IRJET- A Review on Application of Artificial Intelligence to Predict Strength of Concrete

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
A Review on Application of Artificial Intelligence
To Predict Strength of Concrete
Mohini Undal1, Dr. P. O. Modani2, Prof. A. S. Gadewar3
1ME student of Structural Engineering, Department of Civil Engineering, PLIT, Maharashtra, India
2Assistant Professor of Structural Engineering, Department of Civil Engineering, PLIT, Maharashtra, India
3Assistant Professor of Structural Engineering, Department of Civil Engineering, PLIT, Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract –Our thirst for progress as humans is reflected by
our continuous research activities in different areasleadingto
many useful emerging applications and technologies.Artificial
intelligence and its applications are good examples of such
explored fields with varying expectations and realistic results.
Generally, artificially intelligent systems have shown their
capability in solving real-life problems; particularly in non-
linear tasks. Such tasks are often assigned to an artificial
neural network (ANN) model to arbitrate as they mimic the
structure and function of a biological brain; albeit at a basic
level. In this paper, we investigate a newly emerging
application area for ANNs; namely structural engineering.We
design, implement and test an ANN model to predict the
properties of different concrete mixes. Traditionally, the
performance of concrete is affected by manynon-linearfactors
and testing its strength comprises a destructive procedure of
concrete samples.
Key Words: Artificial Neural Network, Compressive
strength, Durability, Ingredients of concrete.
1. INTRODUCTION
Artificial Neural Networks are typical example of modern
interdisciplinary subject that helps solving various
engineering problem which couldn’t solved by traditional
method. Neural network capable of collecting, memorizing,
analyzing and processing large number of data gained from
some experiment. They are an illustration of sophisticated
modeling technique that can be used for solving many
complex problems. The trained neural network serves as an
analytical tool for qualified prognoses of the results, for any
input data which were not included in the learning process
of the network. Their operation is simple and easy. An
artificial neural network isan emulation of biological neural
system. It is developed systematically step by step
procedure. Input/output training data is fundamental for
this network asitconveys information whichis necessaryto
discover the optimal operating point. The weight assigned
with eacharrow which represent information arrow, to give
more or less strength to the signal which they transmit. The
input neuron have only one input, their output will input
they received multiplied by weight. The neuron on output
layer receives output of both input neuron, multiplied by
their respective weight and sums them.
Figure 1 Artificial Neural Network
2. REVIEW OF LITERATURE
Mahmoud Abuy Yaman,Metwally Abd Elaty,Mohamed
Taman (2017)represent self compacting concrete is a
highly flow able type of concrete that spreads into form
without the need of mechanical vibration. It represents a
comparative study between two methodologies which have
been applied on two different data sets of SCC mixtures,
which were gathered from the literature, using artificial
neural network (ANN). The two methodologies aim to get
the best prediction accuracy for the SCC ingredients using
the 28-day compressive strength and slump flow diameters
as inputs of the ANN. In the first methodology, the ANN
model is constructed as a multi input – multi output neural
network with the six ingredients as outputs. In the second
methodology, the ANN model is constructedas a multi input
– single output neural network where the six ingredient
outputs are predicted separately from six different neural
networks of multi input – single output type. Also, the
influence of the mixes homogeneity on the prediction
accuracy is investigated through the second data set. The
results demonstrate the superiority of the second
methodology in terms of accuracy of the predicted outputs.
[1]
Volume: 06 Issue: 04 | Mar 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 73

Behrooz Shirgir, Amir Reza Mamdoohi, Abolfazl
Hassani(2015) states that pervious concrete is a concrete
mixture prepared from cement, aggregates, water, little or
no fines, and in some cases admixtures. The hydrological
property of pervious concrete is the primary reason for its
reappearance in construction. It gives two important
aspects of pervious concrete due to permeability and
compressive strength are investigated usingartificialneural
networks (ANN) based on laboratory data. The proposed
network is intended to represent a reliable functional
relationship between the input independent variables
accounting for the variability of permeability and
compressive strength of a porous concrete. Results of the
Back Propagation model indicate that the general fit and
replication of the data regarding the data points are quite
fine. The R-square goodness of fit of predicted versus
observed values range between 0.879 and 0.918 for thefinal
model; higher values were observed for the permeability as
compared with compressive strength and for the train data
set rather than the test data set. The findings can be
employed to predict these two important characteristics of
pervious concrete when there are no laboratorial data
available. [2]
Palika Chopra, Rajendra Kumar Sharma,Maneek
Kumar(August 2015) gives effort hasbeenmadetodevelop
concrete compressive strength prediction models with the
help of two emerging data mining techniques, namely,
Artificial Neural Networks and Genetic Programming . The
data for analysis and model development was collected at
28, 56, and 91-day curing periods through experiments
conducted in the laboratory under standard controlled
conditions. The developed models have also been tested on
in situ concrete data taken from literature. A comparison of
the prediction results obtained using both the models is
presented and it can be inferred that the ANN modelwiththe
training function Levenberg-Marquardt (LM) for the
prediction of concrete compressive strength is the best
prediction tool. [3]
Neela Deshpande, Shreenivas Londhe, Sushma
Kulkarni(2014) gives artificial neural networks have
emerged out as a promising technique for predicting
compressive strength of concrete. In the present study back
propagation was used to predict the 28 day compressive
strength of recycled aggregate concrete (RAC) along with
two other data driven techniques namely Model Tree (MT)
and Non-linear Regression (NLR). Recycled aggregate is the
current need of the hour owing to its environmental friendly
aspect of re-use of the construction waste. The study
observed that, prediction of 28 day compressive strength of
RAC was done better by ANN than NLR and MT. The input
parameters were cubic meter proportions of Cement,
Natural fine aggregate, Natural coarse Aggregates, recycled
aggregates, Admixture and Water (also called as raw data).
The study also concluded that ANN performs better when
non-dimensional parameters like Sand–Aggregate ratio,
Water–total materials ratio, Aggregate–Cementratio,Water–
Cement ratio and Replacement ratio of naturalaggregatesby
recycled aggregates, were used as additional input
parameters. Study of each network developed using raw
data and each non dimensional parameter facilitated in
studying the impact of each parameter on the performance
of the models developed using ANN, MT and NLR as well as
performance of the ANN models developed with limited
number of inputs. The results indicate that ANN learn from
the examples and grasp the fundamental domain rules
governing strength of concrete. [4]
Sakshi Gupta (2013) presents application of artificial
neural network to develop model for predicting 28 days
compressive strength of concrete withpartialreplacementof
cement with nano-silica for which the data has been taken
from various literatures. The use of nano-particle materials
in concrete can add many benefits that are directlyrelatedto
the durability of variouscementations materials, besidesthe
fact that it is possible to reduce the quantities of cement in
the composite. The performance of the model can be judged
by the correlation coefficient, mean absolute error and root
mean square error have been adopted as the comparative
measures against the experimental resultsobtainedfromthe
literature. [5]
P. Muthupriya, K. Subramanian, B .G. Vishnuram (April
2011) represent artificial neural network for predicting
compressive strength of cubes and durability of concrete
containing metakaolin with fly ash and silica fume with fly
ash are developed at the age of 3, 7, 28, 56 and 90 days. For
building these models, training and testing using the
available experimental results for 140 specimens produced
with 7 different mixture proportions are used. Thedataused
in the multi-layer feed forward neural networks models are
designed in a format of eight input parameters covering the
age of specimen, cement, metakaolin (MK), fly ash (FA),
water, sand, aggregate and super plasticizer and in another
set of specimen which contain SF instead of MK.Accordingto
these input parameters, in the multi-layer feed forward
neural networks models are used to predict thecompressive
strength and durability values of concrete. It shown that
neural networks have high potential for predicting the
compressive strength and durability values of the concretes
containing metakaolin, silica fume and fly ash. [6]
Marai M Alshihri, Ahmed M Azmy, Mousa S E1-Bisy
(2008) this investigation, the neural networks are used to
predict the compressive strength of light weight concrete
(LWC) mixtures after 3, 7, 14, and 28 days of curing. Two
models namely, feed-forward back propagation (BP) and
cascade correlation (CC), were used. The compressive
strength was modeled as a function of eight variables: sand,
water/cement ratio, lightweightfine aggregate, lightweight
coarse aggregate, silica fume used in solution, silica fume
used in addition to cement, super plasticizer, and curing
period. It isconcluded that neural networkmodelpredicated

slightly accurate results and learned very quickly as
compared to the BP procedure. This studyindicatedthatthe
neural networks models are sufficient tools for estimating
the compressive strength of LWC. This will reduce the cost
and save time in this class of problems. [7]
Jerzy Hola, Kezysztof Schabowcia (2005) deals with
neural identification ofcompressive strength ofconcrete on
basis on non-destructivity determined parameter. Basic
information of neural network and types of artificial neural
network most suitable for analysis of experimental results
are given. A set of experimental data for training and testing
covers compressive strength ranging from 24 to 105.The
results predict that artificial neural network highly suitable
for accessing compressive strength of concrete. [8]
I. C. Yeh (1998) is demonstrating possibilities of adapting
ANN to predict compressive strength of high performance
concrete .A set of trial batches with HPC produced in
laboratory & demonstrate satisfactory experimental results
whichconclude that a strength based on ANN moreaccurate
than model based on regression & it is easy, convenienttous
ANN model.[9]
3. CONCLUSIONS
Artificial Neural Network (ANN) model is a reliable
computational model to solve different complex problems
such as prediction problems. The neural network can be
used for a particular problem when deviationintheavailable
data is expected and accepted and also when a deﬁned
methodology is not available .Therefore, in order to predict
the properties of concrete with high reliability, instead of
using costly experimental investigation, Artificial Neural
Network model can be replaced. The neural network model
to predict compressive strength of concrete specimens is
utilized in this study. The prediction from values of average
percentage error Artificial Neural Network shows a high
degree of consistency with experimentally evaluated
compressive strength of concrete specimens used. Thus, the
present study suggests an alternative approach of
compressive strength assessment againstdestructivetesting
methods.
REFERENCES
[1] Mahmoud Abu Yaman, Metwally Abd Elaty, Mohamed
Taman, “Predicting the ingredients of self compacting
concrete using artificial neural network,” Alexandria
Engineering Journal, (2017)56,523-532.
[2] Behrooz Shirgir, Amir Reza Mamdoohi,AbolfazlHassani,
“Prediction of Pervious Concrete Permeability and
Compressive Strength Using ArtificialNeuralNetworks,”
International Journal of Transportation Engineering,
Vol.2/ No.4/ spring 2015.
[3] Palika Chopra, Rajendra Kumar Sharma and Maneek
Kumar, “Prediction o Compressive Strength ofConcrete
Using Artificial Neural Network and Genetic
Programming,” Hindwai Publishing Corporation,
Advances in Materials Science and Engineering Volume
2016, Article ID 467, August 2015.
[4] Neela Deshpande, ShreenivasLondhe, SushmaKulkarni,
“Modeling compressive strength of recycled aggregate
concrete by artificial neural network, model tree and
non-linear regression,” International Journal of
Sustainable Built Environment (2014)3,187-198.
[5] Sakshi Gupta, “Using Artificial Neural Network to
Predict the Compressive StrengthofConcretecontaining
Nano-silica,”Civil Engineering andArchitecture1(3):96-
102, 2013.
[6] P. Muthupriya, K. Subramanian, B. G. Vishnuram,
“PREDICTION OF COMPRESSIVE STRENGTH AND
DURABILITY OF HIGH PERFORMANCE CONCRETE BY
ARTIFICIAL NEURAL NETWORKS,”InternationalJournal
of Optimization In Civil Engineering, April 2011; 1:189-
209.
[7] Marai M. Alshihri, Ahmd M. Azmy, Mousa S. E1-Bisy,
“Neural networks for predictingcompressivestrengthof
structural light weight concrete”, Construction and
Building Materials 23(2009) 2214-2219, 4 January
2009.
[8] Jerzy Hola & Krzysztof Schabowica, “APPLICATION OF
ARTIFICIAL NEURAL NETWORKS TO DETERMINE
CONCRETECOMPRESSIVESTRENGTHBASEDONNON-
DESTRUCTIVE TESTS,” Journal of Civil Engineering and
Management 1822-360, 21 Feb 2005.
[9] I.C.Yeh, “MODELING OF STRENGTH OF HIGH-
PERFORMANCECONCRETEUSINGARTIFICIALNEURAL
NETWORKS,” Cement and Concrete Research,
September 14, 1998.

IRJET- A Review on Application of Artificial Intelligence to Predict Strength of Concrete

More Related Content

What's hot (18)

Similar to IRJET- A Review on Application of Artificial Intelligence to Predict Strength of Concrete (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- A Review on Application of Artificial Intelligence to Predict Strength of Concrete