Reinforced Concrete Slabs by Robert Park- William L.gamble2ed
DESIGN OPTIMIZATION OF REINFORCED CONCRETE SLABS …The two types of reinforced concrete slabs...
Transcript of DESIGN OPTIMIZATION OF REINFORCED CONCRETE SLABS …The two types of reinforced concrete slabs...
http://www.iaeme.com/IJCIET/index.asp 1370 [email protected]
International Journal of Civil Engineering and Technology (IJCIET)
Volume 9, Issue 4, April 2018, pp. 1370–1386, Article ID: IJCIET_09_04_153
Available online at http://www.iaeme.com/ijciet/issues.asp?JType=IJCIET&VType=9&IType=4
ISSN Print: 0976-6308 and ISSN Online: 0976-6316
© IAEME Publication Scopus Indexed
DESIGN OPTIMIZATION OF REINFORCED
CONCRETE SLABS USING GENETIC
ALGORITHMS
Shaik Bepari Fayaz Basha
Assistant Professor, Department of Civil Engineering,
G. Pulla Reddy Engineering college, Kurnool, Andhra Pradesh, India
K. Madhavi Latha
Assistant Professor, Department of Civil Engineering,
G. Pulla Reddy Engineering college, Kurnool, Andhra Pradesh, India
ABSTRACT
Design Optimization is the process of finding best design parameters that satisfy
the project requirements both in terms of strength and serviceability criteria. In the
present paper this optimization is carried out for Reinforced Concrete (RC) slabs
using Genetic Algorithms (GA), an iterative procedure which is based on theory of
natural selection and evolutionary biology. The two types of reinforced concrete slabs
considered in particular for the design are: simply supported one way slab and
cantilever slab. The design of the slabs is based on IS: 456-2000 code specifications.
The objective is to include the cost of concrete, the cost of reinforcement and the cost
of formwork respectively with their volume of materials.
This genetic algorithm iterative values are developed using MATLAB and the
codes are used for optimization. The results obtained are compared with the known
published results.
Further, the changes in the optimum values are studied by the variation of several
constraints such as the number of generations, population size and mutation rate.
Also by changing the fixed parameters i.e., the characteristic cube strength of
concrete and characteristic yield strength of steel, the effect on the optimum cost for a
particular loading condition and also for various loading conditions is studied. By
changing the span length of the slab, effect on the optimum cost and optimum
reinforcement ratio is studied for different loading conditions.
Key words: Cantilever slab, Design optimization, Genetic Algorithm, One way slab,
Reinforced Concrete
Cite this Article: Shaik Bepari Fayaz Basha and K. Madhavi Latha, Design
Optimization of Reinforced Concrete Slabs Using Genetic Algorithms, International
Journal of Civil Engineering and Technology, 9(4), 2018, pp. 1370–1386.
http://www.iaeme.com/IJCIET/issues.asp?JType=IJCIET&VType=9&IType=4
Shaik Bepari Fayaz Basha and K. Madhavi Latha
http://www.iaeme.com/IJCIET/index.asp 1371 [email protected]
1. INTRODUCTION
In the construction stream of civil engineering, in particular the construction of reinforced
concrete structures, optimization is playing a vital role in terms of economy as well as safety
considerations. The overall cost of the reinforced concrete structure including the cost of
concrete, reinforcement steel and cost of formwork are considered for optimization[1].
The
optimum solution obtained by using conventional methods face some difficulties while
solving problems related to executing same moment of resistance exhibited by slab
measurements and percent of reinforcement steel. To avoid the difficulty, the Genetic
Algorithm (GA) method of optimization of RC simply supported one way slab and cantilever
slab according to IS 456:2000[2]
is studied in the present paper.
1.1. Optimum Design of Structure
Optimum design indicates the most economical design that is practically possible which
should also satisfy the safety requirements as per IS code. Optimum structural design
indicates maximum utilisation of the existing material sources.
1.2. Objective of the Study
The main objective of the study is minimisation of total cost of the RC simply supported slab
and cantilever slab using Genetic Algorithm optimization program[3]
in MATLAB software
with IS 456:2000 code as a constraint.
1.3. Approach of the Study
After the detailed inspection of the preceding related works, genetic algorithm optimization
programs are established and the efficiency of the optimization programs are verified by
applying illustrative problems on RC simply supported one way slab and cantilever slab. The
design results obtained from MATLAB are compared with the previous works. Also the
known parameters are changed and the variation of optimum values as influenced by the
variation of the constraint is studied
2. METHODOLOGY OF THE STUDY
Design of any member indicates the determination of dimensions of the structure which fulfil
the requirements of the code and should be most economical and safe. The present study is
conducted on slabs which are the reinforced concrete elements transferring the transverse
loads which creates the bending moments and shear forces[4].
The basic design begins by selecting the cross section dimensions which should withstand
the bending moment and also selecting the necessity of steel reinforcement. Then the slab
dimensions should be checked for shear and deflection.
2.1. Design Preview for Slabs
The programs developed in the thesis for the optimization of simply supported and cantilever
slab follows certain provisions of IS 456:2000, which include the clear cover to the steel, trial
sections for depth, maximum moment coefficients of slabs, requirements for reinforcing steel,
shear reinforcement and deflection control.
2.1.1. Simply Supported One Way Slab
The loading diagram and the geometry of simply supported one way slab are shown in fig.1
and fig.2 respectively.
Design Optimization of Reinforced Concrete Slabs Using Genetic Algorithms
http://www.iaeme.com/IJCIET/index.asp 1372 [email protected]
Figure 1 Typical simply supported RC one way slab with distributed load[5]
Figure 2 Geometry of a RC one way slab[6]
2.1.2. Constant Parameters
The constant values considered for the reinforced concrete one way slab model are Span
length of the slab, Span to depth ratio, The characteristic compressive cube strength of the
concrete, The characteristic strength of the steel, The uniformly distributed super imposed
loads, The cost of the quantity of concrete, The cost of required steel reinforcement, The cost
of the required formwork.
2.1.3. Design Variables
The following variables are treated in the simply supported one way slab problem are: d =
effective depth of slab (x1), pt = percentage of steel (x2), sv = spacing of reinforcement
bars(x3).
2.1.4. Design Constraints
The design constraints used in the study include the span to depth ratio, minimum depth
constraint, constraints to be considered in flexural design, minimum and maximum spacing
between reinforcement bars, deflection constraints and the constraints for shear design
according to IS 456:2000
2.1.5. Objective Function
The objective function in this RC one way slab in which the total cost including the cost of
concrete, the cost of reinforcement steel and the cost of formwork is defined as follows:
Shaik Bepari Fayaz Basha and K. Madhavi Latha
http://www.iaeme.com/IJCIET/index.asp 1373 [email protected]
'
'
'
(x) C [ ( (1) d ) breadth {(x(2) 0.01 width x(1) x(3) ( 1) breadth)(2)
(0.0012 width (x(1) d ))}] [(x(2) 0.01 width x(1) x(3) ( 1) breadth) (0.0012(2)
width (x(1) d ))] [breadth
c
s
f
widthf width x
x
widthC
x
C
'(x(1) d )](1)
Where,
x(1) = effective depth of the slab, d
x(2) = percentage reinforcement ratio of steel, pt
2
2
100 4.5981 (1 )
2 8
ck ut
y ck
f w lp
f bd f
x(3) = spacing of reinforcement, sv
278.5398v
t
sb d p
Cc = cost of concrete including labour charges(Rs./m3)
Cs = cost of steel including bending of bars (Rs./m3)
Cf = cost of formwork(Rs./m2)
d’ = effective nominal cover to the reinforcement (mm)
fck = characteristic compressive strength of the concrete in N/mm2
fy = characteristic yield strength of the steel in N/mm2
l = effective span of the slab in metre.
Mu = bending moment due to super imposed load and self-weight in kN-m
wu = design load in kN/m2 = 1.5(dead load +live load)
b = width of the slab = 1000 mm
Ø = diameter of the reinforcing bar (mm)
2.1.6. Cantilever Slab
The loading diagram and the geometry of cantilever slab are shown in fig.3 and fig.4
respectively.
Figure 3 Typical RC cantilever slab with distributed load
Design Optimization of Reinforced Concrete Slabs Using Genetic Algorithms
http://www.iaeme.com/IJCIET/index.asp 1374 [email protected]
Figure 4 Geometry of a RC cantilever slab
The constant parameters, design variables are same as that of simply supported one way
slab. The design constraints same as that of the simply supported one way slab corresponding
to the cantilever slab are used according to IS 456:2000.
2.1.7. Objective Function
The objective function is same as that of simply supported one way slab given by (1)
Except the percentage reinforcement ratio of steel is given by:
2
2
100 4.5981 (1 )
2 2
ck ut
y ck
f w lp
f bd f
2.1.8. Values of Cost
The value of Cc, Cs, Cf as per USSR (Unified schedule of rates and specifications) are given
below[7]:
Cost of concrete:
For M20 grade, cost of concrete, Cc = 6854.7(Rs. /m3)
For M25 grade, cost of concrete, Cc = 7091.05(Rs. /m3)
Cost of steel:
For Fe415 grade, cost of steel, Cs = 353250(Rs. /m3)
For Fe500 grade, cost of steel, Cs = 392500(Rs. /m3)
Cost of formwork, Cf = 401.65(Rs. /m2)
3. GENETIC ALGORITHM
Genetic algorithms are the search algorithms that have been evolved from th eevolution
observed in nature, namely the proess of natural selection, genetisc and survival of the fittest.
The main operators include:selection, fitness function, reproduction, crossover, mutation[8]
etc.,
Shaik Bepari Fayaz Basha and K. Madhavi Latha
http://www.iaeme.com/IJCIET/index.asp 1375 [email protected]
3.1. Implementation of Genetic Algorithm in Matlab
Figure 5 Flow chart for the developed GA optimization model[9]
MATLAB, an acronym for MAT-rix LAB-oratory, is a very effective technical language
for mathematical programming. It offers a broad form of options that are useful to a designer
who utilises GA and to those who want to experiment with optimization using genetic
algorithms to learn about possible applications. The step-by-step procedure followed in
Genetic Algorithm is shown by the flow chart in fig.5
4. RESULTS
Reinforced concrete simply supported one way slab and cantilever slab are studied by making
valid generated GA programs, the results obtained are compared with the previous work.
4.1. Reinforced Concrete One Way Slab Problem
The loading diagram considered for the slab is as shown in fig. 6
Design Optimization of Reinforced Concrete Slabs Using Genetic Algorithms
http://www.iaeme.com/IJCIET/index.asp 1376 [email protected]
Figure 6 The RC one way slab numerical example
4.1.1. The Fixed Parameters
Span of the slab is 3.96 m
Uniformly distributed load of 1.34 kN/m2
Characteristic cube strength of the concrete fck= 20.68 MPa
Cost of concrete, Cc = 610 (Rs. /m3)
Characteristic strength for the steel fy = 275.8 MPa
Cost of steel bars, Cs =95.2809 (Rs. /kg).
Solution
The above problem is solved using Genetic algorithm coding and the results obtained are as
follows: Cost = 1650.34 Rs. /m
d = 167.80 mm pt = 0.3738% sv = 262.9 mm This study is compared with one of the previous works
Cost = 1770.36 Rs. /m
d = 158.75 mm
pt = 0.42%
sv = 220 mm
The optimal cost obtained by genetic algorithm coding is compared with the optimal cost
obtained by one of the previous works and it is observed that former showed a reduction of
6.78% in total cost.
4.2. Reinforced Concrete Cantilever Slab Problem
The loading diagram considered for the slab is as shown in fig. 7
Figure 7 The RC cantilever slab numerical example
Shaik Bepari Fayaz Basha and K. Madhavi Latha
http://www.iaeme.com/IJCIET/index.asp 1377 [email protected]
4.2.1. The Fixed Parameters
Span of the slab is 3.96 m
Uniformly distributed load of 1.34 kN/m2
Characteristic cube strength of the concrete fck= 20.68 MPa
Characteristic strength for the steel fy = 275.8 MPa
Cost of concrete, Cc = 610 (Rs. /m3)
Cost of steel bars, Cs =95.2809 (Rs. /kg).
Solution
The above problem is solved using Genetic algorithm coding and the results obtained are as
follows: Cost = 3204.05 Rs. /m d = 343.90 mm
pt = 0.3907% sv = 191.8 mm This study is compared with one of the previous works
[10]
Cost = 3951.83 Rs. /m d = 317.50 mm
pt = 0.54% sv = 127.0 mm
The optimal cost obtained by genetic algorithm coding is compared with the optimal cost
obtained by one of the previous works and it is observed that former showed a reduction of
18.92% in total cost.
4.3. Effect of Change of Mutation, Generation and Population
Input data for design problem
Span of the slab is 4 m
Uniformly distributed live load of 3 kN/m2
The characteristic cube strength for concrete fck= 20 MPa
The characteristic yield strength of steel fy = 415 MPa.
Output: For 100 generation, 100 population size, and 0.01mutation.
The optimum cost value for one way slab is shown in fig: 8
Figure 8 Showing the optimum cost value for one way slab
Design Optimization of Reinforced Concrete Slabs Using Genetic Algorithms
http://www.iaeme.com/IJCIET/index.asp 1378 [email protected]
The optimum cost value for cantilever slab is shown in fig: 9
Figure 9 Showing the optimum cost value for cantilever slab
4.3.1. The Number of Generations
A study is carried out by changing the number of generations while making the other values
as unchanged as follows:
The number of population size = 100, and the mutation rate = 0.01, the method of
selection is selected as Roulette Wheel function.
fig.10 and fig.11 shows the results of changing the number of generations for both the
slabs.
Figure 10 No. of generations vs. Optimum cost for one way slab
6336.35
6326.63
6319.93 6319.93
6318
6320
6322
6324
6326
6328
6330
6332
6334
6336
6338
20 40 60 80 100
Op
tim
um
cost
(R
s.)
Generations
fck = 20 N/mm², fy = 415 N/mm²
Shaik Bepari Fayaz Basha and K. Madhavi Latha
http://www.iaeme.com/IJCIET/index.asp 1379 [email protected]
Figure 11 No. of generations vs. Optimum cost for cantilever slab
4.3.2. The Population Size
A study is carried out by changing the population size while making the other values as
unchanged as follows:
The number of generations = 100, and the mutation rate = 0.01, the method of selection is
selected as Roulette Wheel function.
fig.12 and fig.13 showing the outcomes by changing the number of population size for
both the slabs.
Figure 12 Population size vs. Optimum cost for one way slab
10525.8
10518.6
10515.4 10513.52
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
20 40 60 80 100
Op
tim
um
cost
(R
s.)
Generations
fck = 20 N/mm², fy = 415 N/mm²
6369.24
6337.81
6321.41 6319.93
63186322632663306334633863426346635063546358636263666370
20 40 60 80 100
Op
tim
um
cost
(R
s.)
Population size
fck = 20 N/mm², fy = 415…
Design Optimization of Reinforced Concrete Slabs Using Genetic Algorithms
http://www.iaeme.com/IJCIET/index.asp 1380 [email protected]
Figure 13 Population size vs. Optimum cost for cantilever slab
4.3.3. Mutation Rate
A study is carried out by changing the mutation rate while making the other values as
unchanged as follows:
The number of generations = 100, and the number of population size = 100, the method of
selection is selected as Roulette Wheel function.
fig.14 and fig.15 showing the outcomes by changing the mutation rate for both the slabs
Figure 14 Mutation rate vs. Optimum cost for one way slab
10550.5
10526.9
10520.6
10513.52
10512
10516
10520
10524
10528
10532
10536
10540
10544
10548
10552
20 40 60 80 100
Op
tim
um
cost
(R
s.)
Population size
fck = 20 N/mm², fy = 415 N/mm²
6336.35
6319.93
6320.57 6321.34
6322.17
6318
6320
6322
6324
6326
6328
6330
6332
6334
6336
6338
0 0.02 0.04 0.06 0.08 0.1Op
tim
um
cost
(R
s.)
Mutation Rate
fck = 20 N/mm², fy = 415 N/mm²
Shaik Bepari Fayaz Basha and K. Madhavi Latha
http://www.iaeme.com/IJCIET/index.asp 1381 [email protected]
Figure 15 Mutation rate vs. Optimum cost for cantilever slab
4.4. Effect on Optimum Cost by Changing the Constant Parameters
The effect on the optimum cost value by changing the constant parameters is observed using
illustrated problems of both the RC one way and the cantilever slab.
4.4.1. Effect of Variation in Grade of Concrete and Steel
By changing the value of the compressive cube strength of the concrete and for the steel, there
will be correspondingly change in the unit cost of the concrete and steel. In this region genetic
algorithm programs are applied for different values of the compressive cube strength of the
concrete and for the steel and the respective obtained optimum values of the solution is
studied. The changing values of concrete are 20 and 25 MPa and for steel the changing values
are 415 and 500 MPa for the RC one way slab and cantilever examples.
The results of the illustrated problems shown in fig.16 and fig.18 subsequently for a
particular load is studied and by changing loading values the effect of variation in grade of
concrete and steel is studied in fig.17 and fig.19 respectively for both the simply supported
RC one way and cantilever slabs.
Input Data for Design Problem
Span of the slab is 4 m
Uniformly distributed live load of 3,5 and 7 kN/m2
The characteristic cube strength for concrete fck= 20 and 25 MPa
The characteristic yield strength of steel fy = 415 and 500 MPa.
10537.6
10513.52
10515.3 10517
10527
1051210514105161051810520105221052410526105281053010532105341053610538
0 0.02 0.04 0.06 0.08 0.1Op
tim
um
cost
(R
s.)
Mutation rate
fck = 20 N/mm², fy = 415 N/mm²
Design Optimization of Reinforced Concrete Slabs Using Genetic Algorithms
http://www.iaeme.com/IJCIET/index.asp 1382 [email protected]
Figure 16 Effect of variation of grade of concrete and steel (RC one way slab)
Figure 17 Effect of variation of grade of concrete and steel for different loading values (RC one way slab)
Figure 18 Effect of variation of grade of concrete and steel (RC cantilever slab)
6319.93
6238.82
6370.27
6306.34
6000
6050
6100
6150
6200
6250
6300
6350
6400
For load 3 kN/mm²
Op
tim
um
cost
(R
s.)
fck = 20 N/mm², fy = 415 N/mm²
fck = 20 N/mm², fy = 500 N/mm²
6000
6100
6200
6300
6400
6500
6600
6700
6800
6900
7000
3 5 7
Op
tim
um
cost
(R
s.)
Load in kN/mm² fck = 20 N/mm², fy = 415 N/mm² fck = 20 N/mm², fy = 500 N/mm²
fck = 25 N/mm², fy = 415 N/mm² fck = 25 N/mm², fy = 500 N/mm²
10513.52
10416.86
10687.46
10593.84
10250
10300
10350
10400
10450
10500
10550
10600
10650
10700
10750
For load 3 kN/mm²
Op
tim
um
cost
(R
s.)
fck = 20 N/mm², fy = 415 N/mm² fck = 20 N/mm², fy = 500 N/mm²
fck = 25 N/mm², fy = 415 N/mm² fck = 25 N/mm², fy = 500 N/mm²
Shaik Bepari Fayaz Basha and K. Madhavi Latha
http://www.iaeme.com/IJCIET/index.asp 1383 [email protected]
Figure 19 Effect of variation of grade of concrete and steel for different loading values (RC cantilever slab)
4.4.2. Cost Optimization Results for Different Span Lengths
Two problems of the reinforced concrete slabs are studied by changing the support conditions.
Problem 1 is a reinforced concrete simply supported slab. Problem 2 is a reinforced concrete
cantilever slab. The present study investigates the effect of slab span length on optimal design
variables[12],
the cost components and optimal reinforcement ratio.
Total cost obtained for two examples for different span lengths for different loading
values are presented in fig.20, fig.22 and fig.24. Steel reinforcement ratio obtained for two
examples for different span lengths for different loading values are presented in fig.21, fig.23
and fig.25
It should be noted that cantilever slabs are rarely used in high span lengths and for most
practical span lengths (3-4 m). [11]
Input Data for Design Problem
Span of the slab is 3,3.5,4,4.5,5 and 5.5,
Uniformly distributed live load of 3,5 and 7 kN/m2,
The characteristic cube strength for concrete fck= 20 MPa,
The characteristic yield strength of steel fy = 415 MPa.
Figure 20 Optimum cost for one way and cantilever slabs for different span lengths (For load 3kN/mm2)
9800
10000
10200
10400
10600
10800
11000
11200
11400
11600
3 5 7
Op
tim
um
cost
(R
s.)
Load in kN/mm² fck = 20 N/mm², fy = 415 N/mm²
fck = 20 N/mm², fy = 500 N/mm²
1500
4000
6500
9000
11500
14000
16500
19000
21500
24000
3 3.5 4 4.5 5 5.5
Op
tim
um
cost
(R
s.)
Span length(m)
one way slab cantilever
Design Optimization of Reinforced Concrete Slabs Using Genetic Algorithms
http://www.iaeme.com/IJCIET/index.asp 1384 [email protected]
Figure 21 Optimum reinforcement ratio for one way and cantilever slabs for different span lengths
(For load 3kN/mm2)
Figure 22 Optimum cost for one way and cantilever slabs for different span lengths (For load 5kN/mm2)
Figure 23 Optimum reinforcement ratio for one way and cantilever slabs for different span lengths (For load 5kN/mm2)
0.25
0.26
0.27
0.28
0.29
0.30
0.31
3 3.5 4 4.5 5 5.5
Op
tim
um
rei
nfo
rcem
ent
rati
o
(%)
Span length(m)
one way slab cantilever
1500
4000
6500
9000
11500
14000
16500
19000
21500
24000
3 3.5 4 4.5 5 5.5
Op
tim
um
cost
(R
s.)
Span length(m)
one way slab cantilever
0.28
0.29
0.30
0.31
0.32
0.33
0.34
0.35
0.36
0.37
0.38
0.39
3 3.5 4 4.5 5 5.5
Op
tim
um
rei
nfo
rcem
ent
rati
o
(%)
Span length(m)
one way slab cantilever
Shaik Bepari Fayaz Basha and K. Madhavi Latha
http://www.iaeme.com/IJCIET/index.asp 1385 [email protected]
Figure 24 Optimal cost for one way and cantilever slabs for different span lengths (For load 7kN/mm2)
Figure 25 Optimum reinforcement ratio for one way and cantilever slabs for different span lengths (For load
7kN/mm2)
5. CONCLUSIONS
It was observed that when the no. of generations and population size is smaller the obtained
value of the GA codes for the both the slabs show far away from the optimum value of the
solution and the best optimum value is obtained by changing the generation value to 100 after
this value also there is no change in this best solution.
Mutation rate plays an important role in the genetic algorithm process. It was shown that
without and with larger values of mutation rate the obtaining solution is far away from the best
obtained solution and at value of 0.01 mutation rate the optimum solution is obtained.
In this study the illustrated examples are accomplished which shows that the total cost of slab
increases when there is increase in characteristic strength of concrete, while fixing the applied
load and grade of steel.
In this study the illustrated examples are applied which shows that while there is increase in
grade of the steel, there will be decrease in the optimum cost value while fixing the applied
load and compressive strength of concrete.
1500
4000
6500
9000
11500
14000
16500
19000
21500
24000
3 3.5 4 4.5 5 5.5Op
tim
um
co
st (
Rs.
)
Span length(m)
one way slab cantilever
0.300.310.320.330.340.350.360.370.380.390.400.410.420.430.440.450.46
3 3.5 4 4.5 5 5.5Op
tim
um
rei
nfo
rcem
ent
rati
o (
%)
Span length(m)
one way slab cantilever
Design Optimization of Reinforced Concrete Slabs Using Genetic Algorithms
http://www.iaeme.com/IJCIET/index.asp 1386 [email protected]
The optimum cost for the both the slab is achieved by M20 grade of concrete and Fe500 grade
of steel.
Cantilever slab has the maximum total cost among the two examples. It should be noted that
cantilever slabs are rarely used in high span lengths and for most practical span lengths (3-4
m).
As expected in all examples the optimum value of the cost at higher span lengths increases
predominantly.
The percent reduction in optimum reinforcement ratio for the slab is directly proportion to
number of span length increases.
On comparison with an earlier literature related to cost optimization of reinforced concrete
slabs, it was concluded that there was cost reduction of 6.78% and 18.92% for the RC one way
and cantilever slab respectively.
REFERENCES
[1] Chakrabarty, B.K., (1992), “A model for optimal design of reinforced concrete beams”,
Asian Journal of Civil Engineering, Vol. 118, pp. 3238-3242.
[2] IS 456-2000, “Code of Practice for Plain and Reinforced Concrete”, Bureau of Indian
Standards, New Delhi.
[3] Saini, B., Sehgal, V.K., and Gambhir, M.L., (2006), “Genetically optimized artificial
neural network based optimum design of singly and doubly reinforced concrete beams”,
Asian Journal of Civil Engineering, Building and Housing, Vol.7, pp. 82-97.
[4] Sahab, M.G., Ashaour, A.F., and Toropov, V.V., (2004), “Cost optimization of
reinforced concrete flat slab buildings”, Engineering Structures, Vol.12, pp. 124 - 256.
[5] http://www.buildinghow.com/enus/Products/Books/VolumeB/Slabs/Cantilevers-one-way-
slabs.
[6] Krishna Raju, N., and Pranesh, R.N., (2003), Reinforced Concrete Design, Second
Edition, New Age International Limited, Publishers.
[7] Dutta, B.N., (1992), Estimation and Costing in Civil Engineering, Twenty fourth Edition,
UBS Publishers and Distributors Pvt.Ltd.
[8] Whitely, D., (1994), “A genetic algorithm tutorial”, Statistics and computing, Vol.4, pp.
65-85.
[9] Alqedra, M., Arafa, M., and Ismail, M., (2011), “Optimum cost of prestressed concrete
beams using genetic algorithms”, Journal of Artificial Intelligence, Vol.4, pp.76-88.
[10] Behrouz, A.N., and Hesam, V., (2011), “Minimum cost design of concrete slabs using
Particle Swarm Optimization”, World Applied Sciences Journal, Vol. 13, pp.2484-2494.
[11] Gunaratnam, D.J., and Sivakumaran, N.S., (1978), “Optimum design of reinforced
concrete slabs ", Structural Engineering, Vol.3, pp. 61 – 67.
[12] Camp, C.V., Pezeshk, S., and Hansso, H., (2003), Flexural design of reinforced concrete
frames using a genetic algorithm”, Asian Journal of Civil Engineering, Vol.23, pp. 733 –
944.
[13] Şengül CAN and Mustafa GER Şİ L, A Literature Review On The Use of Genetic
Algorithms In Data Mining. International Journal of Computer Engineering &
Technology, 8(6), 2017, pp. 67–76.
[14] Harshdeep Sharma and Gianetan Singh Sekhon, A Review on Load Balancing in Cloud
Using Enhanced Genetic Algorithm. International Journal of Computer Engineering &
Technology, 8(2), 2017, pp. 23–29.