𝑥 − 0.218044 ∙ 𝑎𝑥 + 0.170376 ∙ 𝑎𝑥 +
0.230136 ∙ 𝑎𝑥 − 0.384798 ∙ 𝑎𝑥 + 0.0577948 ∙ 𝑎𝑥 + 0.11429 ∙ 𝑎𝑥 + 0.533959 ∙ 𝑎𝑥 + 0.244539 ∙ (A36)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −0.0126921 − 0.0590893 ∙ 𝑎𝑥 − 0.0584762 ∙ 𝑎𝑥 + 0.428384 ∙ 𝑎𝑥 − 0.162718 ∙ 𝑎𝑥 −
(A37)
0.28943 ∙ 𝑎𝑥 − 0.165741 ∙ 𝑎𝑥 + 0.223617 ∙ 𝑎𝑥 − 0.6501 ∙ 𝑎𝑥 + 0.546167 ∙ 𝑎𝑥 − 0.57052 ∙ 𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.04489 − 0.605727 ∙ 𝑎𝑥 − 0.00105592 ∙ 𝑎𝑥 − 0.507067 ∙ 𝑎𝑥 − 0.354351 ∙ 𝑎𝑥 +
0.727824 ∙ 𝑎𝑥 + 0.0357734 ∙ 𝑎𝑥 + 0.208872 ∙ 𝑎𝑥 − 0.277591 ∙ 𝑎𝑥 + 0.0822228 ∙ 𝑎𝑥 − 0.251631 ∙ (A38)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 0.0274462 − 0.464155 ∙ 𝑎𝑥 + 0.335326 ∙ 𝑎𝑥 − 0.189354 ∙ 𝑎𝑥 + 0.00273104 ∙ 𝑎𝑥 +
0.138291 ∙ 𝑎𝑥 + 0.699764 ∙ 𝑎𝑥 + 0.378692 ∙ 𝑎𝑥 + 0.363206 ∙ 𝑎𝑥 + 0.698019 ∙ 𝑎𝑥 − 0.267254 ∙ (A39)
𝑎𝑥 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 4.767351553463 + 0.00010018415828968 ∙ 𝐶 + 0.0041259755901707 ∙ 𝑊 +
0.000209184787522328 ∙ 𝐹𝐴 + 0.00147687126084511 ∙ 𝐶𝐴 − 0.170582379127354 ∙ 𝑊𝐶 −
0.00739795485330284 ∙ 𝐶𝑆 + 0.0014713281157207 ∙ 𝐶 + 0.00573830926470374 ∙ 𝑊 −
(A40)
0.00348658190095467 ∙ 𝐹𝐴 − 0.00375199793921971 ∙ 𝐶𝐴 − 0.271415999837499 ∙ 𝑊𝐶 +
0.00269179297167401 ∙ 𝐶𝑆 + 0.000645907802623046 ∙ 𝐶 − 0.00511651789903316 ∙ 𝑊 −
0.00119068504591733 ∙ 𝐹𝐴 + 0.00121507017924426 ∙ 𝐶𝐴 − 0.194768583102371 ∙ 𝑊𝐶 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −2.90937028957849 + 0.000513987509738448 ∙ 𝐶 + 0.0104205287263435 ∙ 𝑊 −
0.0000300236136823883 ∙ 𝐹𝐴 + 0.00193442295465733 ∙ 𝐶𝐴 + 0.0304831451994348 ∙ 𝑊𝐶 −
0.00348102557161981 ∙ 𝐶𝑆 − 0.00117363708739863 ∙ 𝐶 + 0.00426298901301358 ∙ 𝑊 −
(A41)
0.00060247532418286 ∙ 𝐹𝐴 + 0.000619551260777826 ∙ 𝐶𝐴 + 0.202375734386783 ∙ 𝑊𝐶 −
0.000233978962466558 ∙ 𝐶𝑆 − 0.00038450344939621 ∙ 𝐶 + 0.00544033538809217 ∙ 𝑊 −
0.000295834802908707 ∙ 𝐹𝐴 − 0.001576885731436 ∙ 𝐶𝐴 − 0.437227409538789 ∙ 𝑊𝐶 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −1.28397136623645 − 0.00265425528655059 ∙ 𝐶 + 0.00134392831181661 ∙ 𝑊 +
0.00187950192048241 ∙ 𝐹𝐴 − 0.000256323950062182 ∙ 𝐶𝐴 + 0.012594583425795 ∙ 𝑊𝐶 +
0.0137268911005708 ∙ 𝐶𝑆 − 0.00153196251341365 ∙ 𝐶 − 0.0065857765027207 ∙ 𝑊 +
(A42)
0.00208609505432554 ∙ 𝐹𝐴 − 0.00000592967658050422 ∙ 𝐶𝐴 − 0.11595281342328 ∙ 𝑊𝐶 −
0.0104040315572809 ∙ 𝐶𝑆 + 0.00196054736213827 ∙ 𝐶 + 0.0102110804430631 ∙ 𝑊 +
0.000620781117815345 ∙ 𝐹𝐴 − 0.00187136972051576 ∙ 𝐶𝐴 − 0.255163361753211 ∙ 𝑊𝐶 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 4.21395574600285 − 0.00105127459631726 ∙ 𝐶 − 0.0112148941682978 ∙ 𝑊 +
0.00163727698209709 ∙ 𝐹𝐴 + 0.000638406176270943 ∙ 𝐶𝐴 + 0.245800411366534 ∙ 𝑊𝐶 +
0.0074057996976356 ∙ 𝐶𝑆 − 0.00233892425018069 ∙ 𝐶 + 0.00377676692330639 ∙ 𝑊 −
(A43)
0.000934383939230747 ∙ 𝐹𝐴 − 0.00383296357061587 ∙ 𝐶𝐴 + 0.599324030373907 ∙ 𝑊𝐶 −
0.00246137349085538 ∙ 𝐶𝑆 − 0.000522500768390411 ∙ 𝐶 − 0.00430098689691885 ∙ 𝑊 −
0.00200997561736293 ∙ 𝐹𝐴 + 0.00176580319743452 ∙ 𝐶𝐴 − 0.242934179812162 ∙ 𝑊𝐶 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −1.6446570342455 + 0.000533587828047032 ∙ 𝐶 + 0.000952303651589457 ∙ 𝑊 +
0.000871116154702258 ∙ 𝐹𝐴 − 0.00000492904456363928 ∙ 𝐶𝐴 + 0.0360531074572857 ∙ 𝑊𝐶 −
0.00992286147701841 ∙ 𝐶𝑆 + 0.001469808247159 ∙ 𝐶 + 0.00642860151461661 ∙ 𝑊 −
(A44)
0.00271657540072071 ∙ 𝐹𝐴 + 0.000246865509647522 ∙ 𝐶𝐴 + 0.0279125858257541 ∙ 𝑊𝐶 +
0.0133855714042725 ∙ 𝐶𝑆 − 0.000541184824066393 ∙ 𝐶 − 0.00824577692013099 ∙ 𝑊 −
0.00000397881537241383 ∙ 𝐹𝐴 + 0.00235002971670078 ∙ 𝐶𝐴 − 0.180135513126205 ∙ 𝑊𝐶 .
Materials 2021, 14, 1661 23 of 32

𝑎𝑥 = 𝑡𝑎𝑛ℎ −3.84884812355591 + 0.00115407871985479 ∙ 𝐶 − 0.00375105915008307 ∙ 𝑊 +

0.000390252688951681 ∙ 𝐹𝐴 + 0.00221305190140043 ∙ 𝐶𝐴 + 0.327755674417453 ∙ 𝑊𝐶 +
0.00166910211893054 ∙ 𝐶𝑆 − 0.000117013083312986 ∙ 𝐶 − 0.010706630159067 ∙ 𝑊 +
(A45)
0.000537751740713538 ∙ 𝐹𝐴 − 0.000386509173984826 ∙ 𝐶𝐴 + 0.038443112623923 ∙ 𝑊𝐶 +
0.00789947089570246 ∙ 𝐶𝑆 − 0.00163089480403489 ∙ 𝐶 + 0.00485445960094249 ∙ 𝑊 +
0.00174073824194078 ∙ 𝐹𝐴 + 0.00107642389772748 ∙ 𝐶𝐴 − 0.0903836711929193 ∙ 𝑊𝐶 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −1.87654029183636 + 0.00140014344181078 ∙ 𝐶 − 0.00531433362617444 ∙ 𝑊 −
0.00413045250962745 ∙ 𝐹𝐴 + 0.00228016416194765 ∙ 𝐶𝐴 − 0.312440638205596 ∙ 𝑊𝐶 +
0.00244581570673698 ∙ 𝐶𝑆 − 0.00140933248958429 ∙ 𝐶 + 0.00161013791429313 ∙ 𝑊 +
(A46)
0.00171544141339727 ∙ 𝐹𝐴 − 0.000329656644298609 ∙ 𝐶𝐴 − 0.448421258516497 ∙ 𝑊𝐶 −
0.00723447006861429 ∙ 𝐶𝑆 + 0.000353775031899132 ∙ 𝐶 − 0.0017893761303401 ∙ 𝑊 +
0.0018920172469581 ∙ 𝐹𝐴 + 0.00306888686044287 ∙ 𝐶𝐴 − 0.0131009807144161 ∙ 𝑊𝐶 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 7.30775875969612 + 0.0025578242040305 ∙ 𝐶 − 0.00303262947215815 ∙ 𝑊 −
0.00165574273119679 ∙ 𝐹𝐴 − 0.00306199296034884 ∙ 𝐶𝐴 − 0.156923718980124 ∙ 𝑊𝐶 +
0.00137102269966526 ∙ 𝐶𝑆 − 0.000419742348687123 ∙ 𝐶 + 0.0061626385341524 ∙ 𝑊 −
(A47)
0.00237717598480315 ∙ 𝐹𝐴 − 0.000972453336543304 ∙ 𝐶𝐴 − 0.190327552460012 ∙ 𝑊𝐶 −
0.00783522799632837 ∙ 𝐶𝑆 − 0.000892188050113014 ∙ 𝐶 − 0.0015154846950607 ∙ 𝑊 +
0.000314135115650862 ∙ 𝐹𝐴 + 0.000748914790764869 ∙ 𝐶𝐴 − 0.184269602615267 ∙ 𝑊𝐶 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ 2.06633738444408 − 0.00195515963988164 ∙ 𝐶 + 0.00138958650164713 ∙ 𝑊 +
0.00262801203222595 ∙ 𝐹𝐴 − 0.000536163722811296 ∙ 𝐶𝐴 − 0.188122517295472 ∙ 𝑊𝐶 +
0.00407903424912999 ∙ 𝐶𝑆 − 0.000183834803792603 ∙ 𝐶 − 0.00183731758403244 ∙ 𝑊 −
(A48)
0.000774757922991741 ∙ 𝐹𝐴 + 0.000574911771861783 ∙ 𝐶𝐴 − 0.100967264097832 ∙ 𝑊𝐶 −
0.0083462680924114 ∙ 𝐶𝑆 + 0.000798708705572374 ∙ 𝐶 − 0.00233339826228642 ∙ 𝑊 −
0.00163577879701815 ∙ 𝐹𝐴 − 0.00020955799115713 ∙ 𝐶𝐴 − 0.28849090239718 ∙ 𝑊𝐶 .
𝑎𝑥 = 𝑡𝑎𝑛ℎ −5.09651077352556 + 0.000206496906491233 ∙ 𝐶 + 0.00444536475350176 ∙ 𝑊 +
0.00109290014495785 ∙ 𝐹𝐴 + 0.00228266395774151 ∙ 𝐶𝐴 + 0.191531435179031 ∙ 𝑊𝐶 +
0.000987346948074925 ∙ 𝐶𝑆 + 0.000289024996218767 ∙ 𝐶 + 0.00254484992089329 ∙ 𝑊 +
(A49)
0.00133254035553042 ∙ 𝐹𝐴 + 0.0018234072550613 ∙ 𝐶𝐴 + 0.332154625352893 ∙ 𝑊𝐶 −
0.00258354089455455 ∙ 𝐶𝑆 + 0.000785116534796457 ∙ 𝐶 − 0.00462902690413978 ∙ 𝑊 −
0.00163107840072543 ∙ 𝐹𝐴 − 0.000691117800517391 ∙ 𝐶𝐴 − 0.134078811558199 ∙ 𝑊𝐶 .
Materials 2021, 14, 1661 24 of 32

Appendix B
Appendix B contains the gradings and fitting curves for the designed recipes. Recipe
#1 designed according to the Bolomey method is presented in Figure A1, and that de-
signed according to the Fuller method is presented in Figure A2. Recipe #2 designed ac-
cording to the Bolomey method is presented in Figure A3, and that designed according to
the Fuller method is presented in Figure A4. Recipe #3 designed according to the Bolomey
method is presented in Figure A5, and that designed according to the Fuller method is
presented in Figure A6. Recipe #4 designed according to the Bolomey method is presented
in Figure A7, and that designed according to the Fuller method is presented in Figure A8.

(A) (B) (C)

(D) (E) (F)

(G) (H) (I)

LEGEND:
—Natural sand
—Limestone gravel 4/10
—Limestone gravel 10/20
—Reference
—Result (combined)
Figure A1. Gradings and fitting curves for Recipe #1—standard mix with plasticizer (lignosulfonate) and superplasticizer
(polycarboxylate ether) designed according to the Bolomey Method: (A) 10 MPa; (B) 15 MPa; (C) 20 MPa; (D) 25 MPa; (E)
30 MPa; (F) 35 MPa; (G) 40 MPa; (H) 45 MPa; (I) 50 MPa. Legend in the left bottom corner.
Materials 2021, 14, 1661 25 of 32

(A) (B) (C)

(D) (E) (F)

(G) (H) (I)

LEGEND:
—Natural sand
—Limestone gravel 4/10
—Limestone gravel 10/20
—Reference
—Result (combined)
Figure A2. Gradings and fitting curves for Recipe #1—standard mix with plasticizer (lignosulfonate) and superplasticizer
(polycarboxylate ether) designed according to the Fuller Method: (A) 10 MPa; (B) 15 MPa; (C) 20 MPa; (D) 25 MPa; (E) 30
MPa; (F) 35 MPa; (G) 40 MPa; (H) 45 MPa; (I) 50 MPa. Legend in the left bottom corner.

(A) (B) (C)

Materials 2021, 14, 1661 26 of 32

(D) (E) (F)

(G) (H) (I)

LEGEND:
—Natural sand
—Limestone gravel 4/10
—Limestone gravel 10/20
—Reference
—Result (combined)

Figure A3. Gradings and fitting curves for Recipe #2—standard mix with plasticizer (lignosulfonate), superplasticizer
(polycarboxylate ether) and air entrainer (tensides) designed according to the Bolomey Method: (A) 10 MPa; (B) 15 MPa;
(C) 20 MPa; (D) 25 MPa; (E) 30 MPa; (F) 35 MPa; (G) 40 MPa; (H) 45 MPa; (I) 50 MPa. Legend in the left bottom corner.

(A) (B) (C)

(D) (E) (F)

Materials 2021, 14, 1661 27 of 32

(G) (H) (I)

LEGEND:
—Natural sand
—Limestone gravel 4/10
—Limestone gravel 10/20
—Reference
—Result (combined)

Figure A4. Gradings and fitting curves for Recipe #2—standard mix with plasticizer (lignosulfonate), superplasticizer
(polycarboxylate ether) and air entrainer (tensides) designed according to the Fuller Method: (A) 10 MPa; (B) 15 MPa; (C)
20 MPa; (D) 25 MPa; (E) 30 MPa; (F) 35 MPa; (G) 40 MPa; (H) 45 MPa; (I) 50 MPa. Legend in the left bottom corner.

(A) (B) (C)

(D) (E) (F)

(G) (H) (I)

Materials 2021, 14, 1661 28 of 32

LEGEND:
—Natural sand
—Limestone gravel 4/10
—Limestone gravel 10/20
—Reference
—Result (combined)

Figure A5. Gradings and fitting curves for Recipe #3—standard mix with superplasticizer (polycarboxylate ether), retarder
(phosphate) and air entrainer (tensides) designed according to the Bolomey Method: (A) 10 MPa; (B) 15 MPa; (C) 20 MPa;
(D) 25 MPa; (E) 30 MPa; (F) 35 MPa; (G) 40 MPa; (H) 45 MPa; (I) 50 MPa. Legend in the left bottom corner.

(A) (B) (C)

(D) (E) (F)

(G) (H) (I)

LEGEND:
—Natural sand
—Limestone gravel 4/10
—Limestone gravel 10/20
—Reference
—Result (combined)

Figure A6. Gradings and fitting curves for Recipe #3—standard mix with superplasticizer (polycarboxylate ether), retarder
(phosphate) and air entrainer (tensides) designed according to the Fuller Method: (A) 10 MPa; (B) 15 MPa; (C) 20 MPa;
(D) 25 MPa; (E) 30 MPa; (F) 35 MPa; (G) 40 MPa; (H) 45 MPa; (I) 50 MPa. Legend in the left bottom corner.
Materials 2021, 14, 1661 29 of 32

(A) (B) (C)

(D) (E) (F)

(G) (H) (I)

LEGEND:
—Natural sand
—Limestone gravel 4/10
—Limestone gravel 10/20
—Reference
—Result (combined)

Figure A7. Gradings and fitting curves for Recipe #4—standard mix with plasticizer (lignosulfonate) and superplasticizer
(naphthalene) designed according to the Bolomey Method: (A) 10 MPa; (B) 15 MPa; (C) 20 MPa; (D) 25 MPa; (E) 30 MPa;
(F) 35 MPa; (G) 40 MPa; (H) 45 MPa; (I) 50 MPa. Legend in the left bottom corner.

(A) (B) (C)

Materials 2021, 14, 1661 30 of 32

(D) (E) (F)

(G) (H) (I)

LEGEND:
—Natural sand
—Limestone gravel 4/10
—Limestone gravel 10/20
—Reference
—Result (combined)

Figure A8. Gradings and fitting curves for Recipe #4—standard mix with plasticizer (lignosulfonate) and superplasticizer
(naphthalene) designed according to the Fuller Method: (A) 10 MPa; (B) 15 MPa; (C) 20 MPa; (D) 25 MPa; (E) 30 MPa; (F)
35 MPa; (G) 40 MPa; (H) 45 MPa; (I) 50 MPa. Legend in the left bottom corner.

References
1. Dimov, D.; Amit, I.; Gorrie, O.; Barnes, M.D.; Townsend, N.J.; Neves, A.I.S.; Withers, F.; Russo, S.; Craciun, M.F. Ultrahigh
Performance Nanoengineered Graphene-Concrete Composites for Multifunctional Applications. Adv. Funct. Mater. 2018, 28, 28,
doi:10.1002/adfm.201705183.
2. Marchon, D.; Cement and Concrete Research. Mechanisms of Cement Hydration; Elsevier: Amsterdam, The Netherlands, 2016.
3. Scrivener, K.; Snellings, R.; Lothenbach, B. A Practical Guide to Microstructural Analysis of Cementitious Materials; CRC Press: Boca
Raton, FL, USA, 2018.
4. Kurdowski, W. Cement and Concrete Chemistry; Springer: Heidelberg, Germany, 2014.
5. Young, J.F.; Mindess, S.; Darwin, D. Concrete; Prentice Hall: Upper Saddle River, NJ, USA, 2002; ISBN 0130646326.
6. Hover, K.C. The influence of water on the performance of concrete. Constr. Build. Mater. 2011, 25, 3003–3013,
doi:10.1016/[Link].2011.01.010.
7. Jensen, O.; Cement and Concrete Research. Water-Entrained Cement-Based Materials: I. Principles and Theoretical Background; Else-
vier: Amsterdam, The Netherlands, 2001.
8. Jensen, O.; Cement and Concrete Research. Water-Entrained Cement-Based Materials: II. Experimental Observations; Elsevier: Am-
sterdam, The Netherlands, 2002.
9. Jiménez, C.; Barra, M.; Valls, S.; Aponte, D.; Vázquez, E. Durabilidad de Hormigones Con Áridos Reciclados Diseñados Con El
Método de Volumen de Mortero Equivalente (EMV): Validación Bajo El Contexto Español y Adaptación a La Metodología de
Bolomey; Durability of Recycled Aggregate Concrete Designed with the Equivalent Mortar Volume (EMV) Method: Validation
under the Spanish Context and Its Adaptation to Bolomey Methodology. Mater. Constr. 2014, 64, 6, doi:10.3989/mc.2014.00913.
10. Abdelgader, H.S. How to design concrete produced by a two-stage concreting method. Cem. Concr. Res. 1999, 29, 331–337,
doi:10.1016/s0008-8846(98)00215-4.
11. Abdelgader, H.S.; Suleiman, R.E.; El-Baden, A.S.; Fahema, A.H.; Angelescu, N. Concrete mix proportioning using three equa-
tions method (Laboratory Study). In Proceedings of the UKIERI Concrete Congress Innovations in Concrete Construction, Jal-
andhar, Punjab, India, 5–8 March 2013.
Materials 2021, 14, 1661 31 of 32

12. Iqbal, M.F.; Liu, Q.-F.; Azim, I.; Zhu, X.; Yang, J.; Javed, M.F.; Rauf, M. Prediction of mechanical properties of green concrete
incorporating waste foundry sand based on gene expression programming. J. Hazard. Mater. 2020, 384, 121322,
doi:10.1016/[Link].2019.121322.
13. Iqbal, M.F.; Javed, M.F.; Rauf, M.; Azim, I.; Ashraf, M.; Yang, J.; Liu, Q.-F. Sustainable utilization of foundry waste: Forecasting
mechanical properties of foundry sand based concrete using multi-expression programming. Sci. Total. Environ. 2021, 146524,
146524, doi:10.1016/[Link].2021.146524.
14. Renigier-Biłozor, M.; Chmielewska, A.; Walacik, M.; Janowski, A.; Lepkova, N. Genetic algorithm application for real estate
market analysis in the uncertainty conditions. Neth. J. Hous. Environ. Res. 2021, 1–42, doi:10.1007/s10901-020-09815-8.
15. Liu, Q.-F.; Iqbal, M.F.; Yang, J.; Lu, X.-Y.; Zhang, P.; Rauf, M. Prediction of chloride diffusivity in concrete using artificial neural
network: Modelling and performance evaluation. Constr. Build. Mater. 2021, 268, 121082, doi:10.1016/[Link].2020.121082.
16. Ziolkowski, P.; Niedostatkiewicz, M. Machine Learning Techniques in Concrete Mix Design. Materials 2019, 12, 1256,
doi:10.3390/ma12081256.
17. Kurpinska, M.; Kułak, L. Predicting Performance of Lightweight Concrete with Granulated Expanded Glass and Ash Aggregate
by Means of Using Artificial Neural Networks. Materials 2019, 12, 2002, doi:10.3390/ma12122002.
18. Czarnecki, S.; Sadowski, Ł.; Hoła, J. Artificial neural networks for non-destructive identification of the interlayer bonding be-
tween repair overlay and concrete substrate. Adv. Eng. Softw. 2020, 141, 102769, doi:10.1016/[Link].2020.102769.
19. Aitcin, P. The durability characteristics of high performance concrete: A review. Cem. Concr. Compos. 2003, 25, 409–420,
doi:10.1016/s0958-9465(02)00081-1.
20. Al-Obaidi, S.; Bamonte, P.; Luchini, M.; Mazzantini, I.; Ferrara, L. Durability-Based Design of Structures Made with Ultra-High-
Performance/Ultra-High-Durability Concrete in Extremely Aggressive Scenarios: Application to a Geothermal Water Basin
Case Study. Infrastructures 2020, 5, 102, doi:10.3390/infrastructures5110102.
21. Cheng, Y.; Zhang, Y.; Tan, G.; Jiao, Y. Effect of Crack on Durability of RC Material under the Chloride Aggressive Environment.
Sustainability 2018, 10, 430, doi:10.3390/su10020430.
22. Kępniak, M.; Woyciechowski, P.; Łukowski, P.; Kuziak, J.; Kobyłka, R. The Durability of Concrete Modified by Waste Limestone
Powder in the Chemically Aggressive Environment. Materials 2019, 12, 1693, doi:10.3390/ma12101693.
23. Ambroziak, A.; Ziolkowski, P. Concrete Compressive Strength Under Changing Environmental Conditions During Placement
Processes. Materials 2020, 13, 4577, doi:10.3390/ma13204577.
24. Abdelgader, H.S.; Saud, A.F.; Othman, A.M.; Fahema, A.H.; El-Baden, A.S. Concrete Mix Design Using the Double-Coating
Method. Plant Precast. Technol. 2014, 80, 66–74.
25. Rajamane, N.P.; Ambily, P.S.; Nataraja, M.C.; Das, L. Discussion: Modified Bolomey equation for strength of lightweight con-
cretes containing fly ash aggregates. Mag. Concr. Res. 2014, 66, 1286–1288, doi:10.1680/macr.14.00154.
26. Zhang, X.-B.; Deng, S.-C.; Deng, X.-H.; Qin, Y.-H. Experimental research on regression coefficients in recycled concrete Bolomey
formula. J. Central South Univ. Technol. 2007, 14, 314–317, doi:10.1007/s11771-007-0272-0.
27. Gołaszewski, J.; Kostrzanowska-Siedlarz, A.; Cygan, G.; Drewniok, M. Mortar as a model to predict self-compacting concrete
rheological properties as a function of time and temperature. Constr. Build. Mater. 2016, 124, 1100–1108,
doi:10.1016/[Link].2016.08.136.
28. Abdelgader, H.S.; El-Baden, A.S.; Shilstone, J.M. Bolomeya model for normal concrete mix design. J. Concr. Plant Int. 2012, 2,
68–74.
29. Kaplan, G.; Yaprak, H.; Memiş, S.; Alnkaa, A. Artificial Neural Network Estimation of the Effect of Varying Curing Conditions
and Cement Type on Hardened Concrete Properties. Buildings 2019, 9, 10, doi:10.3390/buildings9010010.
30. Tang, C.-W.; Cheng, C.-K.; Tsai, C.-Y. Mix Design and Mechanical Properties of High-Performance Pervious Concrete. Materials
2019, 12, 2577, doi:10.3390/ma12162577.
31. Yeh, I.-C. Modeling of strength of high-performance concrete using artificial neural networks. Cem. Concr. Res. 1998, 28, 1797–
1808, doi:10.1016/s0008-8846(98)00165-3.
32. Lee, S.-C. Prediction of concrete strength using artificial neural networks. Eng. Struct. 2003, 25, 849–857, doi:10.1016/s0141-
0296(03)00004-x.
33. Hoła, J.; Schabowicz, K. New technique of nondestructive assessment of concrete strength using artificial intelligence. NDT E
Int. 2005, 38, 251–259, doi:10.1016/[Link].2004.08.002.
34. Hoła, J.; Schabowicz, K.; Hoùa, J. Application of Artificial Neural Networks to Determine Concrete Compressive Strength Based
on Non-Destructive Tests. J. Civ. Eng. Manag. 2005, 6, 23–32, doi:10.1080/13923730.2005.9636329.
35. Gupta, R.; Kewalramani, M.A.; Goel, A. Prediction of Concrete Strength Using Neural-Expert System. J. Mater. Civ. Eng. 2006,
18, 462–466, doi:10.1061/(asce)0899-1561(2006)18:3(462).
36. Bui, D.-K.; Nguyen, T.; Chou, J.-S.; Nguyen-Xuan, H.; Ngo, T.D. A modified firefly algorithm-artificial neural network expert
system for predicting compressive and tensile strength of high-performance concrete. Constr. Build. Mater. 2018, 180, 320–333,
doi:10.1016/[Link].2018.05.201.
37. Deng, F.; He, Y.; Zhou, S.; Yu, Y.; Cheng, H.; Wu, X. Compressive strength prediction of recycled concrete based on deep learn-
ing. Constr. Build. Mater. 2018, 175, 562–569, doi:10.1016/[Link].2018.04.169.
38. Naderpour, H.; Rafiean, A.H.; Fakharian, P. Compressive strength prediction of environmentally friendly concrete using artifi-
cial neural networks. J. Build. Eng. 2018, 16, 213–219, doi:10.1016/[Link].2018.01.007.
39. McCormac, J.; Brown, R. Design of Reinforced Concrete; John Wiley & Sons, Inc.: Hoboken, NJ, USA, 2015.
Materials 2021, 14, 1661 32 of 32

40. Adil, M.; Ullah, R.; Noor, S.; Gohar, N. Effect of number of neurons and layers in an artificial neural network for generalized
concrete mix design. Neural Comput. Appl. 2020, 1–9, doi:10.1007/s00521-020-05305-8.
41. Nunez, I.; Marani, A.; Nehdi, M.L. Mixture Optimization of Recycled Aggregate Concrete Using Hybrid Machine Learning
Model. Materials 2020, 13, 4331, doi:10.3390/ma13194331.
42. Marani, A.; Jamali, A.; Nehdi, M.L. Predicting Ultra-High-Performance Concrete Compressive Strength Using Tabular Gener-
ative Adversarial Networks. Materials 2020, 13, 4757, doi:10.3390/ma13214757.
43. Toniolo, G.; Prisco, M. Reinforced Concrete Design to Eurocode 2; Springer: Heidelberg, Germany, 2017.
44. Andrei, N. An adaptive scaled BFGS method for unconstrained optimization. Numer. Algorithms 2018, 77, 413–432,
doi:10.1007/s11075-017-0321-1.
45. Battiti, R.; Masulli, F. BFGS Optimisation for Faster and Automated Supervised Learning. In International Neural Network Con-
ference; Springer: Dordrecht, the Netherlands, 1990; pp. 757–760.
46. Berahas, A.S.; Takáč, M. A robust multi-batch L-BFGS method for machine learning. Optim. Methods Softw. 2019, 35, 191–219,
doi:10.1080/10556788.2019.1658107.
47. Hagan, M.; Menhaj, M. Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Netw. 1994, 5, 989–
993, doi:10.1109/72.329697.
48. Li, D.-H.; Fukushima, M. A modified BFGS method and its global convergence in nonconvex minimization. J. Comput. Appl.
Math. 2001, 129, 15–35, doi:10.1016/s0377-0427(00)00540-9.
49. Abdi, F.; Shakeri, F. A globally convergent BFGS method for pseudo-monotone variational inequality problems. Optim. Methods
Softw. 2017, 34, 25–36, doi:10.1080/10556788.2017.1332619.
50. Grabowska, K.; Szczuko, P. Ship Resistance Prediction with Artificial Neural Networks. In Proceedings of the IEEE 2015 Signal
Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), Poznan, Poland, 23–25 September 2015.
51. Le, D.; Huang, W.; Johnson, E. Neural network modeling of monthly salinity variations in oyster reef in Apalachicola Bay in
response to freshwater inflow and winds. Neural Comput. Appl. 2019, 31, 6249–6259, doi:10.1007/s00521-018-3436-y.
52. Luenberger, D.G.; Ye, Y. Linear and Nonlinear Programming; Springer: New York, NY, USA, 2008.
53. Yildizel, S.A.; Arslan, Y. Flexural Strength Estimation of Basalt Fiber Reinforced Fly-Ash Added Gypsum Based Composites. J.
Eng. Res. Appl. Sci. 2018, 7, 829–834.
54. Sanjuán, M.A.; Argiz, C.; Menéndez, E. Efecto de la adición de mezclas de ceniza volante y ceniza de fondo procedentes del
carbón en la resistencia mecánica y porosidad de cementos Portland. Mater. Construcción 2013, 63, 49–64,
doi:10.3989/mc.2013.03911.
55. Sanjuán, M.Á.; Estévez, E.; Argiz, C.; del Barrio, D. Effect of curing time on granulated blast-furnace slag cement mortars car-
bonation. Cem. Concr. Compos. 2018, 90, 257–265, doi:10.1016/[Link].2018.04.006.
56. Poloju, K.K.; Anil, V.; Manchiryal, R.K. Properties of Concrete as Influenced by Shape and Texture of Fine Aggregate. Am. J.
Appl. Sci. Res. 2017, 3, 28, doi:10.11648/[Link].20170303.12.
57. Chinchillas-Chinchillas, M.J.; Corral-Higuera, R.; Gómez-Soberón, J.M.; Arredondo-Rea, S.P.; Alamaral-Sánchez, J.L.; Acuña-
Aguero, O.H.; Rosas-Casarez, C.A. Influence of the Shape of the Natural Aggregates, Recycled and Silica Fume on the Mechan-
ical Properties of Pervious Concrete. Int. J. Adv. Comput. Sci. Appl. 2014, 4, 216–220.
58. Jo, H.-S.; Park, C.; Lee, E.; Choi, H.K.; Park, J. Path Loss Prediction Based on Machine Learning Techniques: Principal Compo-
nent Analysis, Artificial Neural Network, and Gaussian Process. Sensors 2020, 20, 1927, doi:10.3390/s20071927.
59. Choi, Y.-Y.; Shon, H.; Byon, Y.-J.; Kim, D.-K.; Kang, S. Enhanced Application of Principal Component Analysis in Machine
Learning for Imputation of Missing Traffic Data. Appl. Sci. 2019, 9, 2149, doi:10.3390/app9102149.
60. Gadekallu, T.R.; Khare, N.; Bhattacharya, S.; Singh, S.; Maddikunta, P.K.R.; Ra, I.-H.; Alazab, M. Early Detection of Diabetic
Retinopathy Using PCA-Firefly Based Deep Learning Model. Electronics 2020, 9, 274, doi:10.3390/electronics9020274.
61. Abdi, H.; Williams, L.J. Principal Component Analysis. Wiley Interdiscip. Rev. Comput. Stat. 2010, 2, 433–459, doi:10.1002/wics.101.
62. Song, F.; Guo, Z.; Mei, D. Feature Selection Using Principal Component Analysis. In 2010 International Conference on System
Science, Engineering Design and Manufacturing Informatization, Proceedings of the 2010 International Conference on System Science,
Engineering Design and Manufacturing, Yichang, China, 18 November 2010; Institute of Electrical and Electronics Engineers (IEEE):
New York, NY, USA; 2010; Volume 1, pp. 27–30.
63. Tabakhi, S.; Moradi, P.; Akhlaghian, F. An unsupervised feature selection algorithm based on ant colony optimization. Eng.
Appl. Artif. Intell. 2014, 32, 112–123, doi:10.1016/[Link].2014.03.007.
64. Song, Y.; Liang, J.; Lu, J.; Zhao, X. An efficient instance selection algorithm for k nearest neighbor regression. Neurocomputing
2017, 251, 26–34, doi:10.1016/[Link].2017.04.018.
65. Yu, H.; Reiner, P.D.; Xie, T.; Bartczak, T.; Wilamowski, B.M. An Incremental Design of Radial Basis Function Networks. IEEE
Trans. Neural Netw. Learn. Syst. 2014, 25, 1793–1803, doi:10.1109/tnnls.2013.2295813.
66. Iqbal, S.Z.; Gull, H.; Ahmed, J. Incremental Sorting Algorithm. In 2009 Second International Conference on Computer and Electrical
Engineering, Proceedings of the 2009 Second International Conference on Computer and Electrical Engineering, Dubai, United Arab Emir-
ates, 15 January 2010; Institute of Electrical and Electronics Engineers (IEEE): New York, NY, USA, 2009; Volume 2, pp. 378–381.
67. Gürbüzbalaban, M.; Ozdaglar, A.; Parrilo, P.A. On the Convergence Rate of Incremental Aggregated Gradient Algorithms.
SIAM J. Optim. 2017, 27, 1035–1048, doi:10.1137/15m1049695.
68. Shobha, G.; Rangaswamy, S. Machine Learning. In Handbook of Statistics; Elsevier B.V.: Amsterdam, the Netherlands, 2018; Vol-
ume 38, pp. 197–228, ISBN 9780444640420.