Construction and Building Materials 25 (2011) 4105–4111

Contents lists available at ScienceDirect

Construction and Building Materials

journal homepage: www.elsevier.com/locate/conbuildmat

Predicting the core compressive strength of self-compacting concrete (SCC)

mixtures with mineral additives using artificial neural network
Mucteba Uysal a, Harun Tanyildizi b,⇑
a
Department of Civil Engineering, Sakarya University, Sakarya, Turkey
b
Department of Civil Engineering, Firat University, Elazig, Turkey

a r t i c l e i n f o a b s t r a c t

Article history: In this study, an artificial neural networks study was carried out to predict the core compressive strength
Received 24 August 2010 of self-compacting concrete (SCC) mixtures with mineral additives. This study is based on the determi-
Received in revised form 19 October 2010 nation of the variation of core compressive strength, water absorption and unit weight in curtain wall
Accepted 13 November 2010
elements. One conventional concrete (vibrated concrete) and six different self-compacting concrete
Available online 2 June 2011
(SCC) mixtures with mineral additives were prepared. SCC mixtures were produced as control concrete
(without mineral additives), moreover fly ash and limestone powder were used with two different
Keywords:
replacement ratios (15% and 30%) of cement and marble powder was used with 15% replacement ratio
Self-compacting concrete (SCC)
The core compressive strength
of cement. SCC mixtures were compared to conventional concrete according to the variation of compres-
Mineral admixture sive strength, water absorption and unit weight. It can be seen from this study, self-compacting concretes
Artificial neural network consolidated by its own weight homogeneously in the narrow reinforcement construction elements.
Experimental results were also obtained by building models according to artificial neural network
(ANN) to predict the core compressive strength. ANN model is constructed, trained and tested using these
data. The results showed that ANN can be an alternative approach for the predicting the core compressive
strength of self-compacting concrete (SCC) mixtures with mineral additives.
Crown Copyright Ó 2011 Published by Elsevier Ltd. All rights reserved.

1. Introduction increasing addition and inert or pozzolanic mineral additions in

Self-compacting concrete (SCC) has emerged in Japan in the late
1980s as a material that can flow under its own weight, so that it
can be easily placed, without need for additional mechanical com-
paction, in complicated formwork, congested reinforced structural
elements and hard to reach areas [1–3]. This concrete has gained
wide use in many countries for different applications and struc-
tural configurations [4–8]. The key performance criterion of this
technology is attaining a highly fluid behavior while preventing
bleeding and segregation of the mixture components [9].
Self-compacting concrete (SCC) removes the need for compac-
tion when placing fresh concrete. This saves time, reduces overall
cost, improves working environment and opens the way for the
automation of the concrete construction. Because of these signifi-
cant benefits, SCC is expected to gradually replace most of the or-
dinary concrete currently produced [10,11]. Especially the
developments in the superplasticizer technology have contributed
considerably to formation and progression of the self-compacting
concrete [12,13]. Different from the classical concrete design, the
self-compacting concrete needs the superplasticizers, viscosity
⇑ Corresponding author. Tel.: +90 424 2370000x4268; fax: +90 424 2367064.
E-mail address: htanyildizi@firat.edu.tr (H. Tanyildizi).
big quantity all together or partly.
The artificial neural networks solve very complex problems with
the help of interconnected computing elements. Basically, the pro-
cessing elements of a neural network are similar to the neurons in
the brain, which consist of many simple computational elements ar-
ranged in layers [14]. In recent years, the ANNs have been extended
extensively and applied to many civil engineering applications [15]
such as concrete durability [16], drying shrinkage [17], ready mixed
concrete delivery [18], slump model [19], workability of concrete
with metakaolin and fly ash [20,21], concrete structures [22–25],
mechanical behavior of concrete at high temperatures [26], con-
struction smoothness specification pay factor limits [27], cost anal-
ysis of HPC in tall building construction [28], asphalt concrete
permeability [29] and long term effect of fly ash and silica fume on
compressive strength [30]. The concrete mix proportion thus ob-
tained is expected to result with the lesser number of trials, cost
and time. Further the concrete designed by ANN is expected to have
optimum cement and water contents, thus leading to higher dura-
bility and relatively better economical and ecological effects [31].
In this study large-sized (300  150  20 cm), L-shaped and dou-
ble-sided reinforcement mesh equipment which was designed often
combined with a special pre-screen in the form of equipment and
placed in molds and curtain wall specimens were produced. The
aim of this paper is to construct an ANN model to predict the com-

0950-0618/$ - see front matter Crown Copyright Ó 2011 Published by Elsevier Ltd. All rights reserved.
doi:10.1016/j.conbuildmat.2010.11.108
4106 M. Uysal, H. Tanyildizi / Construction and Building Materials 25 (2011) 4105–4111

Table 1
Properties of portland cement and mineral additives.

Cement Fly ash Limestone powder Marble powder

Chemical composition (%)
SiO2 19.10 47.09 4.93 0.70
AI2O3 4.85 17.41 0.82 0.29
Fe2O3 3.24 8.34 0.58 0.12
CaO 61.86 13.98 51.97 55.49
MgO 2.02 1.85 0.58 0.23
SO3 2.63 4.65 – –
Loss ignition 2.90 1.79 40.40 42.83
CI 0.00 – – –
Na2O – 2.44 – 2.44
K2O – 1.80 – 1.80
Physical properties
Specific gravity 3.08 2.17 2,79 2,71
Blaine (cm2/g) 3996 2469 2500 8889

Table 2
Mix proportions of SCC and vibrated concrete for 1 m3.

Materials (kg/m3) Vibrated concrete Control FA15 SCC FA30 SCC LP15 SCC LP30 SCC MP15 SCC
Cement 550 550 467 385 467 385 467
Limestone powder – – – – 83 165 –
Marble powder – – – – – – 83
Fly ash – – 83 165 – – –
Water 182 182 182 182 182 182 182
w/c ratio 0.33 0.33 0.39 0.51 0.37 0.47 0.39
w/p ratio 0.33 0.33 0.33 0.33 0.33 0.33 0.33
Sand 865 869 865 878 866 860 863
CSI 466 467 457 445 464 461 463
CSII 320 311 305 297 311 307 312

pressive strength. For this purpose, a computer program was devel-
oped in MATLAB. Furthermore, the results obtained from the ANN
model were compared with the average results of the experiments.
2. Experimental procedure
2.1. Materials
The Portland cement used in this study was produced according to the European
Standards EN-197/1 and labeled as CEM I/42.5 R. The physical and chemical proper-
ties of the Portland cement is listed in Table 1. The maximum size of coarse aggre-
gate was selected as 16 mm in order to avoid the blocking effect of SCC. Besides,
fly ash, marble powder and limestone powder were used as mineral and filler addi-
tives in SCC to utilize it. Specific surface area by Blaine and 28th day compressive
strength of cement were 399.6 m2/kg, and 48.3 MPa, respectively.
Marble powder (MP) was provided from a marble managing plant in Bilecik di-
rectly used in SCC without any processes. The specific surface area by Blaine of MP
is 889 m2/kg. Limestone powder was a by-product of quarry crushers and collected
from the filtration system of a quarry crushers. The characteristic properties, min-
eralogical composition and particle size distribution of filler materials are given
Table 1.
Polycarboxylate based and high range water reducing superplasticizer was also
used in the mixtures at the ratio of 1.6% of binder materials by weight for reducing
the water/binder ratio of SCC. The solid content and pH of superplasticizer were 21%
and 8%, respectively. Tap water used was obtained from the city waterworks of Sak-
arya for the production of concrete mixtures during the experimental procedure.

3
2 4
1 5
6

9 10
8 11
7 12

15 16
14 17
13 18
22
21
20 23
19 24

Fig. 1. Core points on curtain wall.

 M. Uysal, H. Tanyildizi / Construction and Building Materials 25 (2011) 4105–4111 4107

Table 3
Test results of CC, LP15, LP30 and MP15 mixtures in curtain wall element.

Core Nb. CC LP15

Compressive strength Water absorption Unit weight Compressive strength Water absorption Unit weight
1 45.07 4.25 2.418 45.43 3.56 2.401
2 48.14 3.87 2.415 45.38 3.55 2.408
3 46.35 4.06 2.414 44.71 3.61 2.403
4 44.20 4.24 2.411 46.50 3.32 2.413
5 42.61 4.44 2.405 48.10 3.11 2.415
6 43.00 4.39 2.410 45.03 3.55 2.400
7 48.94 3.98 2.415 43.86 3.64 2.394
8 51.04 3.63 2.422 44.84 3.45 2.398
9 61.31 2.71 2.440 49.93 2.86 2.408
10 55.83 3.15 2.437 45.88 3.35 2.403
11 53.87 3.47 2.432 47.99 2.94 2.416
12 57.08 3.14 2.430 45.77 3.46 2.401
13 54.77 3.30 2.426 45.90 3.50 2.405
14 58.17 3.16 2.432 42.09 3.84 2.394
15 58.59 3.01 2.436 43.41 3.69 2.399
16 50.31 3.86 2.420 50.03 2.82 2.428
17 51.60 3.55 2.421 48.06 3.00 2.414
18 50.54 3.79 2.425 46.95 3.37 2.407
19 61.14 2.76 2.438 46.55 3.39 2.422
20 60.37 2.80 2.434 46.07 3.40 2.414
21 59.77 2.95 2.434 46.91 3.35 2.417
22 55.52 3.27 2.429 51.74 2.67 2.426
23 55.99 3.18 2.429 52.27 2.53 2.421
24 57.43 3.11 2.435 51.86 2.57 2.417
LP30 MP15
1 42.38 4.02 2.396 51.35 4.62 2.393
2 38.08 5.07 2.389 55.53 4.35 2.402
3 40.75 4.83 2.399 55.91 4.33 2.405
4 44.58 3.45 2.410 56.60 4.07 2.415
5 36.92 5.36 2.382 52.51 4.47 2.400
6 40.72 4.57 2.397 50.49 4.71 2.389
7 43.19 3.98 2.407 56.54 4.13 2.409
8 45.79 3.89 2.420 48.91 4.80 2.417
9 37.44 5.33 2.391 49.53 4.75 2.390
10 38.87 4.91 2.389 53.13 4.27 2.404
11 44.93 3.71 2.412 56.06 4.25 2.407
12 45.80 3.37 2.414 55.89 4.18 2.409
13 38.50 5.29 2.399 50.07 4.80 2.393
14 44.70 3.66 2.401 52.02 4.62 2.400
15 45.81 3.54 2.410 54.08 4.25 2.412
16 43.75 3.91 2.412 51.10 4.39 2.409
17 36.96 5.67 2.378 52.60 4.48 2.401
18 42.00 4.10 2.399 46.57 4.92 2.385
19 44.13 3.79 2.403 54.25 4.20 2.413
20 42.20 4.19 2.408 49.84 4.60 2.410
21 37.77 5.38 2.376 49.77 4.68 2.396
22 40.78 4.82 2.388 53.46 4.40 2.409
23 41.53 4.05 2.381 46.52 4.90 2.382
24 42.04 4.15 2.401 53.83 4.43 2.414

2.2. Mixture proportions
One conventional concrete (CC, vibrated concrete) and six different SCC mix-
tures with mineral additives were prepared. Table 2 presents the composition
and labeling of the SCCs. As seen in that table, the mixtures were labeled such that
the ingredients were identifiable from their IDs. One control concrete (without min-
eral additives) was produced and fly ash and limestone powder were used with two
different replacement ratios (15%, and 30%) of cement (FA15, FA30, LP15, LP30).
Moreover, marble powder was used with 15% replacement ratio of cement
(MP15). After the preliminary investigations, the water–powder ratio (w/p) was se-
lected as 0.33 and the total powder content was fixed to 550 kg/m3.
2.3. Preparation and testing of specimens
After self-compactibility was determined by fresh concrete experiments con-
cretes were poured from a point at the top of the mold and placed in molds without
vibration. Conventional concrete was vibrated by two sides as L shape. All of the
curtain wall specimens were demoulded after a day, then, samples were cured at
22 ± 2 °C with 100% RH during 28 days period. At the end of 28 days, by taking into
account reinforcement points, the different height levels of the curtain wall core
samples were removed and these samples were made on the compressive strength,
water absorption and unit weight tests. Compressive strength of each core speci-
men was determined using TS EN 12504-1 [32], water absorption of each core spec-
imen was determined using DIN 4226 [33] and unit weight of each core specimen
was determined using TS EN 12390-7 [34]. Curtain wall specimen is presented in
Fig. 1.
3. Experimental results
In order to determine the variation of core compressive
strength, water absorption and unit weight to find out homogene-
ity, there were tests applied on the wall elements and the results
are summarized in Tables 3 and 4. Fig. 1 also shows core specimen
numbers to compare the variation among core specimens. Mean-
while, number 1 is accepted concrete pouring point. When SCC
mixtures are compared to conventional concrete as compressive
strength, there is no significant variance among the results of the
same mix at different depths of the wall elements in SCC. The obvi-
ous trend is that, the bottom specimens have higher strength val-
ues than the top specimens, probably due to higher degree of
compaction due to the weight of the concrete above. This also
shows that the segregation has not occurred while concrete is
4108 M. Uysal, H. Tanyildizi / Construction and Building Materials 25 (2011) 4105–4111

Table 4
Test results of control, FA15 and FA30 mixtures in curtain wall element.

Core Nb. Control FA15

Compressive strength Water absorption Unit weight Compressive strength Water absorption Unit weight
1 40.00 2.40 2.402 53.60 2.82 2.375
2 44.50 1.61 2.406 56.48 2.19 2.396
3 47.67 1.50 2.418 55.68 2.40 2.388
4 49.35 1.24 2.423 55.89 2.13 2.391
5 46.09 1.50 2.417 54.88 2.63 2.389
6 49.88 1.35 2.427 57.23 1.93 2.394
7 44.30 1.72 2.409 56.09 2.08 2.380
8 50.23 1.22 2.425 56.17 1.97 2.392
9 41.40 2.23 2.408 54.02 2.60 2.380
10 48.31 1.46 2.417 55.97 2.75 2.379
11 42.55 1.95 2.409 57.50 1.85 2.374
12 46.66 1.58 2.417 53.99 2.54 2.381
13 43.70 1.80 2.408 53.01 3.05 2.376
14 48.40 1.41 2.424 54.02 2.42 2.388
15 46.23 1.61 2.415 53.78 2.13 2.379
16 47.20 1.53 2.419 53.69 2.19 2.388
17 44.45 1.56 2.410 46.45 3.27 2.372
18 50.06 1.25 2.412 54.07 2.55 2.385
19 42.94 2.05 2.425 54.11 2.15 2.380
20 49.35 1.40 2.427 55.18 1.82 2.391
21 43.17 1.89 2.404 43.88 3.38 2.370
22 46.78 1.61 2.409 47.87 3.19 2.375
23 40.35 2.38 2.413 52.32 3.01 2.376
24 44.54 1.65 2.413 54.87 2.03 2.399
FA30
1 42.71 3.05 2.352
2 45.37 2.56 2.358
3 44.79 2.85 2.350
4 43.80 2.68 2.365
5 40.37 3.40 2.340
6 47.83 2.48 2.356
7 46.34 2.54 2.357
8 44.90 2.63 2.370
9 41.33 3.30 2.344
10 43.76 3.27 2.346
11 45.28 2.69 2.360
12 46.76 2.51 2.362
13 42.15 3.74 2.350
14 43.94 3.15 2.348
15 45.73 2.46 2.355
16 45.14 2.64 2.364
17 41.48 3.19 2.345
18 44.52 2.89 2.360
19 44.87 2.82 2.348
20 42.04 3.46 2.358
21 42.94 2.97 2.350
22 43.08 3.01 2.359
23 43.11 2.89 2.355
24 44.23 2.77 2.359

being poured down a 1.5 m high formwork. This indicates that the
mixes had adequate stability. But, conventional concrete has sig-
nificant variance among the results of the bottom specimens and
the top specimens. The variation between the top compressive
strength values and the bottom compressive strength is higher in
conventional concrete than all of the SCC. According to compres-
sive strength test results, the concrete consists of fly ash 15%
replacement ratio with cement has the highest average compres-
sive strength values.
Water absorption determination was done to cylindrical core
specimens before compressive strength tests were done. The obvi-
ous trend is that, the top specimens have higher water absorption
values than the bottom specimens. The bottom specimens consoli-
date better than the top specimens because of hydrostatic effect and
bottom specimens have less permeable depending on this situation.
Control concrete wall element exhibits the lowest water absorption
values comparing to the other compositions. Such results suggest
that control concrete was denser and more resistant to fluid ingress
than the others. Although limestone powder was assumed to have a
filling effect, this mixture incorporating high volumes of LP (30%
replacement rate with cement), exhibits the highest water absorp-
tion values than other mixtures. This is likely to be due to the high
volume of limestone powder hindering the overall cementitious
reactions, hence creating a more porous microstructure. In general,
any factor tending to improve the compressive strength of the con-
crete will have a beneficial effect upon the water-tightness. There-
fore, a similar trend in the compressive strength is observed for
water absorption results for different compositions.
Unit weight determination was also done to cylindrical core
specimens before compressive strength tests were done. The trend
is that, the bottom specimens have higher unit weight values than
the top specimens. The bottom specimens consolidate better than
the top specimens and they exhibit denser and less porous micro-
structure which means higher unit weight values. According to
unit weight test results, control concrete exhibits the highest aver-
age unit weight values.
 M. Uysal, H. Tanyildizi / Construction and Building Materials 25 (2011) 4105–4111 4109

Input Hidden Output Performance is 9.99953e-005, Goal is 0.0001

1
Layer Layer Layer 10

Σ Σ 0
10

Training-Blue Goal-Black
Inputs Σ
-1
10

Σ Σ Training
-2 Goal
10
Σ
Σ -3
10
bias bias
10-4
Fig. 2. Multilayer feed forward neural network structure.

10-5
4. Artificial neural network model for prediction of 0 50 100 150 200 250 300 350 400 450
experimental results 464 Epochs

Fig. 4. Training performance of the ANN (Fletcher–Powell conjugate gradient

Artificial neural networks (ANNs) are biologically inspired and
mimic the human brain. They are consisting of a large number of
simple processing elements called as neurons. These neurons are
connected with connection link. Each link has a weight that is mul-
tiplied by transmitted signal in network. Each neuron has an acti-
vation function to determine the output. There are many kinds of
activation functions. Usually nonlinear activation functions such
as sigmoid, and step are used. ANNs are trained by experience,
algorithm).
when an unknown input is applied to the network it can generalize
from past experiences and produce a new result [35–38]. Artificial
neural networks are systems that are deliberately constructed to
make use of some organizational principles resembling those of

Cement

Fly ash

Limestone
powders

Marble
powders

Natural
aggregate Compressive
Strength
I number
aggregate

II number
aggregate

Super
plasticizer

Unit
weight

Water
absorption

Fig. 3. ANN architecture.

4110 M. Uysal, H. Tanyildizi / Construction and Building Materials 25 (2011) 4105–4111

1.2 1.2

2
R = 0.95 1

Neural Networks Results

1
Neural Networks Results

2
R = 0.92

0.8 0.8

0.6 0.6

0.4 0.4

0.2 0.2

0 0
0 0.2 0.4 0.6 0.8 1 1.2 0.5 0.6 0.7 0.8 0.9 1 1.1
Experimental Results Experimental Results

Fig. 5. Linear relationship between measured and predicted compressive strengths Fig. 7. Linear relationship between measured and predicted compressive strengths
(Fletcher–Powell conjugate gradient backpropagation algorithm). (Levenberg–Marquardt backpropagation algorithm).

max values. The back propagation learning algorithm has been

Performance is 9.95041e-005, Goal is 0.0001 used in a feed-forward, two hidden layer neural network. ANN
0
10 architecture used for this study is given in Fig. 3.
The all algorithms of ANN were used for this study but the
-1 Fletcher–Powell conjugate gradient and Levenberg–Marquardt
10
Training-Blue Goal-Black

backpropagation were just learning. The computer program was

performed under MATLAB software using the neural network tool-
-2 box. In the training, the number of neuron on the hidden layer is
10
Goal
Training fourteen and teen. A data set including 168 data samples obtained
from experimental studies were used for artificial neural networks.
10
-3 From these, 84 data patterns were used for training the network,
and the remaining 84 patterns were randomly selected and used
as the test data set. Figs. 5 and 7 present the measured compressive
10
-4 strengths versus predicted compressive strengths by ANN model
with R2 coefficients. Figs. 5 and 7 shows that ANN model predict
the compressive strength of concrete with R2 of 0.95 and 0.92,
10-5 respectively. The training performance during the training process
0 10 20 30 40 50 60 is given in Figs. 4 and 6 where the variation of mean-square error
61 Epochs with training epochs is illustrated.

Fig. 6. Training performance of the ANN (Levenberg–Marquardt backpropagation

algorithm).
5. Conclusions

In this study, a ANN prediction model for compressive strength

the human brain [35–38]. They represent the promising new gen-
eration of information processing systems.
When designing an ANN model, a number of considerations
must be taken into account. At first the suitable structure of the
ANN model must be chosen. Then, the activation function need
to be determined. The number of layers and the number of units
in each layer must be chosen. Generally desired model consists
of a number of layers. The most general model assumes complete
interconnections between all units. These connections can be bidi-
rectional or unidirectional. ANN can create its own organization or
representation of the information it receives during learning time
[35–38]. There are many kind of ANN structure. One of these is
multilayer feed forward ANN and is shown in Fig. 2.
In this study, the problem is proposed to network models by
means of ten inputs and one output parameter. The parameters
such as amount of cement, amount of fly ash, amount of limestone
powders, amount of marble powders, amount of natural aggregate,
amount of I number aggregate, amount of II number aggregate,
amount of superplasticizer, Unit weight, water absorption were se-
lected as input variables. The model output variable was the com-
pressive strength of the concrete. A data set including 168 data
samples obtained from experimental studies were used for artifi-
cial neural networks. The data were normalized by dividing with
of SCC was devised. From this laboratory and computer work the
following conclusions were made:
 When SCC mixtures are compared to conventional concrete as
compressive strength, there is no significant variance among
the results of the same mix at different depths of the wall ele-
ments in SCC. But, conventional concrete has significant vari-
ance among the results of the bottom specimens and the top
specimens. The variation between the top compressive strength
values and the bottom compressive strength is higher in con-
ventional concrete than all of the SCC.
 The top specimens have higher water absorption values than
the bottom specimens. The bottom specimens consolidate bet-
ter than the top specimens because of hydrostatic effect and
bottom specimens have less permeable depending on this situ-
ation. According to water absorption test results, a similar trend
in the compressive strength is observed for water absorption
results for different compositions in the narrow reinforcement
construction elements.
 The bottom specimens consolidate better than the top speci-
mens and they exhibit denser and less porous microstructure
which means higher unit weight values in SCC and conventional
concrete curtain wall construction elements.
 M. Uysal, H. Tanyildizi / Construction and Building Materials 25 (2011) 4105–4111
 When the test results were evaluated, it was shown that self-
compacting concretes consolidated by its own weight homoge-
neously in the narrow reinforcement construction elements,
when it was compared to conventional concrete and the use
of self-compacting concrete was optimum solution especially
in the column-beam integrated systems.
 Between the algorithms of ANN tested for this study, Fletcher–
Powell conjugate algorithm is found to be the best learning
algorithm. The ANN model predicts the core compressive
strength of SCC with the high correlation coefficient. Therefore,
the results show that the ANN can be used to predict the core
compressive strength of SCC using the ingredients of concrete.
References
[1] Ozawa K, Maekawa K, Kunishima H, Okamura H. Performance of concrete
based on the durability design of concrete structures. Proc Sec East Asia-Pacific
Conf Struct Eng Const 1989;1:445–56.
[2] Rols S, Ambroise J, Ṕera J. Effects of different viscosity agents on the properties
of self-levelling concrete. Cem Concr Res 1999;29(2):261–6.
[3] Okamura H et al. Self-compacting high performance concrete. In: proceedings
of the fifth EA SEC, vol. 3; 1995. p. 2381–8.
[4] Campion MJ, Jost P. Self-compacting concrete. Concr Int: Des Constr
1999;22(4):31–4.
[5] Khayat KH, Manai K, Trudel A. In situ mechanical properties of wall elements
using self-consolidating concrete. ACI Mater J 1997;94(6):491–500.
[6] Yurugi M. Application of self-compacting concrete in Japan. In: proceedings
23rd OWICS conference, Singapore: CI-Premier Ptc. Ltd.; 1998. p. 29–42.
[7] Petersson O. Application of self-compacting concrete for bridge castings. Swed
Cem Concr Res Inst 1998;54(2):5.
[8] Arima I, Takeguchi M, Sakurai S, Hayashi J. The quality of superworkable
concrete used for the construction of Akashi-Kaikyo Bridge 4A anchorage. Proc
Jpn Concr Inst 1994;16(1):25–30.
[9] Nehdi M, Pardhanb M, Koshowskic S. Durability of self-consolidating concrete
incorporating high-volume replacement composite cements. Cem Concr Res
2004;34(11):2103–12.
[10] Bartos PJM, Grauers M. Self-compacting concrete. Concrete 1999;3(4):9–13.
[11] Skarendahl A. Market acceptance of self-compacting concrete. The Swedish
experience. In: Ozawa K, Ouchi M, editors. Proc. 2nd inter. symp. on SCC, Coms
Engineering Corporation Tokyo; 2001. p. 1–13.
[12] Okamura H, Ozawa K, Maekawa K, Tangtermsinikul S. High performance
concrete mechanism of super-fluidized concrete. EIT-JSCE-AIT joint seminar
on solution to urban infrastructure problems through civil engineering
technology, Bangkok; 1992. p. 16.
[13] Ozawa K, Maekawa K, Kunishima M, Okamura H. High-performance concrete
based on the durability of concrete structures. In: proceedings of the second
East Asia Pacific conference on structural engineering and construction; 1989.
[14] Yeh I. Modeling of strength of high-performance concrete using artificial
neural networks. Cem Concr Res 1998;28(12):1797–808.
4111
[15] Zong WJ, Guang NH, Yun HJ. The application of automatic acquisition of
knowledge to mix design of concrete. Cem Concr Res 1999;29(12):1857–80.
[16] Jepsen MT. Predicting concrete durability by using artificial neural network.
Published in a special NCR-publication; ID. 5268; 2002.
[17] Basma AA, Barakat S, Oraimi SA. Prediction of cement degree of hydration
using artificial neural networks. Mater J 1999;96(2):166–72.
[18] Graham LD, Forbes DR, Smith SD. Modeling the ready mixed concrete delivery
system with neural network. Automat Constr 2006;15(5):656–63.
[19] Yeh C. Exploring concrete slump model using artificial neural networks. J
Comput Civil Eng ASCE 2006;20(3):217–21.
[20] Al-Metairie N, Terroand M, Al-Khaleefi A. Effect of recycling hospital ash on the
compressive properties of concrete. Build Environ 2004;39(5):557–66.
[21] Bai J, Wild S, Ware JA, Sabir BB. Using neural networks to predict workability of
concrete. Adv Eng Softw 2003;34(11–12):663–9.
[22] Oztas A, Pala M, Ozbay E, Kanca E, Caglar N, Bhatti MA. Predicting the
compressive strength and slump of high strength concrete using neural
network. Constr Build Mater 2006;20(9):769–75.
[23] Hadi MN. Neural networks applications in concrete structures. Comput Struct
2003;81(6):373–81.
[24] Waszczyszyn Z, Ziemianski L. Neural networks in mechanics of structures and
materials. Comput Struct 2001;79(22–25):2261–76.
[25] Ashour A, Alqedra M. Concrete breakout strength of single anchors in tension
using neural networks. Adv Eng Softw 2005;36(2):87–97.
[26] Mukherjee A, Biswas SN. Artificial neural networks in prediction of mechanical
behavior of concrete at high temperature. Nucl Eng Des 1997;178(1):1–11.
[27] FanChou S, Pellinen TK. Assessment of construction smoothness specification
pay. J Transport Eng 2005;131(7):563–70.
[28] Tam CM, Fang CF. Comparative cost analysis of using high performance
concrete in tall building construction by artificial neural networks. Struct J
1999;96(6):927–36.
[29] Tarefder RA, White L, Zaman M. Neural network model for asphalt concrete
permeability. J Mater Eng 2005;17(1):468–73.
[30] Pala M, Ozbay E, Oztas A, Yuce MI. Appraisal of long-term effects of fly ash and
silica fume on compressive strength of concrete by neural networks. Constr
Build Mater 2007;21(2):384–94.
[31] Ji T, Lin T, Lin X. A concrete mix proportion design algorithm based on artificial
neural network. Cem Concr Res 2006;36(7):1399–408.
[32] TS EN 12504-1. Testing concrete in structures – part 1: cored specimens –
taking, examining and testing in compression. TSE Ankara; 2002 [in Turkish].
[33] DIN 4226. Test method for determination the specific gravity the absorbtion
water and the void ratio in hardened concrete; 1981.
[34] TS EN 12390-7. Testing hardened concrete – part 7: density of hardened
concrete. TSE Ankara; 2010 [in Turkish].
[35] Hanbay D, Turkoglu I, Demir Y. An expert system based on wavelet
decomposition and neural network for modeling chua’s circuit. Exp Syst
Appl 2008;34(4):2278–83.
[36] Haykin S. Neural networks, a comprehensive foundation. College Publishing
Comp. Inc.; 1994.
[37] Hanbay D, Turkoglu I, Demir Y. Prediction of wastewater treatment plant
performance based on wavelet packet decomposition and neural networks.
Exp Syst Appl 2008;34(2):1038–43.
[38] Bilim C, Atisß CD, Tanyildizi H, Karahan O. Predicting the compressive strength
of ground granulated blast furnace slag concrete using artificial neural
network. Adv Eng Softw 2009;40(5):334–40.